Your browser is out-of-date!

For a richer surfing experience on our website, please update your browser.Update my browser now!

×

Research Seminar :Deep Patel & Maunil Vyas,How can Neural Nets approximate the functions well?

September 08, 2017 12.30pm to 1.30pm   SEAS, Room 109   AU research seminar series

Title: How can Neural Nets approximate the functions well?

Speaker: Deep Patel & Maunil Vyas

Abstract: In this talk we would discuss some factors that enable the neural nets to approximate the data well. We would draw analogy from physics which  plays crucial role in deep learning with necessary mathematics. We would  discuss how to strengthen neural network's capability to approximate functions. We will conclude with arguing about the question - why deep learning is essential instead of shallow learning by neural nets. Our talk is based on the paper:Lin, Henry W., Max Tegmark, and David Rolnick. "Why does deep and cheap learning work so well?." Journal of Statistical Physics (2016): 1-25."