Calculation Consulting
Big Data & Machine Learning Experts: We help leading companies get ROI from Data
San Francisco, CA
Pinned Repositories
big_deep_simple_mlp
cloud-crawler
Distributed Ruby Web Crawler, backed up by Redis
ImplicitSelfRegularization
Repo to accompany paper "Implicit Self-Regularization in Deep Neural Networks..."
PredictingTestAccuracies
Repo to accompany paper: Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks
tensorflow-generative-model-collections
Collection of generative models in Tensorflow
tsvm
experiments testing transductive svm for my blog posts
WeightWatcher
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
WhyDeepLearningWorks
ww-trends-2020
ww-trends-2021
Repo to accompanying the paper: "Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data"
Calculation Consulting 's Repositories
CalculatedContent/WeightWatcher
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
CalculatedContent/ImplicitSelfRegularization
Repo to accompany paper "Implicit Self-Regularization in Deep Neural Networks..."
CalculatedContent/ww-trends-2020
CalculatedContent/PredictingTestAccuracies
Repo to accompany paper: Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks
CalculatedContent/WhyDeepLearningWorks
CalculatedContent/ww-trends-2021
Repo to accompanying the paper: "Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data"
CalculatedContent/RememberingGeneralization
Repo to accompany the paper: Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior
CalculatedContent/ww-phys_theory
Notebooks for the ww phys-theory channel
CalculatedContent/Apollo-11
Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.
CalculatedContent/WeightWatcher-Examples
User Examples of the WeightWatcher project
CalculatedContent/ww-colab
colab notebooks for weightwatcher tool
CalculatedContent/cc-website
Calculation Consulting Website Using Bootstrap Agency theme
CalculatedContent/DLGeneralization
My project to recreate the results in "Understanding Deep Learning Requires Rethinking Generalization" and do something similar on NLP
CalculatedContent/JMLR-2021
Code to repeat the. calculations in the weightwatcher JMLR paper from 2021
CalculatedContent/LLM-Finetuning-Hub
Repository that contains LLM fine-tuning and deployment scripts along with our research findings.
CalculatedContent/CKA-Centered-Kernel-Alignment
Reproduce CKA: Similarity of Neural Network Representations Revisited
CalculatedContent/Deep-Siamese-Networks-with-Attention
This project explorers enhancements to traditional Siamese Architecture to achieve better accuracy by incorporating more semantic information. I have explored 3 enhancements :
CalculatedContent/fine-tuning-demo
deck and notebook for fine tuning demo
CalculatedContent/gpt-2-simple
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
CalculatedContent/grokking
PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
CalculatedContent/imgclsmob
Sandbox for training convolutional networks for computer vision
CalculatedContent/magnitude
A fast, efficient universal vector embedding utility package.
CalculatedContent/mediawiki
MediaWiki API wrapper in python http://pymediawiki.readthedocs.io/en/latest/
CalculatedContent/multihead-siamese-nets
Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task.
CalculatedContent/powerlaw
CalculatedContent/pyRMT-1
Python library for Random Matrix Theory, cleaning schemes for correlation matrices, and portfolio optimization
CalculatedContent/pytorch-siamese
Siamese Network implementation using Pytorch
CalculatedContent/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
CalculatedContent/White-box-Cartoonization
Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”
CalculatedContent/ww-book