neural-networks-from-scratch 开源项目推荐（246 个）

chizkidd /Karpathy-Neural-Networks-Zero-to-Hero

为Andrej Karpathy的课程《神经网络：从零到英雄》的讲座和练习提供了详细的Python笔记和代码。课程重点是从零开始构建神经网络。

mohammad-ghaderi /mnist-asm-nn

A complete neural network built entirely in x86 assembly language that learns to recognize handwritten digits from the MNIST dataset. No frameworks, no high-level languages - just pure assembly - ~5.3× faster than NumPy

ADGEfficiency /teaching-monolith

Data science teaching materials

Ameobea /neural-network-from-scratch

A neural network library written from scratch in Rust along with a web-based application for building + training neural networks + visualizing their outputs

mctrinh /neural-networks-from-scratch

《用 Python 从零实现神经网络》专为作为全北国立大学 Minh-Chien Trinh 讲授的研究生课程（深度学习、计算机视觉深度学习）的教学资源而制作。

trekhleb /micrograd-ts

🤖 A TypeScript version of karpathy/micrograd — a tiny scalar-valued autograd engine and a neural net on top of it

csukuangfj /OpenCNN

An Open Convolutional Neural Network Framework in C++ From Scratch

AyushExel /Neo

Deep learning library in python from scratch

matciotola /Lambda-PNN

Unsupervised Deep Learning-based Pansharpening with Jointly-Enhanced Spectral and Spatial Fidelity

mytechnotalent /HNN

A step-by-step walkthrough of the inner workings of a simple neural network. The goal is to demystify the calculations behind neural networks by breaking them down into understandable components, including forward propagation, backpropagation, gradient calculations, and parameter updates.

wlxiong /learn-ml-the-hard-way

Learn machine learning the hard way

CarloWood /machine-learning

My first ML sandbox

Abhinavexists /NeuNet

Implementation of feedforward-backpropagated Neural Network from Scratch

samrere /pytortto

从零实现深度学习。使用 numpy/cupy，在 GPU 上训练，遵循 pytorch API

mathspp /nnfwp

Neural Networks Fundamentals with Python – implementing neural networks from scratch

milesgranger /pyrus-nn

Lightweight, easy to use, micro neural network framework written in Rust w/ no python dependencies

akazemipour /NN-Without-Frameworks

Let's build Neural Networks from scratch.

josephjaspers /blackcat_tensors

Matrix-Vector Library Designed for Neural Network Construction. cuda (gpu) support, openmp (multithreaded cpu) support, partial support of BLAS, expression template based implementation PTX code generation identical to hand written kernels, and support for auto-differentiation

S0852306 /Surface-Fitting-Neural-Networks

Neural nets for high accuracy multivariable nonlinear regression.

ARUNAGIRINATHAN-K /NeuroMath

Artificial Neural Networks (ANNs)