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.

Related Content you might be interested in

Current Title:

Small book image
Artificial Intelligence for Big Data
Anand Deshpande | Manish Kumar
May, 2018 | 384 pages
Small book image
Mastering Hadoop 3
Manish Kumar | Chanchal Singh
Feb, 2019 | 544 pages
Small book image
Deep Learning with Hadoop
Dipayan Dev
Feb, 2017 | 206 pages
Small book image
Hands-On Artificial Intelligence on Google Cloud Platform
Vikram Chaudhari | Anand Deshpande | Manish Kumar
Mar, 2020 | 350 pages
Table of Contents (19 chapters)
Title Page
Title Page
Copyright and Credits
Copyright and Credits
Packt Upsell
Packt Upsell
Contributors
Contributors
Preface
Preface
Free Chapter
1
Big Data and Artificial Intelligence Systems
Big Data and Artificial Intelligence Systems
Results pyramid
What the human brain does best
What the electronic brain does best
Best of both worlds
Summary
2
Ontology for Big Data
Ontology for Big Data
Human brain and Ontology
Ontology of information science
Summary
3
Learning from Big Data
Learning from Big Data
Supervised and unsupervised machine learning
The Spark programming model
The Spark MLlib library
Regression analysis
Data clustering
The K-means algorithm
Data dimensionality reduction
Singular value decomposition
The principal component analysis method
Content-based recommendation systems
Frequently asked questions
Summary
4
Neural Network for Big Data
Neural Network for Big Data
Fundamentals of neural networks and artificial neural networks
Perceptron and linear models
Nonlinearities model
Feed-forward neural networks
Gradient descent and backpropagation
Overfitting
Recurrent neural networks
Frequently asked questions
Summary
5
Deep Big Data Analytics
Deep Big Data Analytics
Deep learning basics and the building blocks
Building data preparation pipelines
Practical approach to implementing neural net architectures
Hyperparameter tuning
Distributed computing
Distributed deep learning
Frequently asked questions
Summary
6
Natural Language Processing
Natural Language Processing
Natural language processing basics
Text preprocessing
Feature extraction
Applying NLP techniques
Implementing sentiment analysis
Frequently asked questions
Summary
7
Fuzzy Systems
Fuzzy Systems
Fuzzy logic fundamentals
ANFIS network
Fuzzy C-means clustering
NEFCLASS
Frequently asked questions
Summary
8
Genetic Programming
Genetic Programming
Genetic algorithms structure
KEEL framework
Encog machine learning framework
Introduction to the Weka framework
Attribute search with genetic algorithms in Weka
Frequently asked questions
Summary
9
Swarm Intelligence
Swarm Intelligence
Swarm intelligence 
The particle swarm optimization model
Ant colony optimization model
MASON Library
Opt4J library
Applications in big data analytics
Handling dynamical data
Multi-objective optimization
Frequently asked questions
Summary
10
Reinforcement Learning
Reinforcement Learning
Reinforcement learning algorithms concept
Reinforcement learning techniques
Deep reinforcement learning
Frequently asked questions
Summary
11
Cyber Security
Cyber Security
Big Data for critical infrastructure protection
Understanding stream processing
Cyber security attack types
Understanding SIEM
Splunk
ArcSight ESM
Frequently asked questions
Summary
12
Cognitive Computing
Cognitive Computing
Cognitive science
Cognitive Systems
Application in Big Data analytics
Cognitive intelligence as a service
Frequently asked questions
Summary
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think
Index
Index

The particle swarm optimization model

The particle swarm optimization (PSO) model is inspired by flocking of birds and the schooling movement of fish. The goal of the PSO model is to find an optimum solution (food source or a place to live) within a dynamic space. The swarm starts at a random location and a random velocity and is based on the collective behavior by exploring and exploiting the search space. The unique feature of PSO is that the agents operate in a formation that optimizes the search and also minimizes the collective effort in converging to an optimum solution. The agents within a swarm that follows the PSO model follow some of the guideline principles:

  • Separation: Each individual agent is programmed in a way that it is able to keep a sufficient distance with the flock-mates so that they do not run into each other and at the same time, maintain a separate existence space for itself to be part of a formation in search of an optimum solution. The agent follows the nearest neighbor...
Previous Section
End of Section 3
Next Section