The future of Deep Learning can be broken down into these 3 Learning Paradigms

towards-data-science

This post was originally published by Andre Ye at Towards Data Science

Hybrid Learning

How can I use supervised methods to solve/in conjunction with unsupervised problems?

Image for post

Image created by author.

Image for post

Image created by author.

Composite Learning

A single model, even one very large, performs worse than several small models/components, each delegated to specialize in part of the task.

Image for post

Image created by author.

Image for post

Image created by author.

Reduced Learning

Image for post

Source: TDS. Image free to share.

“Moore’s Law is kind of running out of steam.”
– Satya Nadella, CEO of Microsoft

Image for post

Source: O’Reilly. Image free to share.

Summary

Spread the word

This post was originally published by Andre Ye at Towards Data Science

Related posts