Pablo A. Estévez received his professional electrical engineering (EE) title from Universidad de Chile in 1981 and the M.Sc. and Dr. Eng. degrees from the University of Tokyo, Japan, in 1992 and 1995, respectively. He is a Full Professor in the Electrical Engineering Department at the University of Chile and former Chairman of the Electrical Engineering Department from the period 2006-to 2010. Prof. Estévez is an IEEE Fellow. He served as President of the IEEE Computational Intelligence Society (CIS) for the term 2016-2017, Vice-president of Finances (2019-2024), Vice-president of Members Activities (2011-2014), CIS ADCOM Member-at-Large (2008-2010), and CIS Distinguished Lecturer (2006-2011). He has served as an Associate Editor of the IEEE Transactions on Neural Networks (2007-2012), and as Associate Editor of the IEEE Transactions on Artificial Intelligence (2020-2024). Prof. Estévez is the recipient of the 2019 IEEE CIS Meritorious Service Award and the 2019 IEEE Latin-America Eminent Engineer Award.

Prof. Estévez served as conference chair of the International Joint Conference on Neural Networks (IJCNN), held in July 2016, in Vancouver, Canada, and general co-chair of the IEEE World Congress on Computational Intelligence, IEEE WCCI 2018, held in Rio de Janeiro, Brazil, in July 2018. Prof. Estévez has been a keynote speaker at GAITC 2023 (China), IEEE ANDESCON (2022), CBIC 2019 (Brazil), Chilecon 2019 (Chile), WSOM 2016 (USA), IJCRS 2016 (Chile), LA-CCI 2016  (Colombia), LA-CCI 2015 (Brazil), IEEE SSCI 2014 (USA), AISC 2008 (Poland), among other conferences. Prof. Estévez served as PI of the Conicyt-NSF international collaboration project on Big Data in Astronomy (2015-2018, US$300,000), carried out together with the University of Washington. He is a founder and co-PI of the Millennium Institute on Astrophysics (2014-2024, US$10,000,000), and co-Pi of the Millennium Institute for Intelligent Healthcare Engineering-IHEALTH (2023-2032). Prof. Estévez collaborates with researchers from Harvard University, John Hopkins University, University of Washington, University of Florida, Pantheon-Sorbonne, and Nancy University. Prof. Estévez has been an Invited Researcher with the NTT Communication Science Laboratory, Kyoto, Japan; the Ecole Normale Supérieure, Lyon, France; and a Visiting Professor at the Pantheon-Sorbonne University, Paris, France; and the University of Tokyo, Tokyo, Japan. Prof. Estévez has co-authored more than 150 articles in journals and conferences (Google Scholar h-index = 36). His research interests include artificial intelligence, big data, deep learning, artificial neural networks, self-organizing maps, data visualization, feature selection, information theoretic learning, time series analysis, and advanced signal and image processing, with applications to astronomy, energy and medicine.

Empowering Astronomy and Medicine through Transformers and LLMs

Pablo A. Estévez,
Electrical Engineering Department
Universidad de Chile

Abstract: Deep learning attention-based models (transformers) are the new technology underlying the current AI revolution, particularly in natural language processing through large language models (LLMs). In this talk, we will introduce transformers and LLMs. We apply transformers to process astronomical time series to classify supernovae events and compare results with state-of-the-art machine learning models such as recurrent neural networks and random forests. Then, we introduce ATAT, a multimodal transformer that combines time series and tabular data. ATAT is applied to the synthetic dataset from the ELAsTICC challenge, reaching a macro F1-score of 82.9±0.4 using 20 classes. We also apply LLMs to the text-to-SQL parsing problem in astronomical datasets. Next, we apply transformers to detect sleep spindles in electroencephalograms (EEGs). Finally, we use multimodal LLMs for generating text reports from brain medical images.

James M. Keller is a University of Missouri Curators Distinguished Professor Emeritus in the Electrical Engineering and Computer Science Department on the Columbia campus. His research interests center on computational intelligence with a focus on problems in computer vision, pattern recognition, and information fusion including bioinformatics, spatial reasoning, geospatial intelligence, landmine detection and technology for eldercare.  Professor Keller has been funded by a variety of government and industry organizations and has coauthored well over 500 technical publications.

Jim is a Life Fellow of the IEEE, is an IFSA Fellow, and a past President of NAFIPS. He received the 2007 Fuzzy Systems Pioneer Award and the 2010 Meritorious Service Award from the IEEE Computational Intelligence Society. He won the 2021 IEEE Frank Rosenblatt Technical Field Award. Jim was Editor-in-Chief of the IEEE Transactions on Fuzzy Systems (1999 – 2004), followed by being the Vice President for Publications of the IEEE Computational Intelligence Society from 2005-2008, then as an elected CIS Adcom member, and finished another term as VP Pubs (2017-2020). He was President of IEEE CIS for 2022 – 2023. and has served as the IEEE TAB Transactions Chair and as a member of the IEEE Publication Review and Advisory Committee from 2010 to 2017. He was Vice Chair of the IEEE Publication Services and Products Board, chaired an AdHoc Committee on AI in the Publications Domain, and now serves as the chair of the strategic planning committee of that board. He has had many conference positions and duties over the years.

Checking on the Stream

Jim Keller*
Electrical Engineering and Computer Science
University of Missouri

Abstract: With the explosion of ubiquitous continuous sensing (something Lotfi Zadeh predicted as one of the pillars of Recognition Technology in the late 1990s), on-line streaming clustering is attracting more and more attention.  I was drawn into this world mainly due to our desire to continuously monitor the activities, and health conditions, of older adults in a large interdisciplinary eldercare research group. Roughly, the requirements are that the streaming clustering algorithm recognize and adapt clusters as the data evolves, that anomalies are detected, and that new clusters are automatically formed as incoming data dictate. An advantage of a streaming model is that data trends can be examined as they occur, and alerts could be generated as feature vectors representing activity move “toward” cluster boundaries. 
Streaming clustering is fundamentally different from static traditional clustering where the most successful models use some form of alternating optimization in an iterative exploration of a complete dataset.  When the clustering algorithm finishes, there is a variety of so-called cluster validity indices to estimate the goodness of the final partition, be it crisp, probabilistic, fuzzy, or possibilistic. This is not possible in the streaming mode, since data arrives in a continuous fashion and decisions need to be made instantaneously.  In most cases, the data is then discarded and only cluster “footprints” are retained. Is the situation then hopeless?  This would be a short talk if so!
In this talk, I will present my thoughts on streaming clustering in general, looking in a little more detail at the MU streaming clustering algorithm.  I will briefly show an early warning approach of health changes in eldercare monitoring based on monitoring sensor streams.  The main goal, however, is to dig into the streaming equivalent of static cluster validity measures that we call incremental streaming indices.  I will discuss several such indices including two new fuzzy set based measures of incremental cluster growth and drift. 

* research done with lots of friends, almost too numerous to be named!

Bernadette Bouchon-Meunier is a director of research emeritus at the National Centre for Scientific Research and Sorbonne University, the former head of the department of Databases and Machine Learning in the Computer Science Laboratory of the University Pierre et Marie Curie-Paris 6 (LIP6). She supervised 52 PhD students. She is the Editor-in-Chief of the International Journal of Uncertainty, Fuzziness and Knowledge-based Systems and the Co-executive director of the IPMU International Conference held every other year since 1986. B. Bouchon-Meunier is the (co)-editor of 30 books, and the (co)-author of six.

Fuzzy Approaches to Explainable Artificial Intelligence

Bernadette Bouchon-Meunier
National Centre for Scientific Research
Sorbonne University

Abstract: Explainable Artificial Intelligence has been at the core of many developments in Artificial Intelligence in the recent years, following the DARPA incentives (https://www.darpa.mil/program/explainable-artificial-intelligence) to both produce more explainable artificial intelligence models while maintaining good learning performances, and enable the user to easily interact with intelligent systems. Several related concepts are inherent in the quality of intelligent systems, such as their understandability, their expressiveness or their interpretability. The latter has been in particular extensively investigated in the construction and analysis of fuzzy intelligent systems. We will review several of these aspects, mainly dealing with the capacity of an intelligent system to explain how it obtains results, and to provide the user with easily understandable outcomes, in light of the fuzzy paradigm. We will show that fuzzy models participate effectively in solutions to achieve one or the other of these goals, going beyond classic fuzzy rule-based systems.

Maria C. Torres-Madronero received his PhD in Computing and Information Science and Engineering, an M.E. in Electrical Engineering from the University of Puerto Rico, Mayaguez PR, and a B.A. in Electronics Engineering from Universidad Nacional de Colombia, Manizales Colombia. She is an Associate Professor at the Department of Computer and Decision Sciences at the Universidad Nacional de Colombia. Between 2013 and 2023, she was a professor at the Instituto Tecnologico Metropolitano de Medellin (Colombia), where she led the research group in Automation, Electronics, and Computer Science and participated in creating the PhD program in Engineering.

Challenges and opportunities of artificial intelligence for agricultural applications in Colombia

Maria C. Torres-Madronero
Department of Computer and Decision Sciences
Universidad Nacional de Colombia

Abstract: The Colombian agricultural sector needs more technification in crop management and monitoring processes, which leads to low productivity and environmentally unfriendly agricultural practices. Clear examples of this low productivity are avocado, corn, and beans. Avocado is a crop of high interest for Colombia because of its international demand and competitive prices, but it shows low production yields despite a significant increase in cultivated areas. Colombia had 17,000 hectares of avocado by 2007, producing 9.85 tons per hectare. By 2023, the cultivated hectares had increased to more than 51 thousand, but production was only 8.66. Beans, considered an essential source of protein for food security in the Americas, reached a domestic production of 148,829 tons by 2021, which was insufficient to meet demand, and therefore, 22,762 tons were imported. Similarly, corn production needs to be increased in Colombia, requiring annual imports of 79% of what is consumed, although this grain is one of the most important in the food diet. This production behavior in essential and competitive crops represents an opportunity to explore techniques to increase Colombian agriculture’s productivity, competitiveness, and sustainability. Among the alternatives to improve crop monitoring and management is precision agriculture, which integrates techniques, models, and sensors to acquire, process, and analyze data that provide relevant information for decision-making. Thus, there is a high potential for using artificial intelligence (AI) for data analysis and decision support in the agricultural sector. For instance, AI can analyze data collected by spectrometers and multispectral cameras that measure the energy reflected and emitted from a surface along the electromagnetic spectrum. Integrating AI and spectral information can help monitor different crops. However, there are different challenges to incorporating these technologies into the Colombian agricultural sector. This talk will review the potential applications of artificial intelligence and spectral data for Colombian agriculture, identifying the main obstacles and challenges.

Robin Hiesinger received his PhD in neuroscience in 2000 and ran a neurogenetics lab from 2006-2015 in the US and ever since in Berlin, Germany.  The Hiesinger lab uses genetics, live imaging and computational modeling to study the unfolding of genomic information during brain wiring.  With this focus, Robin leads a 13-lab research consortium (RobustCircuit.org), is a current recipient of an ERC Advanced Award (SynPromiscuity.flygen.org), and author of the book The Self-Assembling Brain (SelfAssemblingBrain.com).  More information on the lab is available at flygen.org.

Self-Organization in Brain Development

P. Robin Hiesinger
Division of Neurobiology
Free University Berlin

Abstract: Artificial neural networks underlying current approaches to artificial intelligence are designed to contain little to no information before they are switched on to learn.  By contrast, biological brains grow through a genomically encoded processes, are not switched on at any distinct time point, and contain a lot of information prior to learning.  What information, if any, is missing in today’s AI given that there is no genome and no growth process?  How much – and what type of information – exists in a biological neuron and network compared to synaptic weights of a pre-trained artificial neural net?  In this lecture, I will approach these questions from the perspective of developmental neurobiology. The genome does not describe the brain, it contains information to grow the brain.  The genetically encoded growth process has surprising features: it is non-deterministic, flexible and robust to perturbation.  Yet, adult neural circuitry is precise enough to ensure function.  Moreover, there is no fundamental limit to how much information the growth process can encode in a neural network – prior to any learning.  Self-organization is key to these features of genetically encoded brain development.  Individual neurons need to fend for themselves and make local choices.  Our findings using Drosophila as a biological model highlight that pattern formation during growth and the kinetics of live neuronal interactionsrestrict synapse formation and partner choice for neurons that are not otherwise prevented from making incorrect synapses in this system [1, 2].  The lecture will explore self-organization of neural network topology with a focus on information theory and how growth leads to precise, flexible and robust outcomes in brain wiring.

[1]Agi, E.*, Reifenstein, E.T.*, Wit, C., Schneider, T., Kauer, M., Kehribar, M., Kulkarni, A., von Kleist, M.*, and Hiesinger, P.R.* (2024). Axonal Self-Sorting Without Target Guidance in Drosophila Visual Map Formation. Science, 2024 Mar 8;383(6687):1084-1092.

[2] Wolterhoff, N. and Hiesinger, P.R. (2024). Synaptic Promiscuity in Brain Development. Curr Biol. 2024 Feb 5;34(3):R102-R116.

Professor Richard Barker is a board member and founder of innovative enterprises, including in AI-powered precision medicine (Metadvice), healthy longevity (Althea Trust), a CNS-focused biotech company (NWPharmaTech) and a community interest company developing an online mental health support tool for Ukrainian refugees. He is a Visiting Professor in Precision Population Health at Kings College London. Former roles include: Associate Professor in Oxford University; NED of Celgene; Director General of the ABPI; Global Healthcare GM for IBM; CEO of Chiron Diagnostics; Partner of McKinsey.

Using Artificial Intelligence to Predict and Manage Chronic Disease

Richard Barker
Founding Director, Metadvice, New Medicine Partners
Advisory Board Chair, MWPharmaTech
Visiting Professor, KCL: Precision Population Health

Abstract: Health systems across the world can only become sustainable if we transition from treating late stage disease to anticipating it, and managing it efficiently, and with precision. Fortunately we are rapidly acquiring a wide range of diagnostic tools that can assist us, but the sheer volume of data and the need to personalise clinical intervention demands the use of advanced data science, particularly AI. The talk will describe the challenge and give illustrations of how we are meeting it.

TUTORIALS

James M. Keller is a University of Missouri Curators Distinguished Professor Emeritus in the Electrical Engineering and Computer Science Department on the Columbia campus. His research interests center on computational intelligence with a focus on problems in computer vision, pattern recognition, and information fusion including bioinformatics, spatial reasoning, geospatial intelligence, landmine detection and technology for eldercare.  Professor Keller has been funded by a variety of government and industry organizations and has coauthored well over 500 technical publications.

Introduction to Fuzzy Set Theory and Fuzzy Logic Jim Keller Electrical Engineering and Computer Science Department University of Missouri-Columbia Abstract.  This tutorial introduces the concepts required to utilize fuzzy set theory and fuzzy logic in practical applications.  Motivation for the need to consider fuzzy sets as a means of modeling and managing uncertainty will be presented.  The discussion will focus on the theoretical basis and practical implementation of fuzzy set theory and fuzzy logic in pattern recognition, control, information fusion, and eXplainable AI (XAI).  Several applications will be considered.  Topics (as time dictates)                         Motivation  Why fuzzy sets? Isn’t probability theory enough?                         Fuzzy sets and fuzzy set operations                              Multicriteria Decision Making                         Fuzzy relations and fuzzy inference                         Fuzzy rule-based systems                         Control and information fusion                         Linguistic Summarization                         Fuzzy clustering and classification                         Fuzzy integrals

Leonardo Forero holds a degree in electronic engineering from Universidad Pontificia Bolivariana (2002), a master’s degree in telecommunications engineering from Universidade Federal Fluminense (2009) and a PhD in electrical engineering from Pontifical Catholic University of Rio de Janeiro (2013). He is currently an associate professor of electrical engineering at UERJ and a senior researcher at Puc-Rio. He has experience in the area of artificial intelligence, working mainly on the following topics: machine learning, deep learning. He has over 12 years of experience as a supervisor, manager and coordinator in R&D projects..

RAG applications in the energy industry Leonardo Forero Universidade Estadual do Rio de Janeiro Abstract: RAG (Retrieval-Augmented Generation) offers significant benefits to the energy industry by combining information retrieval with language generation. In this topic, real applications were seen in the energy industry in Brazil, translated through LLM models and the application of RAG. These applications improve operational efficiency, reduce costs, ensure regulatory compliance, and enhance innovation in the energy sector.