Showing 36 of 1845 projects
Jupyter notebooks implementing algorithms, proofs, and summaries from 'The Elements of Statistical Learning' textbook.
A sequence-to-sequence transformer model for predicting chemical reaction pathways (retrosynthesis) with uncertainty calibration.
A collection of deep learning tutorials and implementations using Keras and Lasagne, with a focus on Theano-based frameworks.
A high-performance C++ automatic differentiation library for large-scale, performance-critical systems.
A collection of CI pipelines, Docker images, and optimized examples to simplify JAX development on NVIDIA GPUs.
A joint audio tagging and speech recognition model that adds audio event detection to OpenAI Whisper with minimal computational overhead.
A simple, realtime visualization server for monitoring neural network training performance across frameworks.
A scikit-learn-compatible Python implementation of ReBATE, a suite of Relief-based feature selection algorithms for machine learning.
A benchmark dataset and toolkit for RF-based drone detection and identification using raw IQ data and deep learning models.
A PyTorch reinforcement learning library implementing DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, and IMPALA.
A JupyterLab extension that adds support for creating notebooks from customizable templates.
An open-source machine learning framework built in Rust for high-performance and extensible ML tasks.
A practical demo using LSTM neural networks with TensorFlow to predict lottery numbers.
An open-source machine learning framework built in Rust for high-performance and extensible ML tasks.
A dataset of millions of news articles labeled by credibility type for training fake news detection algorithms.
Python library for multilinear algebra operations and tensor factorizations with support for dense and sparse tensors.
ilastik-shell, applets, and workflows to string them together.
A PyTorch implementation of the DrQA model for reading comprehension and open-domain question answering.
A V library for AI and high-performance scientific computing with pure-V BLAS/LAPACK implementations.
A V library for AI and high-performance scientific computing with pure-V BLAS/LAPACK implementations.
A Naive Bayes machine learning implementation in Elixir with multiple models and storage options.
Interactive visualization tool for understanding Capsule Network (CapsNet) layers and their internal workings.
A curated list of research, applications, tutorials, and software built using the H2O open-source machine learning platform.
A Scala framework for distributed supervised learning of decision tree ensemble models, inspired by Google's PLANET.
A Flutter plugin for integrating Firebase ML Kit's on-device and cloud machine learning features into mobile apps.
A Neo4j-based library for building high-performance recommendation engines with real-time and pre-computed capabilities.
A Julia package for multivariate statistics and data analysis, including dimension reduction techniques like PCA and LDA.
Hyperparameter optimization and feature selection for scikit-learn using evolutionary algorithms. A modern alternative to GridSearchCV and RandomizedSearchCV.
A Julia package providing standard tools and models for text analysis and natural language processing.
A purely functional artificial neural network library for Haskell, enabling rapid prototyping through higher-order function composition.
Convert Torch7 neural network models to Apple CoreML format for deployment on iOS/macOS devices.
A real-time online machine learning library built on Apache Storm for scalable stream processing with incremental algorithms.
A Ruby gem providing TensorFlow bindings for basic tensor operations and machine learning tasks.
A tree ensemble machine learning method that delivers better results than gradient boosted decision trees on many datasets.
A Java HTTP client library for interacting with the OpenAI API and compatible providers in a simple, consistent manner.
A neural network playground built in pure Swift for iOS, with no third-party dependencies.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.