Tensors and Dynamic neural networks in Python with strong GPU acceleration

Visualizer for neural network, deep learning and machine learning models

Low-code framework for building custom LLMs, neural networks, and other AI models

A scikit-learn compatible neural network library that wraps PyTorch

A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Scalable and user friendly neural :brain: forecasting algorithms.

Google's differential privacy libraries.

JAX-based neural network library

TensorFlow-based neural network library

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Message Passing Neural Networks for Molecule Property Prediction