Build, Manage and Deploy AI/ML Systems

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

End-to-end training of sparse deep neural networks with little-to-no performance loss.

Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.

Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"

An open-source NLP research library, built on PyTorch.

Contains code for the NeurIPS 2019 paper "Practical Deep Learning with Bayesian Principles"

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

A curated list of awesome responsible machine learning resources.

A curated list of applied machine learning and data science notebooks and libraries across different industries (by @firmai)

Sequential model-based optimization with a `scipy.optimize` interface

A comprehensive collection of recent papers on graph deep learning

Bayesian Deep Learning Benchmarks

A library for easy and efficient manipulation of tensor networks.

Notebooks about Bayesian methods for machine learning

A system for quickly generating training data with weak supervision

Semantic Image Synthesis with SPADE

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Fast and flexible AutoML with learning guarantees.

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!

A very simple framework for state-of-the-art Natural Language Processing (NLP)

TensorFlow Reinforcement Learning

Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

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

This repository contains lists of state-or-art weakly supervised semantic segmentation works

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

A customisable 3D platform for agent-based AI research

Reinforcement learning resources curated