Statistical Mechanics Methods for Discovering Knowledge from Modern Production Quality Neural Networks
Lists
Only you see this
Abstract
There have long been connections between statistical mechanics and neural networks, but in recent decades these connections have withered. However, in light of recent failings of statistical learning theory and stochastic optimization theory to describe, even qualitatively, many properties of production-quality neural network models, researchers have revisited ideas from the statistical mechanics of neural networks. This tutorial will provide an overview of the area; it will go into detail on how connections with random matrix theory and heavy-tailed random matrix theory can lead to a practical phenomenological theory for large-scale deep neural networks; and it will describe future directions.
BibTeX
@inproceedings{martin2019statistical,
author = {Charles H. Martin and Michael W. Mahoney},
title = {{Statistical Mechanics Methods for Discovering Knowledge from Modern Production Quality Neural Networks}},
booktitle = {ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
year = {2019},
doi = {10.1145/3292500.3332294},
}Loading related content...