Paved2Paradise – cost-effective and scalable LiDAR simulation by factoring the real world.
PyTorch PointPillars – my minimal PyTorch implementation of the PointPillars model described here.
PyTorch PointNet++ – my minimal PyTorch implementation of the PointNet++ model described here.
AQuaMaM – an autoregressive, quaternion manifold model for rapidly estimating complex SO(3) distributions.
PyTorch implicit-PDF – my minimal PyTorch implementations of the implicit-PDF model described here.
PyTorch NeRF and pixelNeRF – my minimal PyTorch implementations of NeRF (as described here) and pixelNeRF (as described here).
PyTorch VQ-VAE – my minimal PyTorch implementation of the VQ-VAE model described here.
Boformer – a look-ahead multi-entity Transformer for jointly modeling coordinated agents in different sports.
DEformer – an order-agnostic distribution estimating Transformer.
PyTorch NADE – my PyTorch implementations of NADE (as described here) and order-agnostic NADE (as described here).
baller2vec++ – a look-ahead multi-entity Transformer for modeling coordinated agents.
baller2vec – a multi-entity Transformer for multi-agent spatiotemporal modeling.
PyTorch Geodesic Loss – implements a criterion for computing the distance between rotation matrices as described here and here.
PyTorch Volume Rotator – applies explicit 3D transformations to feature volumes in PyTorch.
BigGAN-AM – improves the sample diversity of BigGAN and synthesizes Places365 images using the BigGAN generator.
Strike (With) A Pose – a simple GUI application for generating adversarial poses of objects.
Apache Solr (contributor) – I implemented the RankNet scoring model as described here (Jira).
Learning To Name Colors With Word Embeddings – an improved version of the color name model described here.
RankNet and LambdaRank – my (slightly modified) Keras implementation of RankNet (as described here) and PyTorch implementation of LambdaRank (as described here).
Recurrent Convolutional Neural Network Text Classifier – my (slightly modified) Keras implementation of the Recurrent Convolutional Neural Network (RCNN) described here.
scikit-learn (contributor) – I implemented the Complement Naive Bayes classifier described here (pull request).
Sequences With Sentences – a convolutional recurrent neural network that can handle data sequences containing a mixture of fixed size and variable size (e.g., text) inputs at each time step.
(batter|pitcher)2vec – a model inspired by word2vec (hence the name) that learns distributed representations of MLB players.
Deep Semantic Similarity Model – my Keras implementation of the Deep Semantic Similarity Model (DSSM)/Convolutional Latent Semantic Model (CLSM) described here.
LociSelect – a simulated annealing algorithm for selecting loci (locations in DNA) from the output of a high-throughput DNA sequencer for use in genetic analyses.
ARTificial Intelligence – a simple convolutional neural network that attempts to identify the movements and artists of visual art.
Hangouts NLP – a program that performs a number of different natural language processing analyses on instant messaging data.
Sexy Time Markov Model – a Markov model for simulating sex!
Football-o-Genetics – an application for "evolving" near-optimal offensive play calling strategies.
Social Networks in American Football – a social network analysis of coaches and teams in college and professional football. This was my final project for Social Network Analysis, a free course I took through Coursera.
ScatterPlot3D – an application for visualizing and exploring three-dimensional scatter plot data.
CyanogenMod – I developed an option that allows users to keep the status bar visible during “Expanded desktop” mode (pull requests: 1a and 1b).