Book Image

Mastering Machine Learning Algorithms

Book Image

Mastering Machine Learning Algorithms

Overview of this book

Machine learning is a subset of AI that aims to make modern-day computer systems smarter and more intelligent. The real power of machine learning resides in its algorithms, which make even the most difficult things capable of being handled by machines. However, with the advancement in the technology and requirements of data, machines will have to be smarter than they are today to meet the overwhelming data needs; mastering these algorithms and using them optimally is the need of the hour. Mastering Machine Learning Algorithms is your complete guide to quickly getting to grips with popular machine learning algorithms. You will be introduced to the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and will learn how to use them in the best possible manner. Ranging from Bayesian models to the MCMC algorithm to Hidden Markov models, this book will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries such as scikit-learn v0.19.1. You will also learn how to use Keras and TensorFlow 1.x to train effective neural networks. If you are looking for a single resource to study, implement, and solve end-to-end machine learning problems and use-cases, this is the book you need.
Table of Contents (22 chapters)
Title Page
Dedication
Packt Upsell
Contributors
Preface
13
Deep Belief Networks
Index

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;...