In this talk, I present a selection of ideas and algorithms that are presented in my recently published textbook of the same title [1]. The book introduces information measurement methodologies for machine learning that reduce the reliance on hyperparameters and model-type biases. This information-driven perspective enables data quality measurements, task complexity estimations, and reproducible experimental design. Bridging the disciplines of machine learning, information theory, and computer engineering, the methods presented enhance explainability and model resilience, contributing to the robustness and credibility of data science as an engineering discipline. The textbook evolved over many years out of a computer science graduate seminar in combination with the "Information and Uncertainty" discussion group at BIDS.
Biography:
Dr. Gerald Friedland is a Principal Scientist in the AI/ML Lab at Amazon AWS, leading a group of scientists on systematic approaches to fully automatic, no-code machine learning and data science. Previously, he was CTO and co-founder of Brainome, Inc that created a no-code machine learning tool. Before that, he was a Principal Data Scientist at Lawrence Livermore National Lab, integrating machine learning systems with the traditional sciences, especially physics. Before that, he had been with the International Computer Science Institute for 10 years, heading a video and speech analytics group. Several of his accomplishments include being the lead figure behind the Multimedia Commons initiative, a collection of 100M images and 1M videos for research and he is the creator of the SIOX object segmentation tool that has been the de-facto open-source standard for semi-automatic image segmentation since 2005. He has published more than 200 peer-reviewed articles in conferences, journals, and books. He recently authored a new textbook on the intersection of information theory and machine learning that has been translated into several other languages. He also co-authored a textbook on multimedia computing with Cambridge University Press. He served as associate editor for ACM Transactions on Multimedia and IEEE Multimedia Magazine and regularly reviews for IEEE Transactions on Acoustics, Speech, and Language Processing; IEEE Transaction on Multimedia; Springer's Machine Vision and Application; and other journals. He is the recipient of several research and industry recognitions, among them the European Academic Software Award and the Multimedia Entrepreneur Award by the German Federal Department of Economics. Dr. Friedland received his doctorate (summa cum laude) and master's degree in computer science from Freie Universitaet Berlin, Germany, in 2002 and 2006, respectively.
https://link.springer.com/book/10.1007/978-3-031-39477-5
373