Book Image

Artificial Intelligence for Big Data

By : Anand Deshpande, Manish Kumar
Book Image

Artificial Intelligence for Big Data

By: Anand Deshpande, Manish Kumar

Overview of this book

In this age of big data, companies have larger amount of consumer data than ever before, far more than what the current technologies can ever hope to keep up with. However, Artificial Intelligence closes the gap by moving past human limitations in order to analyze data. With the help of Artificial Intelligence for big data, you will learn to use Machine Learning algorithms such as k-means, SVM, RBF, and regression to perform advanced data analysis. You will understand the current status of Machine and Deep Learning techniques to work on Genetic and Neuro-Fuzzy algorithms. In addition, you will explore how to develop Artificial Intelligence algorithms to learn from data, why they are necessary, and how they can help solve real-world problems. By the end of this book, you'll have learned how to implement various Artificial Intelligence algorithms for your big data systems and integrate them into your product offerings such as reinforcement learning, natural language processing, image recognition, genetic algorithms, and fuzzy logic systems.
Table of Contents (19 chapters)
Title Page
Copyright and Credits
Packt Upsell
Contributors
Preface
Index

NEFCLASS


In the previous chapters, we learned the general theory of neural networks, which resemble the human brain in terms of a network of computation units that are interconnected. The neural networks are trained by adjusting the weights on the synapses (connectors). As we have seen, the neural network can be trained to solve classification problems such as image recognition. The neural networks accept crisp input and adjust weights to produce output values (classification into a class). However, as we have seen in this chapter, the real-world input have a degree of fuzziness in the input as well as a degree of vagueness for the output.

The membership of the input and output variables in a specific cluster or a type is represented with a degree instead of a crisp set. We can combine the two approaches to formulate a neuro-fuzzy-classifier (NEFCLASS), which is based on fuzzy input and utilizes the elegance of a multi-layer neural network in order to solve the classification problem. In...