decodyng

coremltools

Converter tools for Core ML.

data-viz-portfolio

Hub for work created in MSAN's Information Visualization course in Spring 2015.

dataChallenge

elecTweets

Exploratory project in collecting data from API and scraping to explore intersection between Twitter conversation and polling data. Eventual inclusion of ad-buy data hoped for, once accessible on Sunlight Foundation.

learning-from-human-preferences

Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"

marginalia

mvp_ray_sacred

Simple example showing how to integrate Ray parallelization with the Sacred experiment framework

subspace_clustering

Code from a project to find newly-dense regions of categorical feature space using the technique here: https://www.cs.cornell.edu/johannes/papers/1998/sigmod1998-clique.pdf

adversarial-policies

Find best-response to a fixed policy in multi-agent RL

learning-from-human-preferences

Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"

decodyng/mvp_ray_sacred

Simple example showing how to integrate Ray parallelization with the Sacred experiment framework

decodyng/subspace_clustering

Code from a project to find newly-dense regions of categorical feature space using the technique here: https://www.cs.cornell.edu/johannes/papers/1998/sigmod1998-clique.pdf

decodyng/learning-from-human-preferences

Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"

decodyng/marginalia

decodyng/coremltools

Converter tools for Core ML.

decodyng/data-viz-portfolio

Hub for work created in MSAN's Information Visualization course in Spring 2015.

decodyng/dataChallenge

decodyng/elecTweets

Exploratory project in collecting data from API and scraping to explore intersection between Twitter conversation and polling data. Eventual inclusion of ad-buy data hoped for, once accessible on Sunlight Foundation.

decodyng/mlgroup5

Shared code/data for MSAN 621 Rotten Tomatoes classification project

decodyng/floydhub_code

decodyng/keras

Deep Learning for humans

decodyng/minerl

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

decodyng/moria

Adventures in deep learning

decodyng/psiTurk

An open platform for science on Amazon Mechanical Turk.

decodyng/SimCLR

A PyTorch implementation of SimCLR based on ICML 2020 paper "A Simple Framework for Contrastive Learning of Visual Representations"

decodyng/simple_bc_baseline

decodyng/stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

decodyng/stable-baselines3

PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.

decodyng/who-recalls-the-recalls

Scraper/parser to turn URLs of FDA recall data into structured CSVs

decodyng/worksafe

"Don't be a statistic; respect workplace safety" Bayes Hackathon 2014 project visualizing OSHA data - David Croushore & Cody Wild