Book Image

Java for Data Science

By : Richard M. Reese, Jennifer L. Reese
Book Image

Java for Data Science

By: Richard M. Reese, Jennifer L. Reese

Overview of this book

para 1: Get the lowdown on Java and explore big data analytics with Java for Data Science. Packed with examples and data science principles, this book uncovers the techniques & Java tools supporting data science and machine learning. Para 2: The stability and power of Java combines with key data science concepts for effective exploration of data. By working with Java APIs and techniques, this data science book allows you to build applications and use analysis techniques centred on machine learning. Para 3: Java for Data Science gives you the understanding you need to examine the techniques and Java tools supporting big data analytics. These Java-based approaches allow you to tackle data mining and statistical analysis in detail. Deep learning and Java data mining are also featured, so you can explore and analyse data effectively, and build intelligent applications using machine learning. para 4: What?s Inside ? Understand data science principles with Java support ? Discover machine learning and deep learning essentials ? Explore data science problems with Java-based solutions
Table of Contents (19 chapters)
Java for Data Science
Credits
About the Authors
About the Reviewers
www.PacktPub.com
Customer Feedback
Preface

Training a neural network


There are three basic training approaches:

  • Supervised learning - With supervised learning the model is trained with data that matches input sets to output values

  • Unsupervised learning - In unsupervised learning, the data does not contain results, but the model is expected to determine relationships on its own

  • Reinforcement learning - Similar to supervised learning, but a reward is provided for good results

These datasets differ in the information they contain. Supervised and reinforcement learning contain correct output for a set of input. The unsupervised learning does not contain correct results.

A neural network learns (at least with supervised learning) by feeding an input into a network and comparing the results, using the activation function, to the expected outcome. If they match, then the network has been trained correctly. If they don't match then the network is modified.

When we modify the weights we need to be careful not to change them too drastically....