Discover CalculatedContent/ww-trends-2021 Open Source project

Stars
3
Rank 3,963,521 (Top 79 %)
Language
Jupyter Notebook
Created over 3 years ago
Updated over 3 years ago

CalculatedContent

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repo to accompanying the paper: "Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data"

WeightWatcher

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

Python

1,440

cloud-crawler

Distributed Ruby Web Crawler, backed up by Redis

Ruby

122

tsvm

experiments testing transductive svm for my blog posts

Perl

ImplicitSelfRegularization

Repo to accompany paper "Implicit Self-Regularization in Deep Neural Networks..."

Jupyter Notebook

big_deep_simple_mlp

Jupyter Notebook

ww-trends-2020

Jupyter Notebook

PredictingTestAccuracies

Repo to accompany paper: Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks

Jupyter Notebook

why-dl-works

A repo for collaborating on research into why deep learning works

Jupyter Notebook

ww-phys_theory

Notebooks for the ww phys-theory channel

Jupyter Notebook

WhyDeepLearningWorks

Jupyter Notebook

ww-colab

colab notebooks for weightwatcher tool

Jupyter Notebook

RememberingGeneralization

Repo to accompany the paper: Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior

cnmf

Blog Posting on Convex NMF

Python

cloud_loader

Ruby

cc-website

Calculation Consulting Website Using Bootstrap Agency theme

CSS

chef-repo

chef repo

Ruby

calculationconsulting.com

old angular / javascript web site for calculation consulting dot com

CSS

CalculatedContent/ww-trends-2021

CalculatedContent

Reviews

Repository Details

More Repositories