Подборка — 3 881

PyTorch library for creating and training sequence autoencoders in just two lines of code

Adaptive Neural Execution Engine for transformers. Per-token sparse inference with dynamic layer skipping, profiler-based gating, and KV-cache-safe compute reduction.

A canon of deep learning optimization algorithms.

A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware.

A library that makes downloading publicly available neuromorphic datasets a breeze and provides event-based data transformation/augmentation pipelines.

lifelines is a complete survival analysis library, written in pure Python

scikit-survival is a Python module for survival analysis built on top of scikit-learn. It allows doing survival analysis while utilizing the power of scikit-learn, e.g., for pre-processing or doing cross-validation.

> source code and experiments results for Home Credit Default Risk.

> source code and experiments results for Google AI Open Images - Object Detection Track.

> source code and experiments results for TGS Salt Identification Challenge.

> source code and experiments results for Airbus Ship Detection Challenge.

> source code and experiments results for 2018 Data Science Bowl.

> source code and experiments results for Santander Value Prediction Challenge.

> source code for Toxic Comment Classification Challenge.

An implementation of Dell Zhang's solution to Wikipedia's Participation Challenge on Kaggle.

Kaggle Submission for "Detecting Insults in Social Commentary".

Code for the Kaggle acquire valued shoppers challenge.

Code for the CIFAR-10 competition at Kaggle, uses cuda-convnet.

Deep learning made easy.

Code for Accelerometer Biometric Competition at Kaggle.

Predicting job salaries from ads - a Kaggle competition.

Amazon access control challenge.

Code for the Best Buy competition at Kaggle.

Kaggle Dogs vs. Cats - Code for Kaggle Dogs vs. Cats competition.

Winning solution for the Galaxy Challenge on Kaggle.

A Kaggle competition: discriminate gender based on handwriting.

Merck challenge at Kaggle.

Predicting closed questions on Stack Overflow.

Predicting wine quality.

DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning.

A library for developing and comparing reinforcement learning algorithms (successor of [gym])(https://github.com/openai/gym).

Serpent.AI is a game agent framework that allows you to turn any video game you own into a sandbox to develop AI and machine learning experiments. For both researchers and hobbyists.

ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular.

Open-source software for robot simulation, integrated with OpenAI Gym.

Retro Games in Gym