🤖 A portable, header-only, artificial neural network library written in C99

Simple tutorials using Keras Framework

Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms

[NeurIPS 2025 Spotlight] Official implementation of the SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment

A simple machine learning framework written in Swift 🤖

Open-source machine learning framework for Java. Designed with speed and lightweight in mind.

SimpleDNN is a machine learning lightweight open-source library written in Kotlin designed to support relevant neural network architectures in natural language processing tasks

[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets

A Deep Learning framework that analyses Windows PE files to detect malicious Softwares.

[ICLR 2023] MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization

A deep learning library for use in high-performance computing applications in modern Fortran

State of the Art Neural Networks for Deep Learning

[CVPR 2022 Oral] Generalizable Human Pose Triangulation

Generate 3D meshes from 2D images and retexture them directly in Unity.

Wonderful Matrices to Build Small Language Models

Multilayer perceptron deep neural network with feedforward and back-propagation for MNIST image classification using NumPy

This code implements a basic MLP for speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and decoding are performed with Kaldi. The current implementation supports dropout and batch normalization. An example for phoneme recognition using the standard TIMIT dataset is provided.

Yet another neural network library

Selected problems and their solutions from the book on "Machine Intelligence in Design Automation"

Unofficial Implementation of "Bag of Tricks for Efficient Text Classification", 2016, Armand Joulin et al. (https://arxiv.org/pdf/1607.01759.pdf)

GEDFN: Graph-Embedded Deep Feedforward Network

Reservoir computing library for .NET. Enables ESN , LSM and hybrid RNNs using analog and spiking neurons working together.

Neuromodulatory Control Networks (NCNs), a novel LLM architectural modification inspired by the neuromodulatory systems in the vertebrate brain.

Machine Learning library for python

A Command-Line Program of Feedforward Neural Networks

[INACTIVE] Amazingly simple to build and train various neural networks. The library is an object-oriented neural network approach (baked with Typescript), containing stateless and stateful neural network architectures.

Feed-forward neural network implementation in C with SIMD instructions

Very basic neural network implementation.

An attempt to use financial news to predict stock market

A tweet sentiment classifier using word2vec and Keras. This Keras model can be saved and used on other tweet data, like streaming data extracted through the tweepy API.