Why Does Deep and Cheap Learning Work So Well?

Why Does Deep and Cheap Learning Work So Well?

Why Does Deep and Cheap Learning Work So Well?

The recent paper at hand approaches explaining deep learning from a different perspective, that of physics, and discusses the role of "cheap learning" (parameter reduction) and how it relates back to this innovative perspective.

Why does deep learning work so well? And... cheap learning?

A recent paper by Henry W. Lin (Harvard) and Max Tegmark (MIT), titled "Why does deep and cheap learning work so well?" looks to examine from a different perspective what it is about deep learning that makes it work so well. It also introduces (at least, to me) the term "cheap learning."

First off, to be clear, "cheap learning" does not refer to using a low end GPU; instead, the following explains its relationship to parameter reduction:

This central idea of this paper is that neural network success owes as much to physics as it does to mathematics (perhaps more), and that simplistic physics functions owing to concepts such as symmetry, locality, compositionality, and polynomial log-probability can be viewed similarly to deep learning's relationship with the reality which it seeks to model. You may have heard something about this in September; this is the paper on which said news was based.

Read Also:
3 Executive Insights for Application of Artificial Intelligence in eCommerce

More from the abstract:

We further argue that when the statistical process generating the data is of a certain hierarchical form prevalent in physics and machine-learning, a deep neural network can be more efficient than a shallow one.

 



Chief Analytics Officer Europe

25
Apr
2017
Chief Analytics Officer Europe

15% off with code 7WDCAO17

Read Also:
Hybrid Data Scientists: Key to Leading and Optimizing Analytics Efforts

Chief Analytics Officer Spring 2017

2
May
2017
Chief Analytics Officer Spring 2017

15% off with code MP15

Read Also:
How to compete against data scientists charging $30/hour

Big Data and Analytics for Healthcare Philadelphia

17
May
2017
Big Data and Analytics for Healthcare Philadelphia

$200 off with code DATA200

Read Also:
Artificial Intelligence, Lawmakers And The Future Of Work

SMX London

23
May
2017
SMX London

10% off with code 7WDATASMX

Read Also:
Sisense wants to make every user a data scientist

Data Science Congress 2017

5
Jun
2017
Data Science Congress 2017

20% off with code 7wdata_DSC2017

Read Also:
3 Executive Insights for Application of Artificial Intelligence in eCommerce
Read Also:
Why you should use open data to hone your machine learning models

Leave a Reply

Your email address will not be published. Required fields are marked *