Can we predict the accuracy of a Neural Network? Yes, with the

Can we predict the accuracy of a Neural Network? Yes, with the WeightWatcher tool by Charles Martin, Ph.D. - 002

Listen now

Description

In this Episode we talked about the deep neural networks and the spectral density of each layer's weights. It turns out, you can predict the accuracy ( and many more) with the WeigthWatcher application. We talk about the 5+1 Phases of learning and Heavy Tailed Self Regularization. Charles Martin, PhD on LinkedIn: https://www.linkedin.com/in/charlesmartin14/

More Episodes

See all »

What is beyond PoCs? ML project-hurdles you should be prepared to take with Balázs Kégl - 016

In this episode, our guest was Balázs Kégl, the head of AI Research at Huawei Paris. We were talking about ML projects from the organizational point of view. We talked about the relationship between technical and non-technical people, and why are there so many POC projects why only a few of them...

Published 12/14/20

Machine Learning Cafe

Published 12/14/20

Alternative Learning Methods 01 with Dmitry Krotov - 015

Published 09/09/20