A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

Generative Probabilistic Novelty Detection with Adversarial Autoencoders

AutoGBT is used for AutoML in a lifelong machine learning setting to classify large volume high cardinality data streams under concept-drift. AutoGBT was developed by a joint team ('autodidact.ai') from Flytxt, Indian Institute of Technology Delhi and CSIR-CEERI as a part of NIPS 2018 AutoML for Lifelong Machine Learning Challenge.

Weakly Supervised Dense Event Captioning in Videos, i.e. generating multiple sentence descriptions for a video in a weakly-supervised manner.

An official PyTorch implementation of the paper "Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language", NeurIPS 2018

Keras implementation of "Image Inpainting via Generative Multi-column Convolutional Neural Networks" paper published at NIPS 2018

Implementation for <Learning towards Minimum Hyperspherical Energy> in NIPS'18.

Open-set Recognition with Adversarial Autoencoders

Gold Loss Correction for training neural networks with labels corrupted with severe noise

Harvard Fall 2019 Applied Math 207 A Primer and Critique of Prior Networks

A re-implementation of the Pommerman environment in C++

Code, documents, and deployment configuration files, related to our participation in the 2018 NIPS Adversarial Vision Challenge "Robust Model Track"

A LaTex template for reports, based on the elegant NIPS 2018 style.

The code for DirBN in NeurIPS 2018

Tensorflow implementation of paper ‘Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoder’ (NIPS18)

AI for Prosthetics NIPS 2018 Challenge. Repo created from helper: https://github.com/seungjaeryanlee/osim-rl-helper

Our submission for the NeurIPs 2018: Adversarial Vision Challenge (Targeted Attack Track). Top-10 submission

Using LDA, we analyze a large collection of NIPS research papers from the past 3 decades, o discover the latest trends in machine learning.

The docker image of the NIPS 2018 challenge (no visualisations for now)