Book Image

Python: Advanced Guide to Artificial Intelligence

By : Giuseppe Bonaccorso, Rajalingappaa Shanmugamani
Book Image

Python: Advanced Guide to Artificial Intelligence

By: Giuseppe Bonaccorso, Rajalingappaa Shanmugamani

Overview of this book

This Learning Path is your complete guide to quickly getting to grips with popular machine learning algorithms. You'll be introduced to the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and learn how to use them in the best possible manner. Ranging from Bayesian models to the MCMC algorithm to Hidden Markov models, this Learning Path will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries. You'll bring the use of TensorFlow and Keras to build deep learning models, using concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Next, you'll learn the advanced features of TensorFlow1.x, such as distributed TensorFlow with TF clusters, deploy production models with TensorFlow Serving. You'll implement different techniques related to object classification, object detection, image segmentation, and more. By the end of this Learning Path, you'll have obtained in-depth knowledge of TensorFlow, making you the go-to person for solving artificial intelligence problems This Learning Path includes content from the following Packt products: • Mastering Machine Learning Algorithms by Giuseppe Bonaccorso • Mastering TensorFlow 1.x by Armando Fandango • Deep Learning for Computer Vision by Rajalingappaa Shanmugamani
Table of Contents (31 chapters)
Title Page
About Packt
Tensor Processing Units

Sanger's network

A Sanger's network is a neural network model for online Principal Component extraction proposed by T. D. Sanger in Optimal Unsupervised Learning in a Single-Layer Linear Feedforward Neural NetworkSanger T. D., Neural Networks, 1989/2. The author started with the standard version of Hebb's rule and modified it to be able to extract a variable number of principal components (v1, v2, ..., vm) in descending order (λ1 > λ2 > ... > λm). The resulting approach, which is a natural extension of Oja's rule, has been called the Generalized Hebbian Rule (GHA) (or Learning). The structure of the network is represented in the following diagram:

The network is fed with samples extracted from an n-dimensional dataset:

The m output neurons are connected to the input through a weight matrix, W = {wij}, where the first index refers to the input components (pre-synaptic units) and the second one to the neuron. The output of the network can be easily computed with a scalar product;...