Pinned Repositories
Election-Web-Scraping-and-Visualization
Web scraping election results and visualizing as an interactive map
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
EY-Competition-2019
EY NextWave Data Science Challenge 2019: Predicting citizen's location in a period of time using previous geolocation records
gym-sokoban
Sokoban environment for OpenAI Gym
InfoGAN-PyTorch
PyTorch Implementation of InfoGAN
NLU-email-title
Natural Language Understanding task for autonomous email title generation.
plasticc-kit
Starter Kit for the Photometric LSST Astronomical Time-series Classification Challenge
pymatch
Semi-supervised_Learning_DL
Semi-supervised Learning method for image classification (1k classes). Structure: CNN with residual connections stacked on top of the encoder module of a convolutional auto-encoder (Pytorch).
SP19-DL-collaborative-notes
Collaborative lecture notes for Spring '19 NYU DL class
Millebean's Repositories
Millebean/Election-Web-Scraping-and-Visualization
Web scraping election results and visualizing as an interactive map
Millebean/examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Millebean/EY-Competition-2019
EY NextWave Data Science Challenge 2019: Predicting citizen's location in a period of time using previous geolocation records
Millebean/gym-sokoban
Sokoban environment for OpenAI Gym
Millebean/InfoGAN-PyTorch
PyTorch Implementation of InfoGAN
Millebean/NLU-email-title
Natural Language Understanding task for autonomous email title generation.
Millebean/plasticc-kit
Starter Kit for the Photometric LSST Astronomical Time-series Classification Challenge
Millebean/pymatch
Millebean/Semi-supervised_Learning_DL
Semi-supervised Learning method for image classification (1k classes). Structure: CNN with residual connections stacked on top of the encoder module of a convolutional auto-encoder (Pytorch).
Millebean/SP19-DL-collaborative-notes
Collaborative lecture notes for Spring '19 NYU DL class
Millebean/TalkingData
How to combine online and offline information for prediction of customer behavior?