AoE (AI on Edge，终端智能，边缘计算) 是一个终端侧AI集成运行时环境 (IRE)，帮助开发者提升效率。

A small convolution neural network deep learning framework implemented in c++.

Convolutional Neural Network with CUDA (MNIST 99.23%)

A resource-conscious neural network implementation for MCUs

ADAS is short for Adaptive Step Size, it's an optimizer that unlike other optimizers that just normalize the derivative, it fine-tunes the step size, truly making step size scheduling obsolete, achieving state-of-the-art training performance

A C++ implementation to create, visualize and train Convolutional Neural Networks

A tiny deep learning training framework implemented from scratch in C++ that follows PyTorch's API.

CUDA for MNIST training/inference

C++ implementation of KDTree & kNN classification on MNIST

Deep Neural Network from scratch in C++ for learning purposes

C++ demo of deep neural networks (MLP, CNN)

Implementing CNN for Digit Recognition (MNIST and SVHN dataset) using PyTorch C++ API

C++ 实现 BP 神经网络识别手写数字数据集 MNIST

MNIST accelerator using binary qunatization on Xilinx pynq-z2

A simple yet powerful C++17 implementation of deep neural networks from scratch. High efficient and vectorised implementation using OpenMp.

Collection of Machine Learning Algorithms

Spiking Neural Network implementation in pure C++ with minimal dependencies

A node based deep neural network library on top of CuDNN

A CUDA project that implements optimizations of neural network operations on the GPU.

Mnist digits multi perceptron neural-network training from scratch with c++ and opencv matrix. (nn with c++)