Mathematical Finance & Financial Data Science Seminar

Deep (Supervised or Otherwise) Learning

Speaker: Dhruv Madeka, Senior Machine Learning Scientist, Amazon

Location: Warren Weaver Hall 1302

Date: Tuesday, April 23, 2019, 5:30 p.m.


Deep Learning usually refers to a set of computational models, composed of multiple processing layers, that perform tasks on data by generating multiple intermediate representations. These models have surpassed state of the art performance in many different tasks and have become the focus of a vast amount of scientific literature. In this talk, we will begin by covering the basics of Deep Learning - including an overview of backpropagation, gradient descent methods, regularization, representation learning and the latest information bottleneck theories. We will also review the difference between supervised and reinforcement learning - and overview how Deep Learning can be used to act on the world and learn from that information.


Bio – Dhruv Madeka

Dhruv Madeka is a Senior Machine Learning Scientist at Amazon. His current research interests focus on Deep Reinforcement Learning, Data Visualization and Applied Mathematics. Having graduated from the University of Michigan with a BS in Operations Research and from Boston University with an MS in Mathematical Finance, Dhruv previously worked in the Quantitative Research team at Bloomberg LP, before becoming a Senior Scientist at Amazon.