In this talk...
Dr. Hari Koduvely will discuss how Bayesian Inference is useful for Machine Learning. Bayesian methods allow for more accurate predictions under uncertainty and with less amount of data. When applied to very complex models such as Deep Neural Networks, they would help in automatic tuning of hyperparameters and efficient compression of the models. Dr. Koduvely will present a brief introduction to Bayesian Inference and some examples of machine learning models where Bayesian methods are used very effectively.
About the Speaker
Dr. Hari Koduvely, Chief Data Scientist of Zighra Inc in Ottawa
Prior to moving to Canada, Dr. Koduvely worked as Senior/Principal Data Scientist for Amazon and Samsung R&D Institute in Bangalore, India. He has a PhD in Statistical Physics from Tata Institute of Fundamental Research in Mumbai, India and has done post doctoral research from Weizmann Institute of Science, Israel and Georgia Institute of Technology, USA. He has published several papers in the area of Bayesian Machine Learning including a book titled Learning Bayesian Models with R.
For more information and to register for this event, please visit the CUIDS website.