The Wayback Machine - https://web.archive.org/web/20210730011448/https://github.com/csinva
Skip to content
Avatar
🎯
Focusing
🎯
Focusing
190 followers · 12 following · 90

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

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 like to explain and simplify machine learning

csinva.github.io Slides, paper notes, class notes, blog posts, and research on ML, stat, and AI.

imodels Interpretable ML package for concise and accurate predictive modeling (sklearn-compatible).

stable-pipelines 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)

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

adaptive-wavelet-distillation Adaptive, interpretable wavelets across domains.

📊 I care about working on serious applied data-science problems

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

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.

matching-with-gans Matching in GAN latent space for better bias benchmarking.

mdl-complexity "Revisiting complexity and the bias-variance tradeoff".

disentangled-attribution-curves "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"

Pinned

  1. csinva.github.io

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

    HTML 372 88

  2. imodels

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

    Jupyter Notebook 241 23

  3. hierarchical-dnn-interpretations

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

    Jupyter Notebook 93 17

  4. laura-rieger/deep-explanation-penalization

    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 83 10

  5. Yu-Group/covid19-severity-prediction

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

    Jupyter Notebook 186 76

  6. gan-vae-pretrained-pytorch

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

    Jupyter Notebook 77 25

860 contributions in the last year

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

Contribution activity

July 2021

Created 9 commits in 3 repositories
Opened 1 pull request in 1 repository
csinva/imodels
1 merged
2 contributions in private repositories Jul 4 – Jul 20