In the scope of CBQF celebration of its 30 years we will organize a cycle of Seminars about several topics related with the different areas of research.
Signal processing (SP) theory originates from mathematical foundation with astonishing applications which help information technologists discover and invent new realities branching off into many research and development applications. Linear algebra, data transforms, and signal distributions have been playing the major roles in most of these applications. On the other hand, machine learning prefers to create generative models for the problem under study.
Despite the above facts, ML and information theoretic ideas apparently can help statistical signal processing overcome the barriers of linear models and mitigate the need for Gaussianity and stationarity assumptions. However, they involve many other applications such as latent variable analysis and blind source separation commonly discussed in SP.
In this talk after we address a number of cases where signal processing and machine learning meet particularly by comparing adaptive systems in SP with generative adversarial networks in ML, we will focus on cooperative learning suitable for multiagent decentralised networks where a number of intelligent nodes have the same objective and try to provide a SP solution. Some examples in healthcare particularly for EEG (such as detection of event related potentials or the signature of Parkinsonian hand tremor from EEG) will be examined. Such solutions may be achieved using generative AI models leading to a wider range of applications.
Saeid Sanei, PhD, DIC, FBCS, is a Professor of Signal Processing and Machine Learning at Nottingham Trent University, UK, and a Visiting Professor at Imperial College London, UK. He received his doctorate from Imperial College London in 1991. His current research focus is on EEG, MEG, and joint EEG-fMRI processing. He published five books and approximately 400 peer reviewed journal and conference papers and served as the Technical Committee Member of IEEE MLSP and SPTM. He has been an Associate Editor for IEEE Signal Processing Magazine, IEEE Signal Processing Letters, and the journal of Computational Intelligence and Neuroscience.
Seminar 1: Human Health and the One Health Continuum, with Ed Topp