Jonathan Symonds's Blog Posts Tagged 'topological' (4)

Relationships, Geometry, and Artificial Intelligence

By Gunnar Carlsson

December 3, 2018

In their very provocative paper, Peter Battaglia and his colleagues, posit that in order for artificial intelligence (AI) to achieve the capabilities of human intelligence, it must be…

Continue

Added by Jonathan Symonds on December 4, 2018 at 3:00pm — No Comments

How the incorporation of prior information can accelerate the speed at which neural networks learn while simultaneously increasing accuracy

Deep neural nets typically operate on “raw data” of some kind, such as images, text, time series, etc., without the benefit of “derived” features. The idea is that because of their flexibility, neural networks can learn the features relevant to the problem at hand, be it a classification problem or an estimation problem. Whether derived or learned, features are important. The challenge is in determining how one might use what one learned from the features in future work (staying…

Continue

Added by Jonathan Symonds on August 30, 2018 at 7:00am — No Comments

Going Deeper: More Insight Into How and What Convolutional Neural Networks Learn

In my earlier post I discussed how performing topological data analysis on the weights learned by convolutional neural nets (CNN’s) can give insight into what is being learned and how it is being learned.

The significance of this work can be summarized as follows:

It…

Continue

Added by Jonathan Symonds on August 9, 2018 at 11:30am — No Comments

Using Topological Data Analysis to Understand the Behavior of Convolutional Neural Networks

TLDR: Neural Networks are powerful but complex and opaque tools. Using Topological Data Analysis, we can describe the functioning and learning of a convolutional neural network in a compact and understandable way. The implications of the finding are profound and can accelerate the development of a wide range of applications from self-driving everything to GDPR.