Chandan Singh
Chandan Singh
csinva.github.io
Slides, paper notes, class notes, blog posts, and research on ML π, statistics π, and AI π€.
gan-vae-pretrained-pytorch
Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.
imodels
Interpretable ML package π for concise, transparent, and accurate predictive modeling (sklearn-compatible).
hierarchical-dnn-interpretations
Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" π§ (ICLR 2019)
gpt-paper-title-generator
Generating paper titles (and more!) with GPT trained on data scraped from arXiv.
data-viz-utils
Functions for easily making publication-quality figures with matplotlib.
disentangled-attribution-curves
Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"
iprompt
Finding semantically meaningful and accurate prompts.
matching-with-gans
Matching in GAN latent space for better bias benchmarking and semantic image editing. πΆπ»π§πΎπ©πΌβπ¦°π±π½ββοΈπ΄πΎ
mdl-complexity
MDL Complexity computations and experiments from the paper "Revisiting complexity and the bias-variance tradeoff".