Computational Neuroscience, Neurotechnology and Neuro-inspired AI Autumn School

08:30am -09:30am Welcome and opening speech (Liam Maguire - Pro Vice-Chancellor Research Ulster University; KongFatt Wong-Lin - Organiser; Damien Coyle - ISRC Research Director)
09:30am - 11am Introductory neuroscience (Elaine Murray)
11am - 11:15am Break
11:15am -12:45pm Cognitive neural systems and behaviour (Simon Kelly)
1pm -3pm Lunch and social activity - Derry~Londonderry city tour
3pm - 4.30pm Mathematics for neuroscience (Áine Byrne) (notes provided in advance)
4pm - 4.45pm Break
5pm - 6pm Lab 1 - Fundamentals of Python and MATLAB programming (notes provided in advance)
6:15pm Dinner

9:30am - 11am Computational modelling of plasticity and learning in brains (Cian O'Donnell)
11am - 11:15am Break
11:15am -12:45pm Ionostasis at the tripartite synapse: Computational modelling of neuronal and glial interactions (Liam McDaid; Marinus Toman)
12:45pm - 2:15pm Lunch and tour of ISRC labs
2:15pm -3:45pm Modelling the dynamics of decision-making (KongFatt Wong-Lin)
3:45pm - 4:00pm Break
4pm - 5pm Understanding behaviour and the brain from the perspective of a dynamical theory of coordination (J. A. Scott Kelso)
5pm - 5:15pm Break
5:30pm - 6:30pm Lab 2 – Modelling neurons, glial cells, neural networks & cognition
6:45pm Dinner

9:30am - 11am Investigating time series neural data: Experimental design & signal processing practises (Saugat Bhattacharyya)
11am - 11:15am Break
11:15am - 12:45pm Fundamentals of functional and effective connectivity and their applications to mental health conditions (Maria Dauvermann)
12:45pm - 2:15pm Lunch and campus tour
2:15pm - 3:45pm Non-invasive brain-computer interfaces: Enhancing applicability using computational intelligence and technological advances (Girijesh Prasad)
3:45pm - 4pm Break
4pm - 5pm Decoding mental imagery from electroencephalography (EEG) and applications of AI-enabled wearable neurotechnology for communication and rehabilitation (Damien Coyle)
5pm - 5:15pm Break
5:30pm - 6:30pm Lab 3 – Neural data processing, neural data science & applications

9:30am - 10:30am Brain-inspired spiking neural network models for life-long and explainable learning (Nikola Kasabov)
10:30am - 10:45am Break
10:45am - 11:45am Sparse reservoir computing (Eleni Vasilaki)
11:45am - 1:15pm Lunch
1:15pm - 2.45pm Building reliable and secure embedded systems with neuromorphic computing (Jim Harkin)
2:45pm - 3pm Break
3pm - 4pm Lifelong Learning AI via neuro-inspired solutions (Hava Siegelmann) [Distinguished External Speaker]
4pm - 4:15pm Break
4:15pm - 5:15pm Ethical and regulatory issues in neurotechnology (Arleen Salles)
5:30pm - 6:30pm Lab 4 – Neuro-inspired AI and applications
7:30pm Social activity - Formal dinner and Derry Halloween dressing up

9:30pm - 12:15pm Attendees’ micro-talks
12:15pm - 1:45pm Lunch
1:45pm - 2:15pm KTPs - Bridging academia and business and supercharging graduate careers (Amanda Fullerton)
2:15pm - 2:45pm Translating AI-enabled, neurotechnology research and experiences of developing an award winning neurotech startup (Damien Coyle, NeuroCONCISE)
2:45pm - 3pm Break
3pm - 3:30pm Time series analytics of IoT sensor data - An industry challenge perspective (Mark Gorman)
3:30pm - 3:45pm Prize-giving for attendees' micro-talks
3:45pm - 4pm Closing remarks

Elaine Murray

Elaine Murray is a Lecturer in Personalised Medicine (Mental Health) at Ulster University. She received her undergraduate degree in Biomedical Sciences from Ulster University and her PhD in Neuroscience and Behaviour at the University of Massachusetts, Amherst, where she demonstrated that perinatal disruption of histone acetylation leads to long lasting changes in sexually dimorphic regions of the brain. She then joined the Translational Neuroscience group at the University of Aberdeen as a research fellow, where she worked on the genetic basis of major mental illness as part of a Pfizer Neuroscience Grand Challenge project. Elaine returned to Northern Ireland in 2013 to take up her current post within the Northern Ireland Centre for Stratified Medicine.

Elaine's current research focuses on identifying novel biomarkers to improve diagnosis and treatment of psychiatric disorders. Elaine is a council member of Neuroscience Ireland, Northern Ireland local group representative for the British Neuroscience Association and is currently leading a CHITIN project investigating mental health among at-risk young people in a cross-border region funded by the EU’s INTERREG VA Programme.

Lecture title

Introductory neuroscience

Synopsis

This session will provide an overview of the structure and function of the nervous system. The lecture will start with a review of the divisions of the nervous system and the main cell types, neurons and glia. An introduction to basic neuroanatomy will follow covering key external and internal structures of the brain and the main components of systems controlling movement, learning and memory, and emotional regulation. To understand neuronal processes and pathologies it is important to understand how neurons work. An overview of the action potential, the electrical signal used by neurons to carry information to their target, will be provided. Finally, the main steps involved in synaptic transmission, including the neurotransmitters responsible for chemical signalling in the nervous system, will be reviewed.

Simon Kelly

Simon Kelly is an Associate Professor in the School of Electrical and Electronic Engineering at University College Dublin. In his research he studies the perceptual and cognitive brain processes that allow people to interact effectively with their environment. He mainly employs a combination of electrophysiology, psychophysics and computational modelling to study the neural computations underlying perception, attention and decision making.

Simon received his B.E. and Ph. D. degrees in Engineering from UCD in 2001 and 2005, respectively. He then worked as a postdoctoral researcher in the Nathan S. Kline Institute for Psychiatric Research, New York, and in the Columbia University Department of Neuroscience, and held an Assistant Professor position in the Department of Biomedical Engineering in the City College of the City University of New York for four years before joining UCD in Jan 2015.

Lecture title

Cognitive neural systems and behaviour

Synopsis

Our knowledge of the brain processes underlying perception, cognition and action has come from research using a spectrum of levels of analysis from the molecular, through single neurons and circuits, to behaviour. This lecture provides an introduction to the behavioural end of this spectrum. I will give a broad overview of basic methods of psychophysics - the systematic measurement of behaviour - and how these methods provide insights into properties and mechanisms of the neural systems for basic sensation and for cognitive functions such as attention, decision making and memory and learning.

I will discuss how the principled measurement of behaviour helps to make sense of even the lowest-resolution forms of neural activity measurements amenable to human research, and conversely, how such neural activity measurements, once well-characterised functionally, can inform simple mathematical models that capture not just the observed patterns of behaviour but also the underlying algorithms the brain is using to generate them. A core thread running through all of these themes will be the importance of careful task design - what we ask our subjects to do and under what conditions.

Áine Byrne

Áine Byrne is an Assistant Professor in the School of Mathematics and Statistics, at University College Dublin. She obtained her PhD from the University of Nottingham in 2017, before receiving a Swartz Fellowship for her postdoctoral studies at the Center for Neural Sciences, New York University.

Her research focus is coarse-grained models of neural activity. Starting with large networks of interacting neurons, she employs mean-field techniques to arrive at low-dimensional descriptions of these systems. Her next generation neural mass model successfully links the average population activity to the level of synchronisation within the underlying network of neurons, providing an explicit link between the microscopic and macroscopic dynamics. Byrne employs this model to study event-related changes in EEG/MEG spectral power and neurological disorders, such as schizophrenia, epilepsy and Parkinson’s disease.

Lecture title

Mathematics for neuroscience: An overview

Synopsis

The use of mathematics has many historical successes, particularly in the realm of physics and engineering, where mathematical concepts are regularly employed to address challenges far beyond the context in which they were originally developed. More recently, mathematics has been employed to further our understanding of biological systems, such as the brain. Despite the immense complexity of the brain, mathematical modelling has allowed for major advances to be made towards understanding behaviour, consciousness and disease. This lecture introduces the mathematical tools needed for mathematically modelling the brain. We will review concepts from linear algebra, vector calculus and differential equations. We will learn how to describe neural systems using differential equations and how to simulate these equations computationally.

Cian O’Donnell

Cian O’Donnell did a B.Sc. in Applied Physics at Dublin City University, followed by an M.Sc. and Ph.D. in Neuroinformatics at University of Edinburgh where he studied biophysical models of electrical noise and synaptic plasticity in single neurons. He then worked for 3 years as a postdoc in the Salk Institute in La Jolla, California modelling synaptic plasticity in neural circuits, and analysing neural population activity data from mouse models of autism. From 2015-2021 he was a lecturer at the University of Bristol, then in October 2021 he joined Ulster University at Magee as a Lecturer in Data Analytics. His research group has 3 postdoctoral RAs and 6 PhD researchers, working on three topics: 1) learning and memory in the brain; 2) neural circuit dysfunction in autism; 3) statistical methods for neuroscience data.

Visit Cian's website

Lecture title

Computational modelling of plasticity and learning in brains

Synopsis

This lecture will introduce the basics of how we think learning works in the brain, and common computational models of synaptic plasticity at the single synapse, single neuron, and neural circuit levels. It will cover classic models of Hebbian plasticity, spike-timing-dependent plasticity, and attractor networks. Finally, we will briefly discuss modern attempts to link brain learning to backpropagation and deep learning in artificial neural networks.

Liam McDaid

Liam McDaid, BEng, PhD (Liverpool), is Professor of Computational Neuroscience at Ulster University. His research focuses on hardware/software implementations of neural based computational systems with particular emphasis on modelling glia-neural interactions. He has secured funding from Higher Education Authority of Ireland, which focuses on inter-neuron on-chip communications and was Co-PI for the EPSRC project (EP/F05551X/1) to develop compact low power spiking neuron cells. Prof. McDaid was PI for a recent EPSRC eFutures (EFXD12011) project and CI on SPANNER (EP/N00714X/1). He also secured funding from the Human Science Frontiers Programme (HFSP) to model G-Protein signaling in astrocytes. He is guest editor for a special issue in the International Journal of Neural Systems and has co-authored over 120 publications.

Marinus Toman

Marinus Toman received a B.Sc. (Hons.) degree in Cloud Computing from Letterkenny Institute of Technology, Donegal, Ireland in 2018, and a PhD degree in Computational Neuroscience as part of the Computational Neuroscience and Neural Engineering Research Team at Ulster University, Derry, Northern Ireland in 2022. His primary research interests include modelling of glial and neuronal cells in the brain to investigate how memory and learning occurs at a cellular level in the brain. His other research interests include computer science, specifically indoor positioning and localisation.

Lecture title

Ionostasis at the tripartite synapse: Computational modelling of neuronal and glial interactions

Synopsis

Computational models of neuro-glia interactions are an important tool for researchers studying different levels of the central nervous system; from network level to single cell and sub-cellular. Astrocytes are the most abundant glial cell in the brain and in many brain regions, they come in close proximity to synapses and provide supporting roles like homeostasis. The tripartite synapse is a recent concept that acknowledges both the close proximity and the important contribution of astrocytes to neuronal synapses. The tripartite synapse is currently too small a region for experimentalists to probe, therefore, computational models of the tripartite synapse can provide an insight, and possibly predictions, into the signalling dynamics between astrocytes and neurons at the point of information transfer between neurons.

In this tutorial, we will construct a neuron-astrocyte model of ionic homeostasis (ionostasis) at the tripartite synapse, using the MATLAB language. First, the popular Hodgkin-Huxley action potential model will be solved using MATLAB’s built-in ODE solver. Then, an astrocyte model will be constructed and solved using Euler’s method. The full model will be simulated and results plotted to show the neuron-astrocyte interactions during periods of neuronal activity. By the end of the tutorial, participants will be familiar with some computational modelling techniques and will leave with a working model of astrocytic ionostasis at the tripartite synapse.

KongFatt Wong-Lin

KongFatt Wong-Lin is a Reader at the Intelligent Systems Research Centre, School of Computing, Engineering and Intelligent Systems, Ulster University. Dr. Wong-Lin's research interests lie at the interface of computational modelling and mathematical analysis of systems and cognitive neuroscience, psychology, brain disorders, neural computation and engineering, AI and data science. Dr. Wong-Lin is Editorial Member for the Journal of Neuroscience Methods, and Associate Editor for Frontiers in Integrative Neuroscience.

Before joining Ulster University, he was a research associate at Princeton University, USA, with affiliation to The Program in Applied and Computational Mathematics, Center for the Study of Brain, Mind and Behavior, and Princeton Neuroscience Institute. Prior to that, he received his Ph.D. in Physics with focus on Computational Neuroscience at Brandeis University, USA, with affiliation to the Volen National Center for Complex Systems. He received the 2011 IJCNN Best Paper Award (Overall), the 2016 Ulster University's Distinguished Research Fellowship Award, and the 2019 Ulster University Research Excellence Award. In 2017, he received the Moore Institute Visiting Research Fellowship at the National University of Ireland Galway, and in 2020, a Visiting Fellowship at University College at the University of Oxford.

Lecture title

Modelling the dynamics of decision-making

Synopsis

This lecture will first discuss neural network models that are conducive for theoretical analysis and conceptual understanding. Then examples of how different neural network dynamics can be linked to different cognitive functions will be discussed. A primary focus will be on understanding the network mechanism of decision-making, and how they can be adapted to produce different decision-making behaviour.

J. A. Scott Kelso

Bio: Scott Kelso’s research aims to understand how human beings (and human brains)—individually and together—control and coordinate their behavior on multiple levels, from cells to cognition to (most recently) social settings. Kelso’s approach is to look for commonalities and differences in the way such complex systems are coordinated across scales with the goal of identifying common principles and mechanisms—an empirical, theoretical and computational modeling framework called Coordination Dynamics. From 1978 to 1985 Kelso was Senior Research Scientist at Yale University’s Haskins Laboratories in New Haven, Connecticut.

Since then, he has held the Glenwood and Martha Creech Eminent Scholar Chair in Science at Florida Atlantic University (FAU) in Boca Raton, Florida where he founded The Center for Complex Systems and Brain Sciences, obtaining the first NIH National Training Grant in this new interdisciplinary field. Kelso is also a Professor at The University of Ulster’s Intelligent Systems Research Centre in his hometown of Derry where he continues to collaborate with colleagues and students. In 2016, Kelso was elected an Honorary Member of The Royal Irish Academy (Hon. MRIA). Trained in a specifically interdisciplinary setting, Kelso’s PhD students and Postdoctoral fellows have gone on to careers in some of the top academic and research institutions in the world.

Talk title

Understanding behaviour and the brain from the perspective of a dynamical theory of coordination

Synopsis

What does it mean to “understand” a phenomenon regardless of the level of description one chooses to investigate it (e.g., micro-, meso-, macro- etc.)? Given that the usual categories of describing behaviour and cognition are suspect with respect to their neural underpinnings (see, e.g. “The brain doesn’t think the way you think it does”, Quanta, August 24, 2021 ), the focus here will be on coordination -- assumed to be crucial for complex systems regardless of how we categorize behavioral and cognitive function and their relation to structure. In that context, we will explore some of the main concepts, methods and messages of Coordination Dynamics. I offer a strategy aimed at understanding coordination and show how it can be implemented at both behavioral and brain levels.

Saugat Bhattacharyya

Saugat Bhattacharyya is a Lecturer in Computer Science in the School of Computing, Engineering & Intelligent Systems. His research interests are in the area of Cognitive Neuroscience, Artificial Intelligence, Data Analytics and Machine Learning and its application in Human-Machine Interaction and Neuro-Rehabilitation. His research is primarily focussed on developing brain-computer interfacing systems based on robust signal processing, quantitative and machine learning algorithms to draw inference into an users' state of mind through their neural and other physiological signals.

He has publications in 17 peer-reviewed journals, 32 international/national conferences, and 17 book chapters. He is also a recipient of GCRF pump-priming as co-investigator in and two PhD fellowships by CSIR, India and Erasmus Mundus. He is also an associate editor/section board member in Frontiers in Medical Technology and MDPI Brain Sciences, and served as guest editors in Frontiers in Neuroscience, MDPI Sensors and International Conference on Intelligent Robots and Systems (IROS).

Lecture title

Investigating time series neural data: Experimental design & signal processing practises

Synopsis

Recent advances in neuroscience technologies have paved the way to innovative applications in healthcare, rehabilitation, biometrics and brain-computer interfacing. These technologies are tuned to observe and influence brain activity to augment or assist in human motor or cognitive development. The neural activities are recorded using invasive or no-invasive technologies, albeit non-invasive technologies, such as electroencephalography (EEG), magnetoencephalography (MEG), functional near-infrared spectroscopy (fNIRS) and functional magnetic resonance imaging (fMRI) are the most popular form of recording amongst researchers and users. Non-invasive neural signals recorded from EEG or MEG devices are non-stationary, complex signals.

Hence, it is vital to follow standard experiment design practices to evoke or induce the necessary task response among users and apply time-/frequency-/time-frequency domain processing methods to extract meaningful information about those task responses from the neural signals (EEG/MEG).

In this lecture, you will be introduced to some standard practices and consideration while designing an experiment involving EEG/MEG recording, necessary pre-processing methods including temporal and spatial filtering, and artefact removal, and finally signal processing using time-frequency and inter-trial phase clustering techniques.

Maria Dauvermann

Maria Dauvermann is Assistant Professor in Youth Mental Health in the Institute for Mental Health at University of Birmingham. Her research focusses on the identification of risk and resilience markers in young people who are at high risk of developing neurodevelopmental and mental health conditions, and is also interested in the characterisation of biopsychosocial prognostic markers of clinical and functional outcome. She uses cognitive neuroscientific and interdisciplinary methods to integrate neurobiological, psychological and psychosocial factors to better understand how youth vulnerability can influence and be influenced by neurodevelopmental and mental health conditions.

Lecture title

Fundamentals of functional and effective connectivity and their applications to neurodevelopmental and mental health conditions

Synopsis

Progress in functional brain imaging allows us to noninvasively investigate human brain activity in vivo with optimised spatial and temporal resolution. Such neural maps enable the examination of functional large-scale networks leading to a better understanding of cognitive functions. For optimised clinical practice, greater insight into functional networks in individuals with mental health conditions is important since it is thought that dysfunctional networks may underlie clinical symptoms and cognitive deficits in neurodevelopmental disorders, such as psychosis and autism spectrum disorders.

In the first part of this lecture, I will discuss the theoretical basis of functional connectivity and provide an overview of different approaches across neuroimaging techniques of functional Magnetic Resonance Imaging (fMRI), electroencephalogram (EEG) and magnetoencephalogram (MEG). In the next step, I will cover the fundamentals of effective connectivity and different methodologies across fMRI, EEG and MEG. Advantages and disadvantages of both functional and effective connectivity will be discussed. Then, functional and connectivity approaches during resting state and cognitive tasks will be reviewed focussing on psychosis and autism spectrum disorders. This will be followed by a discussion of how functional and effective connectivity may contribute to clinical and cognitive diagnostic, predictive and treatment interventions in neurodevelopmental and mental health conditions.

Girijesh Prasad

Girijesh Prasad is Professor of Intelligent Systems in the School of Computing, Engineering and Intelligent Systems, Ulster University (UU), UK. He is Director of Northern Ireland Functional Brain Mapping (NIFBM) facility at UU’s Intelligent Systems Research Centre, where he leads the Cognitive Neuroscience and Neurotechnology research team. He received a BTech in Electrical Engineering from Regional Engineering College (now National Institute of Technology) Calicut, India in 1987, an MTech in Computer Science and Technology from University of Roorkee (now Indian Institute of Technology Roorkee), India in 1992, and a PhD in Electrical Engineering from Queen's University of Belfast, UK in 1997.

He is a Chartered Engineer, a Fellow of IET, a Fellow of Higher Education Academy, a Senior Member of IEEE, and a founder member of IEEE Systems, Man, and Cybernetics Society’s Technical Committee on Brain-Machine Interface Systems as well as Brain-Computer Interface (BCI) Society. In 2017, he was awarded the Fellowship of International Academy of Physical Sciences and the Senior Distinguished Research Fellowship of Ulster University.

His research interests are in intelligent systems, data engineering, brain modelling, brain-computer interface (BCI) & neuro-rehabilitation, and assistive technology. Under his supervision, an advanced rehabilitation protocol has been developed incorporating an active physical practice stage followed by a mental practice stage, using a neuro-rehab system consisting of a robotic hand exoskeleton and an EEG/EEG-EMG based BCI, which has been trialled on groups of chronic stroke patients in UK as well as India, resulting in transformative change in patients’ quality of life.

He has published over 285 research papers in journals, edited books, and conference proceedings. He has supervised to completion 22 PhD students. His research has attracted 18 research grant awards amounting to over £10M funding from national and international agencies including Invest Northern Ireland, Department of Employment and Learning, Research Councils UK (RCUK), Leverhulme Trust, Royal Society, UK India Education and Research Initiative (UKIERI), UK Research and Innovation (UKRI) and Irish industry.

Lecture title

Non-invasive brain-computer interfaces: Enhancing applicability using computational intelligence and technological advances

Synopsis

A Brain-Computer Interface (BCI), also known as Brain-Machine Interface (BMI), utilizes neuro-physiological correlates of voluntary mental tasks to facilitate direct communication between human brain and computing devices without the involvement of neuro-muscular pathways. The BCI research is, in general, progressing in two main areas: augmentative & alternative communication (AAC) by replacing neuro-muscular pathways and neuro-rehabilitation by helping to activate desired cortical areas for targeted brain plasticity. Current BCI systems however, lack sufficient robustness and performance variability among users is quite high. One of the critical limitations is because of the non-stationary characteristics of brain’s neurophysiological responses, which makes it hard to extract time-invariant stable features unique to voluntary mental tasks.

In this talk, the presentation will first briefly review state-of-the-art BCI research and then discuss our computational intelligence supported R&D towards robust BCI design using multi-modal neuroimaging techniques and our current application focus in post-stroke neuro-rehabilitation.

In particular, it will be discussed how integrating an EEG-EMG based BCI and hand exoskeleton results into a personalized post-stroke neuro-rehabilitation system that ensures active and engaging exercises and leads to enhanced recovery of the paralysed upper limbs. Also to take advantage of MEG’s highest spatiotemporal resolution (306 channels, Elekta Neuromag® TRIUX, recorded at 1k Hz) of all neuroimaging modalities, the development of an MEG-based BCI controlling an MEG compatible hand exoskeleton located in a magnetically shielded room (MSR) will be discussed. It will be discussed how using multi-modal neuroimaging modalities facilitates understanding the neuronal mechanisms involved in motor recovery of stroke patients. Finally the remaining R&D challenges will be highlighted.

Damien Coyle

Damien Coyle, Professor of Neurotechnology, is Director of the Intelligent Systems Research Centre at Ulster University’s Magee Campus. He has published over 150 research papers in areas such as computational intelligence/AI, bio-signal processing, computational neuroscience, neuroimaging, neurotechnology and brain-computer interface (BCI) applications and has won a number of prestigious international awards for his R&D including the 2008 IEEE Computational Intelligence Society (CIS) Outstanding Doctoral Dissertation Award, the 2011 International Neural Network Society (INNS) Young Investigator of the Year Award and the IET and E&T Innovation of the Year Award 2018.

He was an Ulster University Distinguished Research Fellow in 2011, a Royal Academy of Engineering/The Leverhulme Trust Senior Research Fellow in 2013, a Royal Academy of Engineering Enterprise Fellow in 2016-2017 and is currently a UKRI Turing AI Fellow 2021-2025. He is a founding member of the International Brain-Computer Interface Society, a Senior member of the IEEE, chairs the IEEE Computational Intelligence Society (CIS) UK Ireland chapter, is the IEEE CIS representative and member on the steering committee of the IEEE Brain Technical Community and UK KTN Neurotechnology Innovation Network advisory board member.

He is Ulster lead of the Spatial Computing and Neurotechnology Innovation Hub (SCANi-hub) and the Northern Ireland High Performance Computing Facility (NIHPC) and co-investigator in Northern Ireland Functional Brain Mapping Facility (NIFBM) and lead a number of industry led data analytics projects via Ulster’s Cognitive Analytics Research Laboratory (CARL). He is Founder and CEO of NeuroCONCISE Ltd, an award-winning, AI-enabled, wearable neurotechnology company.

Lecture title

Decoding mental imagery from electroencephalography (EEG) and applications of AI-enabled wearable neurotechnology for communication and rehabilitation

Lecture synopsis

Research in the field of brain–computer interfaces (BCIs) and neurotechnology has proven that electrical signals in the brain, modulated intentionally by mental imagery, can relay information directly to a computer, where it is translated by intelligent algorithms (some inspired by the brain’s neural networks) into control signals that enable communication and control without movement or can improve self- regulation of brain activity. This talk will present results from research at Intelligent Systems Research Centre that shows people with restricted abilities resulting from disease, injury or trauma may benefit from neurotechnology, including those who have prolonged disorders of consciousness or locked-in syndrome following traumatic brain injury, spinal injury, stroke and post-traumatic stress disorder.

Neural activity can be modulated by many kinds of mental imagery e.g., classical motor imagery BCIs distinguish between imagined hand/arm movements. This presentation will also show recent results in decoding imagined three-dimensional limb movements, imagined primitive shapes, emotion inducing imagery and silent/imagined speech from EEG. The presentation will attempt to address the question is it feasible to expect high and robust performance with these types of imagery in EEG-based BCIs and will highlight results which indicate user proficiency in BCI control is a matter of training time, machine learning/AI ability, application of the technology and maintenance of stable affective states. A number of neurogaming applications that enhance BCI user training will be demonstrated.

Nikola Kasabov

Nikola Kasabov is Life Fellow of IEEE, Fellow of the Royal Society of New Zealand, Fellow of the INNS College of Fellows, DVF of the Royal Academy of Engineering UK. He is the George Moore Chair Professor of Data Analytics at the Intelligent Systems Research Center of the University of Ulster and also Professor of Knowledge Engineering at the School of Engineering, Computing and Mathematical Sciences at Auckland University of Technology, New Zealand and a Visiting Professor at Peking University. Kasabov is the Past President of the Asia Pacific Neural Network Society (APNNS) and of the International Neural Network Society (INNS).

He is Editor of Springer Handbook of Bio-Neuroinformatics, Springer Series of Bio-and Neurosystems and Springer journal Evolving Systems. He is Associate Editor of several journals, including Neural Networks, IEEE TrNN, Tr CDS, Information Sciences, Applied Soft Computing. Kasabov holds MSc and PhD from TU Sofia, Bulgaria. His main research interests are in the areas of neural networks, intelligent information systems, soft computing, bioinformatics, neuroinformatics, bioinformatics. He has published more than 700 publications.

He has extensive academic experience at various academic and research organisations in Europe and Asia, including: TU Sofia Bulgaria; University of Essex UK; University of Otago, NZ; Advisory Professor at Shanghai Jiao Tong University and CASIA China, Visiting Professor at ETH/University of Zurich.

Prof. Kasabov has received a number of awards, among them: Honorary Professor of the University of Auckland, NZ and Teesside University UK; Doctor Honoris Causa from Obuda University, Budapest; INNS Ada Lovelace Meritorious Service Award; NN Best Paper Award for 2016; APNNA ‘Outstanding Achievements Award’; INNS Gabor Award for ‘Outstanding contributions to engineering applications of neural networks’; EU Marie Curie Fellowship; Bayer Science Innovation Award; APNNA Excellent Service Award; RSNZ Science and Technology Medal; 2015 AUT Medal; Honorary Member of the Bulgarian, the Greek and the Scottish Societies for Computer Science.

More information

Lecture title

Brain-inspired spiking neural network models for life-long and explainable learning

Synopsis

The lecture introduces the third generation of artificial neural networks, the spiking neural networks (SNN), as the latest methods and systems for neuro-inspired computation, along with their algorithms for life-long and explainable learning and numerous applications. SNN are not only capable of deep incremental learning of temporal or spatio-temporal data, but also enabling the extraction of knowledge representation from the learned data. Similarly to how the brain learns, these SNN models do not need to be restricted in number of layers, neurons in each layer, etc. as they adopt self-organising learning principles of the brain [ref. 1,2].

The lecture consists of 3 parts:
1. Fundamentals of SNN
2. Brain-inspired SNN architectures. NeuCube
3. Algorithms for life-long and explainable learning in NeuCube
4. Design and implementation of selected applications

The material is illustrated on an exemplar SNN architecture NeuCube (for free software and open source, visit the AUT Knowledge Engineering & Discovery Research Innovation website). Case studies are presented of brain and environmental data modelling and knowledge representation using incremental and transfer learning algorithms. These include: predictive modelling of EEG and fMRI data measuring cognitive processes and response to treatment; prediction dementia and AD [3]; understanding depression; predicting environmental hazards and extreme events; moving object recognition and control; brain-inspired audio-visual information processing.

It is also demonstrated that SNN allow for knowledge transfer between humans and machines through building brain-inspired Brain-Computer Interfaces (BI-BCI) [4]. These are used to understand human-to-human knowledge transfer through hyper-scanning and also to create brain-like neuro-rehabilitation robots. This opens the way to build a new type of AI systems – the open and transparent AI.

References:
1. N. K. Kasabov, "NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data," Neural Networks, vol. 52, pp. 62-76, 2014.
2. N.Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial Intelligence, Springer, 2019, (Available at Springer)
3. M. Doborjeh, …, N.Kasabov, Personalised Predictive Modelling with Spiking Neural Networks of Longitudinal MRI Neuroimaging Cohort and the Case Study for Dementia, Neural Networks, vol.144, Dec.2021, 522-539, (Available at Science Direct)
4. K.Kumarasinghe, N.Kasabov, D.Taylor, Deep Learning and Deep Knowledge Representation in Spiking Neural Networks for Brain-Computer Interfaces, Neural Networks, vol.121, Jan 2020, 169-185

Eleni Vasilaki

Eleni Vasilaki is Professor and Chair of Bioinspired Machine Learning and the head of the Machine Learning Group in the Department of Computer Science at the University of Sheffield, UK. Inspired by biology, Prof. Vasilaki and her team design novel machine learning techniques with a focus on reinforcement learning and reservoir computing. She also works closely with material scientists and engineers to design hardware that computes in a brain-like manner.

Lecture title

Sparse reservoir computing

Synopsis

"Sparse" neural networks, in which relatively few neurons or connections are active, are common in both machine learning and neuroscience. Whereas in machine learning, "sparsity" is related to a penalty term that leads to some connecting weights becoming small or zero, in biological brains, sparsity is often created when high spiking thresholds prevent neuronal activity. Here we introduce sparsity into a reservoir computing network via neuron-specific learnable thresholds of activity, allowing neurons with low thresholds to contribute to decision-making but suppressing information from neurons with high thresholds. This approach, which we term "SpaRCe", optimises the sparsity level of the reservoir without affecting the reservoir dynamics. The read-out weights and the thresholds are learned by an online gradient rule that minimises an error function on the network's outputs.

Threshold learning occurs by balancing two opposing forces: reducing inter-neuronal correlations in the reservoir by deactivating redundant neurons while increasing the activity of neurons participating to correct decisions. We test SpaRCe on classification problems and find that threshold learning improves performance compared to standard reservoir computing. SpaRCe alleviates the problem of catastrophic forgetting, a problem most evident in standard echo state networks and recurrent neural networks in general, due to increasing the number of task-specialised neurons that are included in the network decisions.

Jim Harkin

Jim Harkin holds a Bachelor of Technology, MSc and PhD in Electronic Engineering. He was employed as a post-doctoral researcher in embedded system design at Ulster for 3 years before taking up the post of Lecturer in 2004. He is currently Head of the School of Computing, Engineering and Intelligent Systems at Ulster University on the Magee Campus.

His research investigates the design of highly efficient, secure, and reliable embedded systems that emulate bio-inspired computational and fault tolerance capabilities. In particular, he focuses his efforts on the development of the brain-inspired EMBRACE architecture which aims to address electronic reliability challenges by investigating new paradigms of Networks-on-Chip interconnect and harnessing the principles of brain-like repair. His work also explores how neural networks in hardware can be used in Networks-on-Chip interconnect for security and traffic congestion awareness.

Lecture title

Building reliable and secure embedded systems with neuromorphic computing

Synopsis

The demand for increasingly more ‘intelligent’ computing systems has to be viewed through the explosion of their complexity. An important knock-on effect however, is degradation in reliability: designing reliable electronic systems is a major challenge. Self-repair is critical in hardware systems where long-term reliable performance is not guaranteed. Increasing gate densities, scaling to sub-nanometer geometries and variations in silicon manufacturing result in additional challenges. Current self-repairing hardware approaches rely on a central controller, with constraints placed on the type and number of faults (e.g. open/short-circuits) and repair granularity. There is a pressing need to progress beyond these concepts and look for inspiration from biology.

While state-of-the-art hardware devices and neuromorphic chips replicate to an extent a brain information processing paradigm, they are not fault-tolerant and can develop faults due to incorrect operations in post manufacturing, wear-out failures, or radiation effects. Nonetheless, the human brain does exhibit high levels of distributed repair and more recently it has emerged that interactions between astrocyte cells and spiking neurons provide a distributed repair paradigm that has the potential to advance progress in establishing new approaches to reliable information processing in hardware.

This lecture establishes the current challenges in capturing self-repair capabilities in electronic hardware and outlines progress in addressing the interconnect complexity in the communication of vast quantities of information while enabling large-scale hardware implementations of self-repairing neural networks. In addition, methods for the acceleration of such neural networks in hardware will be discussed and remaining challenges in future deployment. Example applications of SNNs in hardware security for prediction of traffic congestion will also be presented.

Hava Siegelmann [Distinguished External Speaker]

Hava Siegelmann is an internationally known professor of Computer Science and a recognized expert in neural networks. She is core member of the Neuroscience and Behavior Program, and director of the Biologically Inspired Neural and Dynamical Systems (BINDS) Laboratory at the University of Massachusetts. She is particularly known for her ground-breaking work in computing beyond the Turing limit, and for achieving advanced learning capabilities through a new type of Artificial Intelligence: Lifelong Learning.

Siegelmann conducts highly interdisciplinary research in next generation machine learning, neural networks, intelligent machine-human collaboration, computational studies of the brain - with application to AI, data science and high-tech industry. She is a leader in increasing awareness of ethical AI and in supporting minorities and women in AI and STEM fields all over the world.

Siegelmann has been a visiting professor at MIT, Harvard University, the Weizmann Institute, ETH, the Salk Institute, Mathematical Science Research Institute Berkeley, and the Newton Institute Cambridge University.

Her list of awards includes the Obama Presidential BRAIN Initiative award, the Donald O. Hebb Award of the International Neural Network Society (INNS) for “contribution to biological learning”; she was named a Distinguished Lecturer of the IEEE Computational Intelligence Society and was given DARPA’s Meritorious Public Service award. Siegelmann is a Fellow of both the IEEE and the INNS.

Lecture title

Lifelong Learning AI via neuro inspired solutions

Synopsis

AI embedded in real systems, such as in satellites, robots and other autonomous devices, must make fast, safe decisions even when the environment changes, or under limitations on the available power; to do so, such systems must be adaptive in real time. To date, edge computing has no real adaptivity – rather the AI must be trained in advance, typically on a large dataset with much computational power needed; once fielded, the AI is frozen: It is unable to use its experience to operate if environment proves outside its training or to improve its expertise; and worse, since datasets cannot cover all possible real-world situations, systems with such frozen intelligent control are likely to fail.

Lifelong Learning is the cutting edge of artificial intelligence - encompassing computational methods that allow systems to learn in runtime and incorporate learning for application in new, unanticipated situations. Until recently, this sort of computation has been found exclusively in nature; thus, Lifelong Learning looks to nature, and in particular neuroscience, for its underlying principles and mechanisms and then translates them to this new technology. Our presentation will introduce a number of state-of-the-art approaches to achieve AI adaptive learning, including from the DARPA’s L2M program and subsequent developments.

Arleen Salles

Arleen Salles is a Senior Researcher in philosophy at the Center for Research Ethics and Bioethics (CRB) at Uppsala University, Director of NeuroeticaBA (Buenos Aires, Argentina), a tenured professor of philosophy at Universidad Argentina de la Empresa (Buenos Aires, Argentina), Principal Investigator in FLACSO (Facultad Latinoamericana de Ciencias Sociales), and also affiliated to Weill Cornell Medical College (NY, United States). She is the Deputy Leader of the Responsible Research and Innovation Work Package of the EU-flagship Human Brain Project where she is a researcher and leads the task Neuroethics and Engagement.

She is also member of the executive board of the International Neuroethics Society, founding board member of the Institute of Neuroethics, and member of the International Brain Initiative’s Neuroethics Working Group. Salles received her M.A and Ph.D in philosophy from State University of New York at Buffalo, USA.

Salles’ scholarship focuses on: (a) the ethical, social, and epistemological issues related to neuroscientific findings and its diverse applications, (b) disciplinary issues such as the nature of neuroethics and its potential for collaborating with other disciplines, and (c) methodological issues regarding how to integrate ethical and societal considerations into brain research and emerging technologies. In particular, she is interested in responsible innovation, engagement, and the development of a culturally engaged neuroethics.

Lecture title

Ethical and regulatory issues in neurotechnology

Synopsis

The development and use of a large variety of invasive and non-invasive technologies that interface with the brain show promise in a number of contexts. At the same time, as neurotechnologies continue to advance and the range of applications increase, so has awareness of the ethical and societal issues raised, including questions about their potential impact on our belief system and our humanness itself. A few articles and documents describing salient ethical issues and articulating approaches to understanding them have been published, as have some general recommendations and guidelines intended to help find a regulatory solution to some of ethical issues raised. In this talk, I present an overview of these attempts, discussing their promises and challenges.

Amanda Fullerton

In 2004, Amanda Fullerton joined Ulster University’s Knowledge Transfer Partnerships Office (KTP) to work with Northern Ireland industry partners and the University’s research experts to help them develop high-quality, fundable, KTP proposals. Amanda was later appointed as the University’s KTP Programme Manager (2013) where her main role has been to develop and grow the University’s KTP portfolio, aligned with the University’s overall focus to stimulate and support the development of commercial partnerships between academics and businesses, with particular emphasis on research capabilities and academic resources. Amanda continues to play a leadership role in the generation and management of KTPs across the University, and to manage the business and academic relationships during the delivery of each project.

Talk title

KTPs - Bridging academia and business and supercharging graduate careers

Synopsis

For 45 years, Knowledge Transfer Partnerships (KTPs) have been helping businesses innovate for growth. They do this by connecting businesses that have an innovation idea with the university expertise to help deliver it. In effect, they link forward thinking businesses with world-class University researchers to deliver innovation projects led by inspired graduates. Ulster University has been engaged in KTP since its inception, having continuously regarded the KTP programme as an excellent pathway for generating strategic knowledge transfer opportunities with business partners to improve their performance whilst also demonstrating the impact of the University’s research.

The presentation will demonstrate the key benefits of KTPs for businesses, academic researchers and will have a particular emphasis on how the programme helps graduates in their careers by managing a challenging, innovative project central to a business’s strategic development and long term growth. The presentation will conclude with a profile of a current KTP Associate who has been selected as a finalist in the ‘Future Leaders’ category of this year’s National KTP Awards.

NeuroCONCISE / Damien Coyle

Talk title

Translating AI-enabled, neurotechnology research and experiences of developing an award winning neurotech startup

Talk synopsis

Training over multiple sessions is certainly key to learning how to modulate brain activity via a motor imagery and this involves the collection of large dataset from multiple users. An award-winning AI-enabled wearable neurotechnology platform that may enable this, developed by NeuroCONCISE Ltd, will be presented along with an overview of the challenges and opportunities of developing a neurotech startup.

Mark Gorman

Mark Gorman joined the Data Science Group (DSG) at Seagate in 2020, working on improving the value extracted from the data collected in the semiconductor wafer manufacturing process. Mark received his B.Sc. in Mathematics from Queen’s University Belfast in 2013, M.Sc. in Computational Intelligence from Ulster University in 2014 and is currently enrolled as a part-time PhD Researcher within the ISRC Ulster University, Magee campus. His Ph.D. project is focused on unsupervised anomaly detection applied to multivariate time series semiconductor multi-modal datasets. Prior to his current role in Seagate, Mark was the lead Data Scientist for The LYCRA Company, Equipment Data Scientist and Factory Analytics and Control Systems Engineer from 2014 to 2020.

Talk title

Time series analytics of IoT sensor data – An industry challenge perspective

Talk synopsis

Industry 4.0 [1] and Smart Manufacturing [2] are initiatives that accurately capture the disruption within the manufacturing sector as a result of improving technological availability and the increasing adoption rate of said technologies. Intelligent manufacturing is an important contributor to the advancement of modern industries and economies [3]. Specifically, the Semiconductor sector, with its highly competitive market, has embraced these initiatives to drive operational efficiency, yield improvement and deliver best-in-class product quality for customers. Important interconnected areas of interest are the application of Machine Learning (ML) [4] and Deep Learning (DL) [5] to datasets generated through the Industrial Internet of Things (IIOT) [6].

Time series anomaly detection is a methodology of detecting anomalous equipment operating behaviour using data collected through sensors installed within the process equipment. Application of statistical methods, ML [4] and DL [7]–[10] to large time-series datasets highlight potential faults within the system that require further Engineering scrutiny. Initially, sensors can be used to detect and contain process deviations so that stability and quality can be restored through maintenance activities.

However, signals may exist to predict and prevent fault occurrence, also referred to as Predictive Maintenance (PdM), so that Engineering teams may intervene further reducing the impact on the factory throughput and overall supply chain [11]. Furthermore, a significant challenge exists in the orchestration of models in a production environment. Model deployment, versioning, and continuous improvement in a high volume, high process mix facility requires significant resources and is the single largest restriction in continued value creation from DL and ML in the production environment. The presentation will explore Seagate’s approach to these challenges, the technologies implemented and the subsequent value creation opportunities.

References

1. J. Lenz, T. Wuest, and E. Westkämper, “Holistic approach to machine tool data analytics,” J. Manuf. Syst., vol. 48, pp. 180–191, Jul. 2018, doi: 10.1016/j.jmsy.2018.03.003.
2. H. S. Kang et al., “Smart manufacturing: Past research, present findings, and future directions,” Int. J. Precis. Eng. Manuf. - Green Technol., vol. 3, no. 1, pp. 111–128, 2016, doi: 10.1007/s40684-016-0015-5.
3. R. Y. Zhong, X. Xu, E. Klotz, and S. T. Newman, “Intelligent Manufacturing in the Context of Industry 4.0: A Review,” Engineering, vol. 3, no. 5, pp. 616–630, 2017, doi: 10.1016/J.ENG.2017.05.015.
4. Z. Ge, Z. Song, S. X. Ding, and B. Huang, “Data Mining and Analytics in the Process Industry: The Role of Machine Learning,” IEEE Access, vol. 5, pp. 20590–20616, Sep. 2017, doi: 10.1109/ACCESS.2017.2756872.
5. J. Wang, Y. Ma, L. Zhang, R. X. Gao, and D. Wu, “Deep learning for smart manufacturing: Methods and applications,” J. Manuf. Syst., vol. 48, pp. 144–156, Jul. 2018, doi: 10.1016/j.jmsy.2018.01.003.
6. D. Mourtzis, E. Vlachou, and N. Milas, “Industrial Big Data as a Result of IoT Adoption in Manufacturing,” Procedia CIRP, vol. 55, pp. 290–295, 2016, doi: 10.1016/j.procir.2016.07.038.
7. T. Ko and H. Kim, “Fault Classification in High-Dimensional Complex Processes Using Semi-Supervised Deep Convolutional Generative Models,” IEEE Trans. Ind. Informatics, vol. 16, no. 4, pp. 2868–2877, 2020, doi: 10.1109/TII.2019.2941486.
8. S. Chen, J. Yu, and S. Wang, “One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes,” J. Process Control, vol. 87, pp. 54–67, 2020, doi: 10.1016/j.jprocont.2020.01.004.
9. F. Cheng, Q. P. He, and J. Zhao, “A novel process monitoring approach based on variational recurrent autoencoder,” Comput. Chem. Eng., vol. 129, Oct. 2019, doi: 10.1016/j.compchemeng.2019.106515.
10. K. B. Lee, S. Cheon, and C. O. Kim, “A convolutional neural network for fault classification and diagnosis in semiconductor manufacturing processes,” IEEE Trans. Semicond. Manuf., vol. 30, no. 2, pp. 135–142, May 2017, doi: 10.1109/TSM.2017.2676245.
11. J. Iskandar, J. Moyne, K. Subrahmanyam, P. Hawkins, and M. Armacost, “Predictive Maintenance in semiconductor manufacturing,” 2015 26th Annu. SEMI Adv. Semicond. Manuf. Conf. ASMC 2015, pp. 384–389, 2015, doi: 10.1109/ASMC.2015.7164425.

The ISRC (MS) building is located at Magee campus (left) of Ulster University in the city of Derry~Londonderry (right), which is one of four campuses in Northern Ireland. It is the oldest campus with a history, dating back to the year 1865.

Located in the Northwest of Ireland where The Wild Atlantic Way meets the Causeway Coastal Route, the vibrant city of Derry~Londonderry is renowned for one of the finest Walled Cities in Europe and home to award winning museums, some of the islands best cultural attractions and a variety of lively festivals and events; Derry~Londonderry offers a vibrant social scene where your visitors are guaranteed the warmest of welcomes and hospitality.

For delegates looking to experience the local culture, the city walls surround cosy pubs with live music, award-winning museums that tell stories from times past, and vibrant eateries that serve up LegenDerry Food.

Address:

Intelligent Systems Research Centre
School of Computing, Engineering and Intelligent Systems
Faculty of Computing, Engineering and the Built Environment
Ulster University
Magee campus
Northland Road
Derry~Londonderry, BT48 7JL
Northern Ireland, UK

The city has ten 4-star hotels within a five mile radius of the city. centre, from award winning boutique hotels to larger hotel groups. For more information please visit the Visit Derry website. More economical options are also available.

Further information will be provided when the Autumn School's information booklet is made available.

By Air

1. City of Derry Airport

Only 7 miles from Derry~Londonderry city centre
Direct flights from London Stansted, Manchester, Liverpool, Glasgow and Edinburgh

2. Belfast City Airport

1h 30min by car/bus to Derry~Londonderry city centre

3. Belfast International Airport

1h 15min by car/bus to Derry~Londonderry city centre

4. Dublin International Airport

2h 45min from Dublin airport to Derry-Londonderry by car (3 h 45 min by bus)

Airport transfers with the Airporter (coach) is available

Car hire and taxi service are also available

By Rail

Translink

Hourly direct rail link to Belfast and connection to Dublin

Further information will be provided when the Autumn School's information booklet is made available.

Things to do

Derry~Londonderry - Avail of Visit Derry’s brand-new Visitor Pass giving you entry into 10 of the city’s most popular visitor attractions including guided walking tours. This is a great way to explore Derry’s hidden gems and take in the city’s views by foot. On the week of the Autumn School, various Derry Halloween Festival (Europe's biggest Halloween festival) activities, including fireworks, will be happening around town. For more information, visit the Visit Derry website. We hope your visit is LegenDerry!

Northern Ireland - There are many things to do in Northern Ireland, from spectacular landscapes (e.g. Giant's Causeway) and beaches to famous sites (e.g. Game of Thrones). For more information, visit the Discover Northern Ireland wesbite.

Donegal - Derry~Londonderry lies near the border with beautiful county Donegal, Republic of Ireland. For more information, visit the Go Visit Donegal website.

Computational Neuroscience, Neurotechnology and Neuro-inspired AI Autumn School

Background

The Computational Neuroscience, Neurotechnology and Neuro-inspired AI Autumn School

ISRC-CN3 Autumn School Information

Lecturers & Speakers

Organising Committee

Teaching Assistants

Schedule

Schedule

Biographies and Synopses

Biographies and Synopses

Elaine Murray

Lecture title

Synopsis

Simon Kelly

Lecture title

Synopsis

Áine Byrne

Lecture title

Synopsis

Cian O’Donnell

Lecture title

Synopsis

Liam McDaid

Marinus Toman

Lecture title

Synopsis

KongFatt Wong-Lin

Lecture title

Synopsis

J. A. Scott Kelso

Talk title

Synopsis

Saugat Bhattacharyya

Lecture title

Synopsis

Maria Dauvermann

Lecture title

Synopsis

Girijesh Prasad

Lecture title

Synopsis

Damien Coyle

Lecture title

Lecture synopsis

Nikola Kasabov

More information

Lecture title

Synopsis

Eleni Vasilaki

Lecture title

Synopsis

Jim Harkin

Lecture title

Synopsis

Hava Siegelmann [Distinguished External Speaker]

Lecture title

Synopsis

Arleen Salles

Lecture title

Synopsis

Amanda Fullerton

Talk title

Synopsis

NeuroCONCISE / Damien Coyle

Talk title

Talk synopsis

Mark Gorman

Talk title

Talk synopsis

References

Location

Map

Travel and Accomodation

Travel & Accommodation

By Air

By Rail

Things to do

Sponsors

Sponsors