Chandan Singh

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

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

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

imodelsX. Interpret text data with LLMs (sklearn compatible).

gpt-paper-title-generator. Generating paper titles (and more!) with GPT trained on data scraped from arXiv.

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

iprompt. Finding semantically meaningful and accurate prompts.

interpretable-embeddings. Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

tree-prompt. Tree prompting: easy-to-use scikit-learn interface for improved prompting.

disentangled-attribution-curves. Using / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"

matching-with-gans. Matching in GAN latent space for better bias benchmarking and semantic image editing. 👶🏻🧒🏾👩🏼‍🦰👱🏽‍♂️👴🏾

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

cookiecutter-ml-research. A logical, reasonably standardized, but flexible project structure for conducting ml research 🍪

mdl-complexity. MDL Complexity computations and experiments from the paper "Revisiting complexity and the bias-variance tradeoff".

clinical-rule-development. Building and vetting clinical decision rules.

transformation-importance. Using / reproducing TRIM from the paper "Transformation Importance with Applications to Cosmology" 🌌 (ICLR Workshop 2020)

tree-prompt-experiments. Create a tree of prompts during training that improves efficiency and accuracy.

glaucoma-diagnosis. Code for diagnosing glaucoma from Lumos lens

clinical-rule-survey. Analyzing clinical decision instruments through the lens of data and large language models.

imodels-data. Preprocessed data for various popular tabular datasets to go along with imodels.

fmri. Experiments with language fMRI data from Alex Huth lab. More organized repo here: https://github.com/microsoft/automated-brain-explanations

pybaobab-fork. Fork of pybaobabdt adding more customization.

news-balancer. News Balancer takes a story and provides articles on that story with credibility and varying political bias. The homepage will randomly generate a story from its archives, but a user can type in a query to get stories relating to their query along with their credibility / political bias.

max-activation-interpretation-pytorch. Code for creating maximal activation images (like Deep Dream) in pytorch with various regularizations / losses.

dnn-ensemble. Testing the properties of ensembled neural networks.

trees-to-networks. Bridging random forests and deep neural networks. Partial implementation of "Neural Random Forests" https://arxiv.org/abs/1604.07143

acronym-generator. Generator acronyms given a sequence of words (useful for making paper titles).

abide-multitask-learning. Multi-task learning of functional connectivity on the ABIDE dataset.

tpr-fmri. Python

news-title-bias. Scraping and analyzing political bias in news titles using data from allsides.com

local-vae. Making locally disentangled vaes.

pyfim-clone. Clone of pyfim making it installable as a dependency. Copied from http://www.borgelt.net/pyfim.html

fmri_decoding. Python

dnn-experiments. A set of scripts and experiments making it easier to analyze deep learning empirically.

mouse-brain-decoding. Decoding images from calcium recordings using data from stringer et al. 2018.

mini-games. Code for simple games made in java + google sheets.

inverse-scaling. A prize for finding tasks that cause large language models to show inverse scaling

scattering-transform-experiments. Repository for experiments with scattering transforms

hummingbird-tracking. Code for tracking various things in hummingbird video

analyzing-patient-perspectives. Analyzing interview data from the PediDOSE EFIC interviews using LLMs.

imodels-playground. Demos for visualizing how rule-based models work.

neural-spike-sorting. Experimental code for performing spike sorting using a neural network.

stable-interpretation. Exploring ways to extract stable interpretations from neural networks.

pyGAM. [HELP REQUESTED] Generalized Additive Models in Python