Data to Actionable Knowledge (DtAK) Lab

adversarial-robustness-public

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

hip-mdp-public

Code for training and testing a Hidden Parameter Markov Decision Process, used to facilitate the transfer of learning

hs-bnn-public

interactive-reconstruction

Code for Evaluating the Interpretability of Generative Models by Interactive Reconstruction

mbrl-smdp-ode

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

ocbnn-public

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

POPCORN-POMDP

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

rrr

Code/figures in Right for the Right Reasons

tree-regularization-public

Code for AAAI 2018 accepted paper: "Beyond Sparsity: Tree Regularization of Deep Models for Interpretability"

dtak/rrr

Code/figures in Right for the Right Reasons

dtak/adversarial-robustness-public

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

dtak/mbrl-smdp-ode

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

dtak/ocbnn-public

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

dtak/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

dtak/POPCORN-POMDP

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

dtak/interactive-reconstruction

Code for Evaluating the Interpretability of Generative Models by Interactive Reconstruction

dtak/lit

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

dtak/addressing-leakage

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

dtak/interpretable_ope_public

dtak/Decision-Region-for-ICU-Hypotension

dtak/hierarchical-disentanglement

Code for Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement

dtak/local-independence-public

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

dtak/optimal-summaries-public

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

dtak/power-constrained-bandits-public

dtak/wide-bnns-public

dtak/kernel-evolutions-public

dtak/osiris

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

dtak/porbnet

dtak/rethinking_discount_reg_public

Simulations for the paper: "Rethinking Discount Regularization: New Interpretations, Unintended Consequences, and Solutions for Regularization in Reinforcement Learning"

dtak/dtak.github.io

dtak/anchor-box

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

dtak/dynamic-mixing

dtak/i-airl

dtak/kernel_mismatch_workshop

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

dtak/pgmult

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

dtak/robust_decision_focused_rl_public

dtak/signature-activation

dtak/tensorpack

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

dtak/umls_tagger