Neural Network Tutorials - Herong's Tutorial Examples

∟Deep Playground for Classical Neural Networks

This chapter provides introductions and tutorials on Deep Playground. Topics include introduction to Deep Playground; solving the classification problems without and with hidden layers; impact comparison of training set, network configuration, learning rate, and activation function.

What Is Deep Playground

Simple Model in Playground

Impact of Extra Input Features

Impact of Additional Hidden Layers and Neurons

Complex Model in Playground

Impact of Training Set Size

Impact of Neural Network Configuration

Impact of Learning Rate

Impact of Activation Functions

Takeaways:

• Deep Playground is a nice open source interactive tool for learning classical neural networks.
• Deep Playground runs in a Web browser without any additional plugins or programs.
• Deep Playground comes with some 2 dimensional classification and regression problems.
• Deep Playground supports up to 6 hidden layers and 8 neurons per layer.
• Deep Playground supports a selection of 4 activation functions: ReLU(), Tanh(), Sigmoid(), and Linear().

Table of Contents

 About This Book

►Deep Playground for Classical Neural Networks

 Building Neural Networks with Python

 Simple Example of Neural Networks

 TensorFlow - Machine Learning Platform

 PyTorch - Machine Learning Platform

 Gradio - ML Demo Platform

 CNN (Convolutional Neural Network)

 RNN (Recurrent Neural Network)

 GNN (Graph Neural Network)

 GAN (Generative Adversarial Network)

 Performance Evaluation Metrics

 References

 Full Version in PDF/EPUB

Deep Playground for Classical Neural Networks - Updated in 2023, by Herong Yang