#A.I. Recently, Microsoft Research published the LASER method: ”Layer-Selective Rank Reduction” in this recent, very popular paper The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction And it got a lot of...
Tuesday, February 13, 2024
Friday, July 22, 2022
Better than BERT: Pick your best model #AI
#A.I. Have you ever had to sort through HuggingFace to find your best model ? There are over 54,000 models on HuggingFace! So it’s not an easy task. Most people just choose the most popular model–and this is usually BERT. Or some BERT variant. B...
Monday, October 18, 2021
Fantastic Measures of Generalization — That Actually Work (part 1) #AI
#A.I. In the next few posts, I am going to discuss how to use the generalization metrics included in the open-source weightwatcher tool. The goal is to develop a general-purpose tool can that you can use, among other things, to predict (tends in) t...
Friday, November 27, 2020
Protected: Simpson’s Paradox and Deep Learning Metrics with Weightwatcher #AI
#A.I. There is no excerpt because this is a protected post. via https://AIupNow.com Charles H Martin, PhD, Khareem Sudlow ...
Tuesday, September 15, 2020
Why WeightWatcher Works #AI
#A.I. I am frequently asked, why does weightwatcher work ? The weightwatcher tool uses power law fits to model the eigenvalue density of weight matrices of any Deep Neural Network (DNN). The average power-law exponent is remarkably well correlat...