Directory
Published directory entries matching your search.
A Matlab package implementing machine learning algorithms described in the textbook Pattern Recognition and Machine Learning by C. Bishop. It is written purely in Matlab and is self-contained with no external dependency.
Machine Learning library for PHP. Algorithms, Cross Validation, Neural Network, Preprocessing, Feature Extraction and much more in one library.
Polyaxon is a platform for building, training, and monitoring large-scale deep learning applications. It deploys into any data center or cloud provider and supports major deep learning frameworks such as Tensorflow, MXNet, Caffe, and Torch. It manages workloads with container and node management and offers hyperparameter tuning through experiment groups defining a search algorithm and search space.
PyBroker is a Python framework for developing algorithmic trading strategies with a focus on machine learning. It provides a backtesting engine built in NumPy and accelerated with Numba, model training and backtesting using Walkforward Analysis, parameter optimization with Optuna, and access to historical data from Alpaca, Yahoo Finance, and AKShare. It supports Python 3.11+ on Windows, Mac, and Linux.
Retrieval-based-Voice-Conversion-WebUI is a project for training voice conversion models from voice data, with an easy-to-use WebUI. It includes a pymss/MSST model to separate vocals and instruments and a high-pitch voice extraction algorithm to prevent a muted sound problem. Dependencies differ by hardware, including CPU, AMD, Intel and NVIDIA GPU setups.
Basic sampling algorithms for Julia.
A tutorial project for applying machine learning in Python with scikit-learn, a Python module built on numpy and scipy. It aims to teach practical application of scikit-learn algorithms; the stated audience is experienced Python developers familiar with numpy and scipy. Prebuilt PDF and HTML versions, tutorial source and exercise solutions are available, and the material is under a Creative Commons Attribution 3.0 license.
CodeFormer, developed by sczhou, is a robust open-source face restoration algorithm designed for restoring old photos and AI-generated faces. The associated web demo is intended for research purposes. It is available via the Replicate platform or for local deployment, runs on Nvidia L40S GPUs, and typically completes predictions in 3 seconds. The associated research was published at NeurIPS 2022.
Stan is software for Bayesian data analysis that combines statistical modeling capabilities with user-friendly interfaces and open-source development. Its probabilistic programming language supports applications from simple linear regression to multi-level models and time-series analysis. Interfaces exist for Python, Julia, R, and the Unix shell, usable on laptops, clusters, or in the cloud. Official documentation covers the language, inference algorithms, and built-in functions.
Surprise is a Python scikit for building and analyzing recommender systems that deal with explicit rating data. It includes built-in datasets, prediction algorithms such as SVD and NMF, similarity measures, and cross-validation tools. The documentation states that Surprise does not support implicit ratings or content-based information.
GFPGAN is a face restoration algorithm for old photos or AI-generated faces, created by tencentarc and available on Replicate. The model runs on Nvidia L40S GPU hardware and costs approximately $0.0076 to run. It is also open source and can be run on a personal computer with Docker.
Tune is a Python library for experiment execution and hyperparameter tuning at any scale. It supports machine learning frameworks including PyTorch, XGBoost, and TensorFlow and Keras, and runs algorithms such as Population Based Training (PBT) and HyperBand/ASHA. It also integrates with hyperparameter optimization tools including Ax, BayesOpt, BOHB, Nevergrad, and Optuna.
Vega is an AutoML algorithm tool chain developed by Noah's Ark Laboratory. It covers hyperparameter optimization, data augmentation, network architecture search, model compression and fully train functions, and supports PyTorch, TensorFlow and MindSpore backends.
VocalRemover is a free online application that separates a song into a karaoke version without vocals and an acapella version with isolated vocals. It uses artificial intelligence algorithms and processing usually takes about 10 seconds.
Voctro Labs is a Barcelona-based company founded in 2011 that develops AI-based voice, music and audio technologies for creative companies and individuals. Its products include Voiceful, a toolkit for speech and singing voice experiences with a cloud-based API and SDK libraries, and Virtual Singers for Yamaha's VOCALOID software. Services include personalized voices and customized algorithms.
Zipline is a Pythonic algorithmic trading library and an event-driven system for backtesting. It is described as used in production as the backtesting and live-trading engine powering Quantopian. Historical data input and performance statistics output are based on Pandas DataFrames. Zipline supports Python 2.7, 3.5 and 3.6 and may be installed via pip or conda.
