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... ...
-
Updated
Nov 28, 2020 - Jupyter Notebook
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... ...
Implemented Convolutional Neural Network, LSTM Neural Network, and Neural Network From Scratch in Python Language.
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
Python version of Andrew Ng's Machine Learning Course.
Create a Deep Neural Network from Scratch using Python3.
Deep Learning Specialization (5 Courses) . Course offered by deeplearning.ai and Coursera. Taught by Andrew Ng.
Explains the basic concepts of NN like activation functions, forward propagation, backward propagation, gradient descent, finding the optimized weights and bias etc.
This notebook demonstrates a neural network implementation using NumPy, without TensorFlow or PyTorch. Trained on the MNIST dataset, it features an architecture with input layer (784 neurons), two hidden layers (132 and 40 neurons), and an output layer (10 neurons) with sigmoid activation.
Logistic Regression and Neural Networks implementation from scratch
A.K.A. NUS ME5411 Final Project. Implemented a CNN framework without off-the-shelf libraries and its application for character recognition.
Deep Learning & Labs Course, NYCU, 2023
A highly modular design and implementation of fully-connected feedforward neural network structured on NumPy matrices
This is a project to recognize cat using logistic regression with Neural Network concepts of backward and forward propagation from DeepLearning.AI.
Built a simple RNN Model using NumPy
Learning about Perceptron and Multi layered perceptron
Building a cat classifier via L-layer neural network
A tool that quickly and accurately segments Urdu sentences and words in your text.
Add a description, image, and links to the backward-propagation topic page so that developers can more easily learn about it.
To associate your repository with the backward-propagation topic, visit your repo's landing page and select "manage topics."