仅使用numpy从头开始实现神经网络,包括反向传播公式推导过程; numpy构建全连接层、卷积层、池化层、Flatten层;以及图像分类案例及精调网络案例等,持续更新中... ...
backward-propagation 开源项目推荐(59 个)
backward-propagation 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 59 个仓库该项目在 GitHub 上没有填写描述
Implemented Convolutional Neural Network, LSTM Neural Network, and Neural Network From Scratch in Python Language.
A structured, hands-on guide to neural networks and deep learning fundamentals, covering forward propagation, activation functions, backpropagation, optimization, TensorFlow, Keras, PyTorch, and CIFAR-10 image classification.
搭建、深度学习、前向传播、反向传播、梯度下降和模型参数更新、classification、forward-propagation、backward-propagation、gradient descent、python、text classification
Desenvolvimento de ferramenta para efetuar a Modelagem e a Migração Sísmica de um modelo 2D.
building a deep neural network with as many layers as you want!
A from-scratch Multilayer Perceptron (MLP) for classifying MNIST handwritten digits. Built without TensorFlow, Keras, or PyTorch, using only basic Python and CuPy.
Deep Learning & Labs Course, NYCU, 2023
Learning about Perceptron and Multi layered perceptron
A.K.A. NUS ME5411 Final Project. Implemented a CNN framework without off-the-shelf libraries and its application for character recognition.
backward_step, a FreeFem++ code which solves the backward step benchmark problem for Navier Stokes flow.
Neural Network from scratch using Python and NumPy, featuring forward/backward propagation and basic optimizers. Perfect for learning deep learning fundamentals.
A C++ machine learning framework/library.
I build the Micrograd autogradient engine, which is a functioning neural network with forward pass, backward propagation, and stochastic gradient descent, all built from scratch. This is derived from the great @karpathy micrograd lecture. Each notebook is complete with Andrei's lecture code and speech, as well as my own code, anecdotes and addition
Implementing a 4 layer neural to identify digits from a 28x28 grid using just python and numpy
A highly modular design and implementation of fully-connected feedforward neural network structured on NumPy matrices
CNN, ANN, Python, Matlab
A pure Go neural network implementation with a Transformer implementation example (a project only for fun)
This code uses computational graph and neural network to solve the five-layer traffic demand estimation in Sioux Falls network. It also includes comparison of models and 10 cross-validations.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/backward-propagation。
- 该话题在 GitHub 上共有 59 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 853 Star,覆盖 6 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。