IEEE International Conference on
Evolving and Adaptive Intelligent
Systems 2026 (IEEE EAIS 2026)
From 21/09/2026 To 23/09/2026
University of Pisa, Pisa, Italy
Keynote
Rethinking Adaptivity of Deep Learning
Plamen Angelov | Lancaster University, UK
Abstract
The success of deep learning fuelled by the Large Language Models (LLMs), Transformers such as ViT and Foundation Models combined with the abundance of digital data led to the temptation to short-cut from Data to Predictions bypassing the deeper insight, reasoning, semantics, causality and logic which are traditionally related to the model structure or architecture. Deep Learning the way we know it offers unparallel accuracy and generalisation, and class separability, but this comes at the cost of opaque and amorphous internal structure offering little to the increasing demands for human agency and oversight and interpretability in regards to the way the decisions are being made.
In this talk, deep learning pipeline will be re-examined and compared to the traditional machine learning pipeline on one hand and to Cognitive Sciences and Agentic AI pipeline on the other, some parallels with the Brain and the way humans make decisions will also be sketched. Based on this, an alternative to the so called “end-to-end” mantra will be discussed offering a modular approach based on prototypes which provides more degrees of freedom in regards to interpretability, human agency and oversight and, interestingly, in regards to adaptivity and continual learning.
While traditionally, adaptivity (not only in deep learning) is being addressed by additive updates in this talk this is being critically analysed and considered as one of the reasons for the so called “catastrophic forgetting”. An alternative is considered instead – adaptation of atomic knowledge representations (KR) in the form of prototypes and clusters. We argue that they are more suitable KR than weights of a deep neural network as sometimes suggested in literature. We further demonstrate that such KRs are practically invariant to latent space transformations and further adaptation during a continual learning process. Some examples and applications are used mostly as a proof of the concept.
Bio
Prof. Angelov holds a Chair in Intelligent Systems and leads AI group at the School of Computing and Communications, Lancaster University where he served as School’s Director of Research (2020-2025); this academic year being on sabbatical. Prof. Angelov is a Visiting Professor at the PI School of Φ-Lab of the European Space Agency (ESA), founding co-Director of one of the funded programmes by ELLIS (on Human-centred machine learning) and founding Director of the Lancaster Intelligent, Robotic and Autonomous systems (LIRA) Centre and a Fellow of the IEEE, of ELLIS, of the IET and of AAIA.
He has 450+ publications in leading journals (like TPAMI, Information Fusion, IEEE Transactions on Cybernetics, Nature Scientific reports, etc.), peer-reviewed conference proceedings (such as CVPR, ICLR, NeurIPS, AAAI, ICCV, ECCV, IEEE), 3 granted US patents, 3 research monographs (by Wiley, 2012 and Springer, 2002 and 2018) cited 20,000 times (h-index 67); according to SciVal around half of his publications are in top 10% venues. He is ranked top 0.1% (503th out of 458615 researchers in the AI and Image Processing subfield worldwide in 2025) according to the “Top 2% Scientists” Stanford University’s list and has 12 highly cited papers. He has an active research portfolio in the area of interpretable (explainable-by-design), adaptive and continual deep learning and internationally recognised results into evolving systems for streaming data and computational intelligence.
Prof. Angelov leads numerous projects funded by UK research councils, EC, European Space Agency, DSTL, GCHQ, Royal Society, Faraday Institute, industry. He is recipient of the Dennis Gabor award (2020) for “outstanding contributions to engineering applications of neural networks”, IEEE awards ‘For outstanding Services’ (2013 and 2017) and other awards. He is Editor-in-Chief of Springer’s journal Evolving Systems (recipient of Editorial Excellence awards for 2020 and 2024) and Associate Editor of IEEE Transactions on Cybernetics, IEEE Transactions on AI and other journals. He gave 40 keynote talks and was General co-Chair of a number of high profile IEEE conferences, including IJCNN. He is founding Chair of the Technical Committee on Evolving Intelligent Systems, SMC Society of the IEEE and was previously chairing the Standards Committee of the Computational Intelligent Society of the IEEE (2010-2012) where he initiated and chaired the Work Group P2976 on the IEEE standard on explainable AI. He was also a member of International Program Committee of over 150 international conferences (primarily IEEE). More details can be found at www.lancs.ac.uk/staff/angelov
Going with the flow: designing Graph Neural Networks as dynamical systems
Davide Bacciu, Ph.D. | Full Professor of Machine Learning, Università di Pisa | Pervasive AI Lab Coordinator
Abstract
Graph neural networks learn by passing information across the edges of a graph. This local diffusion process is central to their success, but it also raises a fundamental design challenge: how can information travel far enough to capture long-range dependencies without being washed out, oversmoothed, or lost?
This talk revisits graph neural network design through the lens of dynamical systems. Rather than treating message passing as a generic stack of layers, we view it as a neural flow whose propagation, conservation, and dissipation can be deliberately controlled. This perspective leads to principled architectures for both static and temporal graphs, and offers theoretical tools for understanding when information is preserved and when it fades.
The talk will emphasize broadly applicable ideas for learning systems: how dynamics can inform model design, how stability and conservation can become architectural principles, and how theoretical guarantees can help us build graph models that propagate information more reliably across complex data.
Bio
Davide Bacciu is Full Professor of Machine Learning at the Department of Computer Science, University of Pisa, where he leads the Pervasive Artificial Intelligence Laboratory. His research focuses on the design of neural learning systems for graph-structured, temporal, and distributed data, with interests spanning graph representation learning, generative models, continual learning, and pervasive AI. He has co-authored over 250 research works on the field.
He has coordinated major European research projects, including EIC Pathfinder EMERGE, and serves as Director of AI Research at Aptus.AI. He sits in the AdCom board of the IEEE Computational Intelligence Society, and previously served as Chair of the IEEE CIS Neural Network technical committee, as Senior Editor of the IEEE Transactions on Neural Networks and as Vice-President of the Italian Association for AI.
Auckland University of Technology, NZ
Evolving Spatio-Temporal Associative Memories: From Predictive Brains to Predictive AI
Nikola Kasabov | Auckland University of Technology, New Zealand | Fellow of IEEE, Fellow of the Royal Society of New Zealand
Abstract
Despite the success of some neural network-based associative memories (AM), such as the Hopfield’s network, that deal with static, vector-based data, there have been practically no AM to deal with more complex spatio-temporal data, which is the majority of spatio-temporal processes in Nature.
At the same time, the human brain is the most sophisticated spatio-temporal AM, evolved for millions of years, to learn and predict events. Brain-inspired computational architectures are available now. This talk introduces evolving spatio-temporal associative memories (ESTAMs) realised in a brain-inspired spiking neural network framework and discusses their application for predictive AI. ESTAM is defined as a dynamical memory learning system that learns associations between input spatio-temporal patterns and output patterns and recalls them. It can be further evolved on new data, including new variables, measured at different times.
ESTAM is a computational model in which memory is represented as a dynamically growing structure within the brain-inspired SNN framework NeuCube. Its novel formulation suggests new directions for predictive AI, to predict events in spatio-temporal processes. This is illustrated on case studies of real spatio-temporal data, where they can be recalled successfully using new data. Future research and applications of predictive AI across domain areas are discussed.
Bio
Nikola Kasabov is Professor at the School of Engineering, Computing and Mathematical Sciences at Auckland University of Technology, New Zealand, and also Professor at the Institute for Information and Communication Technologies of the Bulgarian Academy of Sciences. Kasabov is Director of Knowledgeengineering.ai and member of the advisory board of Conscium.com.
Kasabov is Past President of the Asia Pacific Neural Network Society (APNNS) and the International Neural Network Society (INNS). He has been a chair and a member of several technical committees of IEEE Computational Intelligence Society. He is Editor of Springer Handbook of Bio-Neuroinformatics, Editor-in-Chief of Springer Series of Bio- and Neuro-Informatics, and Editor-in-Chief of the Springer journal Evolving Systems. He is Associate Editor of several journals. His main research interests are in the areas of neural networks, intelligent information systems, soft computing, and neuroinformatics, with hundreds of highly cited 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; Shanghai Jiao Tong University; and University of Zurich.
Kasabov has received a number of awards, among them: INNS Ada Lovelace Meritorious Service Award; 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.
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.
© 2026 Università di Pisa