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 Essential Ways To Use Data Strategically

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.

 



Sentiment Analysis Symposium

27
Jun
2017
Sentiment Analysis Symposium

15% off with code 7WDATA

Read Also:
3 Essential Ways To Use Data Strategically

Data Analytics and Behavioural Science Applied to Retail and Consumer Markets

28
Jun
2017
Data Analytics and Behavioural Science Applied to Retail and Consumer Markets

15% off with code 7WDATA

Read Also:
Four perspectives on data lakes

AI, Machine Learning and Sentiment Analysis Applied to Finance

28
Jun
2017
AI, Machine Learning and Sentiment Analysis Applied to Finance

15% off with code 7WDATA

Read Also:
Information architecture: The key to governance, integration and

Real Business Intelligence

11
Jul
2017
Real Business Intelligence

25% off with code RBIYM01

Read Also:
Build the Right Team for Big Data Success

Advanced Analytics Forum

20
Sep
2017
Advanced Analytics Forum

15% off with code Discount15

Read Also:
3 Advantages of Using an Open Source Business Intelligence Tool
Read Also:
Data Is Dominating Emerging Tech

Leave a Reply

Your email address will not be published.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