Prof Nikhil R. Pal delivering his seminar 'Some attempts to realise explainable, trustworthy and bio-inspired NNs' to an audience of AAII researchers, 23 October 2023.
Topic: 'Some attempts to realise explainable, trustworthy, and bio-inspired NNs'
Abstract: We are in an era of artificial intelligence (AI) and there are many successful AI systems, often beating human performance. In many cases, neural networks, particularly the deep neural networks, are the main pillars of such systems. But generally these systems are not comprehensible and/or biologically plausible. In my view, comprehensibility of a system depends, at least, on the following: simplicity, interpretability, explainability, trustworthiness, fairness, and biological plausibility of such systems, if that makes sense. Ideally, we should strive for realising all these attributes in any intelligent system, but this is very difficult. So, we adopt an easier path to describe how some of these attributes may be realised separately. Particularly, we explain how a convolutional neural network can be augmented with explainability, how some observations in the visual cortex of a cat can be exploited to make a multi-layered perceptron a little more comprehensible. Finally, we shall discuss how a network can say “Don’t know” under the right conditions, making it trustworthy.
Speaker: Prof Nikhil R. Pal (Indian Statistical Institute, India)
Nikhil R. Pal is a Professor in the Electronics and Communication Sciences Unit and was the founding Head of the Center for Artificial Intelligence and Machine Learning of the Indian Statistical Institute. His current research interest includes brain science, computational intelligence, machine learning and data mining.
He was the Editor-in-Chief of the IEEE Transactions on Fuzzy Systems for the period January 2005-December 2010. He served/has been serving on the editorial /advisory board/ steering committee of several journals including the International Journal of Approximate Reasoning, Applied Soft Computing, International Journal of Neural Systems, Fuzzy Sets and Systems, IEEE Transactions on Fuzzy Systems and the IEEE Transactions on Cybernetics.
He is a recipient of the 2015 IEEE Computational Intelligence Society (CIS) Fuzzy Systems Pioneer Award and 2021 IEEE CIS Meritorious Service Award. He has given many plenary/keynote speeches in different premier international conferences in the area of computational intelligence. He has served as the General Chair, Program Chair, and co-Program chair of several conferences. He has been a Distinguished Lecturer of the IEEE CIS (2010-2012, 2016-2018, 2022-2024) and was a member of the Administrative Committee of the IEEE CIS (2010-2012). He has served as the Vice-President for Publications of the IEEE CIS (2013-2016) and the President of the IEEE CIS (2018-2019).
He is a Fellow of the West Bengal Academy of Science and Technology, Institution of Electronics and Tele Communication Engineers, National Academy of Sciences, India, Indian National Academy of Engineering, Indian National Science Academy, International Fuzzy Systems Association (IFSA), The World Academy of Sciences, and a Fellow of the IEEE, USA. (www.isical.ac.in/~nikhil)