Data to Actionable Knowledge (DtAK) Lab

rrr

Code/figures in Right for the Right Reasons

adversarial-robustness-public

Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

ocbnn-public

General purpose library for BNNs, and implementation of OC-BNNs in our 2020 NeurIPS paper.

mbrl-smdp-ode

PyTorch implementation of "Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs", NeurIPS 2020

prediction-constrained-topic-models

Public repo containing code to train, visualize, and evaluate semi-supervised topic models and baselines for regression/classification on labeled bag-of-words dataset, as described in Hughes et al. AISTATS 2018

POPCORN-POMDP

Implementation of "POPCORN: Partially Observed Prediction Constrained Reinforcement Learning" (Futoma, Hughes, Doshi-Velez, AISTATS 2020)

interactive-reconstruction

Code for Evaluating the Interpretability of Generative Models by Interactive Reconstruction

lit

Code for AAAI 2020 paper "Ensembles of Locally Independent Prediction Models"

addressing-leakage

Code for the paper 'Addressing leakage in Concept Bottleneck Models'

interpretable_ope_public

batch-apprenticeship-learning

Truly Batch Apprenticeship Learning with Deep Successor Features.

Decision-Region-for-ICU-Hypotension

hierarchical-disentanglement

Code for Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement

local-independence-public

Code/figures in Learning Qualitatively Diverse and Interpretable Rules for Classification

optimal-summaries-public

Code repository for the MLHC 2022 paper "Learning Optimal Summaries of Clinical Time-series with Concept Bottleneck Models"

power-constrained-bandits-public

wide-bnns-public

policy-summarization-with-user-models-public

kernel-evolutions-public

osiris

Omitting-States-Irrelevant-to-Return Importance Sampling estimator for off-policy evaluation

porbnet

dtak.github.io

anchor-box

This repository contains the code for out work, Guarantee Regions for Local Explanations

dynamic-mixing

i-airl

kernel_mismatch_workshop

Code for Implications of Gaussian process kernel mismatch for out-of-distribution data (ICML 2023 workshops)

pgmult

Dependent multinomials made easy: stick-breaking with the Pólya-gamma augmentation

signature-activation

tensorpack

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

umls_tagger