PyTorch Geometric Temporal provides models and tools for spatiotemporal signal processing with neural learning.
Open source
24 alternativesmgl
mgl provides a machine learning library in Common Lisp, including neural networks and Gaussian processes.
About mgl
mgl is an open source machine learning library written in Common Lisp by Gábor Melis, with some parts originally contributed by Ravenpack International. It focuses mainly on neural networks, including Boltzmann machines and feed-forward and recurrent backpropagation networks. It also includes tools for datasets, resampling, feature selection and encoding, gradient-based optimization, Gaussian processes, and a bag-of-words approach to natural language processing.
Most of the library is built on MGL-MAT, which provides BLAS and CUDA support. According to the source, the stated focus is power and performance rather than ease of use. Setup requires installing two main dependencies, CL-CUDA and MGL-MAT, manually because they are not yet in Quicklisp. If no suitable GPU or CUDA SDK is present, the library falls back to BLAS and Lisp code.
Key features
- Feed-forward and recurrent backpropagation neural networks
- Boltzmann machines
- Gaussian processes
- Cross-validation, bagging, shuffling and partitioning for resampling
- Gradient descent and conjugate gradient optimizers
- Feature selection and feature encoding
Best for: Common Lisp developers and researchers who want neural network and related statistical models and are willing to trade ease of use for power and performance.
Good for
- Released under the MIT licence
- GPU use through CUDA when a suitable GPU and CUDA SDK are present, with BLAS and Lisp fallback
- Covers several model families, including neural networks, Boltzmann machines and Gaussian processes
Watch out for
- The stated focus is power and performance, not ease of use
- CL-CUDA and MGL-MAT are not yet in Quicklisp and must be installed manually
- Running code on the GPU requires wrapping it in MGL-MAT:WITH-CUDA*
mgl at a glance
- Website
- github.com/melisgl/mgl
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
mgl alternatives
Tools and sites you could use instead, ranked by how closely they match.
This Common Lisp repository collects algorithms for online linear classification.
Open source
24 alternatives
This repository implements random forest models in Common Lisp for classification tasks.
Open source
24 alternatives
Bender helps developers build neural networks for iOS using TensorFlow models and Metal.
Open source
24 alternatives
Katib automates machine learning on Kubernetes, including hyperparameter tuning and neural architecture search.
Open source
24 alternatives
neural-fortran provides a parallel framework for deep learning in Fortran.
Open source
24 alternativesPopular in ML Training & Optimization
Well-known listings from the same topic.
Edwardedwardlib.orgAerosolveaerosolve.airbnb.techDataturedatature.ioTogether AItogether.aiOptunaoptuna.orgCatBoostcatboost.ai
mgl FAQ
Does mgl use the GPU?
It supports CUDA through MGL-MAT. Code is run on the GPU by wrapping it in MGL-MAT:WITH-CUDA*, and MGL-MAT:CUDA-AVAILABLE-P can confirm whether the GPU is being used. If there is no suitable GPU or the CUDA SDK is not installed, mgl falls back to BLAS and Lisp code.
What license does mgl use?
mgl is licensed under the MIT licence, as stated in the COPYING file in the repository.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.