The role of a layer in deep learning

Seminar
QUEST Center event
Yes
Speaker
Zohar Ringel, Hebrew University
Date
10/12/2018 - 12:30Add to Calendar 2018-12-10 12:30:00 2018-12-10 12:30:00 The role of a layer in deep learning Deep artificial neural networks (DNNs) have been driving many of the recent advancements in machine learning. An important question on the theory side of DNNs concerns the role played by each layer in the network. Recently two bold conjectures were made: The first is that DNNs learn to perform a series of Renormalization-Group (RG) transformations on the data they are given. The second claims that each subsequent layer in a DNN increases more and more a certain conditional-entropy. In this talk, I’ll discuss some tests and refinements of these two conjectures. In particular, I’ll present an information-theory based formulation of real-space RG and compare it with more conventional training algorithms for DNNs. Time permitting I’ll also discuss the training of DNNs using the above conditional-entropy based goal. Relevant papers [1] M. Koch-Janusz and Z.R. (2018)https://www.nature.com/articles/s41567-018-0081-4 [2] Z.R. and R. A. de Bem (2017) https://openreview.net/forum?id=BJGWO9k0Z [3] P. M. Lenggenhager, Z.R.,S. D. Huber, M. Koch-Janusz (2018)https://arxiv.org/pdf/1809.09632.pdf Physics 301 המחלקה לפיזיקה physics.dept@mail.biu.ac.il Asia/Jerusalem public
Place
Physics 301
Abstract

Deep artificial neural networks (DNNs) have been driving many of the
recent advancements in machine learning. An important question on the
theory side of DNNs concerns the role played by each layer in the
network. Recently two bold conjectures were made: The first is that
DNNs learn to perform a series of Renormalization-Group (RG)
transformations on the data they are given. The second claims that
each subsequent layer in a DNN increases more and more a certain
conditional-entropy. In this talk, I’ll discuss some tests and
refinements of these two conjectures. In particular, I’ll present an
information-theory based formulation of real-space RG and compare it
with more conventional training algorithms for DNNs. Time permitting
I’ll also discuss the training of DNNs using the above
conditional-entropy based goal.


Relevant papers
[1] M. Koch-Janusz and Z.R. (2018)
https://www.nature.com/articles/s41567-018-0081-4
[2] Z.R. and R. A. de Bem (2017) https://openreview.net/forum?id=BJGWO9k0Z
[3] P. M. Lenggenhager, Z.R.,S. D. Huber, M. Koch-Janusz (2018)
https://arxiv.org/pdf/1809.09632.pdf

תאריך עדכון אחרון : 27/11/2018