Название: Neural Network Tutorials - Herong's Tutorial Examples
Автор: Herong Yang
Издательство: Independently published
Год: 2020 (Version 1.20)
Страниц: 193
Язык: английский
Формат: pdf, epub
Размер: 14.5 MB

This book is a collection of notes and sample codes written by the author while he was learning Neural Networks in Machine Learning. Topics include Neural Networks (NN) concepts: nodes, layers, activation functions, learning rates, training sets, etc.; deep playground for classical neural networks; building neural networks with Python; walking through Tariq Rashi's 'Make Your Own Neural Network' source code; using 'TensorFlow' and 'PyTorch' machine learning platforms; understanding CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), GNN (Graph Neural Network).

What Is TensorFlow? TensorFlow is an end-to-end open source platform for Machine Learning with APIs for Python, C++ and many other programming languages. TensorFlow was originally developed by researchers and engineers working on the Google Brain team within Google's Machine Intelligence Research organization to conduct machine learning and deep neural networks research.

TensorFlow is designed with 2 key concepts, Tensor and Flow, as described below:
1. Tensor - A tensor is a multidimensional array with elements of the same data type. A tensor is also called a multidimensional matrix, or vector.
2. Flow (Tensor Flow Graph) - A Tensor Flow Graph is a directed graph representing an expression of multiple tensor operations. In tensor flow graph, a node represents a single tensor operation and an edge represents a single tensor flowing from one operation into another operation.

PyTorch is a Python-based scientific computing package targeted at two sets of audiences: A replacement for NumPy to use the power of GPUs and a deep learning research platform that provides maximum flexibility and speed. PyTorch was originally developed as a research framework by a Facebook intern in 2017.