6 November 2020, 13.00 (Swedish time)
Title: Dynamics of Machine Learning: Toward Demystifying Neural Networks
Abstract: We review a recent trend in analyzing machine leaning techniques that unlike the traditional studies, incorporates the role of numerical methods such as optimization algorithms. We will refer to this approach by the term “Dynamics of Machine Leaning”. We discuss how the study of the dynamics of machine learning has provided promising answers to some of the fundamental questions about the learning behavior of artificial neural networks. In this regard, we present potential ideas and relevant observations. Further, we present the application of the dynamics of machine learning in understanding information distillation in neural networks.
About the sepaker:
Ashkan Panahi is an assistant professor at the Computer Science and Engineering Department at Chalmers University of Technology, Sweden. He received his BSc and MSc degrees in electrical and communication systems engineering from Iran University of Science and Technology (IUST) (2008) and Chalmers University (2010). He also received his PhD degree in Signal Processing from the Electrical Engineering Department at Chalmers (2015).
He has held multiple other research positions such as visiting research student at California Institute of Technology (Caltech 2014), U.S. National Research Council Research Associate (2016-2018) and Postdoctoral Researcher at North Carolina State University (2018-2019). His research interest spans a broad range of topics in machine learning and data science, including optimization algorithms, statistical analysis and probabilistic methods, compressed sensing, and statistical detection and estimation theory.
06 November, 2020, 13:00
06 November, 2020, 13:45