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… Read More »Using unsupervised learning to improve prediction performance
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… Read More »Going Deeper: More Insight Into How and What Convolutional Neural Networks Learn
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… Read More »Using Topological Data Analysis to Understand the Behavior of Convolutional Neural Networks
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… Read More »Relationships, Geometry, and Artificial Intelligence
For many, mathematical modeling is exclusively about algebraic models, based on one form or another of regression or on differential equation modeling in the case… Read More »Alternatives to algebraic modeling for complex data: topological modeling via Gunnar Carlsson
