Skip to content
Avatar
🎯
Focusing
🎯
Focusing
216 followers · 12 following

Achievements

Arctic Code Vault Contributor

Achievements

Arctic Code Vault Contributor

Highlights

  • Pro

Organizations

@conda-forge @BerkeleyML @Yu-Group @lumosvision @response4life
Block or Report

Block or report csinva

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
csinva/README.md

Hi there 👋. I'm Chandan, a PhD candidate at UC Berkeley working on interpretable machine learning.

🤖 I make general-purpose AI packages and cheatsheets

Interpretable and accurate predictive modeling, sklearn-compatible (JOSS 2021)

Slides, paper notes, class notes, blog posts, and research on ML, stat, and AI

Making it easier to build stable, trustworthy data-science pipelines

🧠 Some of my research focuses on interpreting neural networks

hierarchical-dnn-interpretations Hierarchical interpretations for neural network predictions (ICLR 2019)

deep-explanation-penalization Interpretations are useful: penalizing explanations to align neural networks with prior knowledge (ICML 2020)

adaptive-wavelets Adaptive, interpretable wavelets across domains (NeurIPS 2021)

transformation-importance Transformation Importance with Applications to Cosmology (ICLR Workshop 2020)

📊 My research also focuses on implactful applied data-science problems

covid19-severity-prediction Extensive and accessible COVID-19 data + forecasting for counties and hospitals (HDSR 2021)

rule-vetting General pipeline for deriving clinical decision rules

iai-clinical-decision-rule Interpretable clinical decision rules for predicting intra-abdominal injury

molecular-partner-prediction Predicting successful CME events using only clathrin markers

And I also explore various aspects of deep learning and machine learning

gan-vae-pretrained-pytorch Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch

gpt2-paper-title-generator Generating paper titles with GPT-2

disentangled-attribution-curves Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees (arxiv 2019)

data-viz-utils Functions for easily making publication-quality figures with matplotlib

matching-with-gans Matching in GAN latent space for better bias benchmarking. (CVPR workshop 2021)

mdl-complexity Revisiting complexity and the bias-variance tradeoff (TOPML workshop 2021)

Open-source contributions

Major: autogluon , big-bench , nl-augmenter

Minor: conference-acceptance-rates , iterative-random-forest , interpretable-ml-book , awesome-interpretable-machine-learning , awesome-machine-learning-interpretability , executable-books

Mini-projects

hummingbird-tracking, imodels-experiments, nano-descriptions, news-title-bias, java-mini-games, news-balancer, arxiv-copier, dnn-experiments, max-activation-interpretation-pytorch, hpa-interp, sensible-local-interpretations, global-sports-analysis, mouse-brain-decoding, ...

Pinned

  1. csinva.github.io Public

    Slides, paper notes, class notes, blog posts, and research on ML 📉, statistics 📊, and AI 🤖.

    HTML 397 93

  2. imodels Public

    Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

    Jupyter Notebook 433 45

  3. hierarchical-dnn-interpretations Public

    Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

    Jupyter Notebook 103 18

  4. laura-rieger/deep-explanation-penalization Public

    Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

    Jupyter Notebook 94 12

  5. Yu-Group/covid19-severity-prediction Public

    Extensive and accessible COVID-19 data + forecasting for counties and hospitals. 📈

    Jupyter Notebook 203 83

  6. gan-vae-pretrained-pytorch Public

    Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.

    Jupyter Notebook 104 34

830 contributions in the last year

Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Mon Wed Fri
Learn how we count contributions
Less More

Contribution activity

January 2022

Created 53 commits in 7 repositories
Created 1 repository

Created a pull request in csinva/imodels that received 1 comment

Shrinkage distillation

+50 −0 • 1 comment
Opened 3 other pull requests in 2 repositories
Yu-Group/autogluon 2 merged
Yu-Group/veridical-flow 1 merged
Reviewed 1 pull request in 1 repository
awslabs/autogluon 1 pull request
2 contributions in private repositories Jan 13 – Jan 14

Seeing something unexpected? Take a look at the GitHub profile guide.