By Gunnar Carlsson

December 3, 2018

By Gunnar Carlsson

The appeal of forecasting the future is very easy to understand, even though it is not realizable.  That has not stopped an entire generation of analytics companies from selling such a promise. It also explains the myriad methods that attempt to give partial, inexact, and probabilistic information about the future.

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…

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:

1. It…