Artificial Intelligence for Big Data by Deshpande, Anand -- Read -- Imperial Library of Trantor

Index

Title Page Copyright and Credits

Artificial Intelligence for Big Data

Packt Upsell

Why subscribe? PacktPub.com

Contributors

About the authors About the reviewers Packt is searching for authors like you

Preface

Who this book is for What this book covers To get the most out of this book

Download the example code files Download the color images Conventions used

Get in touch

Reviews

Big Data and Artificial Intelligence Systems

Results pyramid What the human brain does best

Sensory input Storage Processing power Low energy consumption

What the electronic brain does best

Speed information storage Processing by brute force

Best of both worlds

Big Data Evolution from dumb to intelligent machines Intelligence

Types of intelligence Intelligence tasks classification

Big data frameworks

Batch processing Real-time processing

Intelligent applications with Big Data

Areas of AI

Frequently asked questions

Summary

Ontology for Big Data

Human brain and Ontology Ontology of information science

Ontology properties Advantages of Ontologies Components of Ontologies The role Ontology plays in Big Data Ontology alignment Goals of Ontology in big data Challenges with Ontology in Big Data RDF—the universal data format

RDF containers RDF classes RDF properties RDF attributes

Using OWL, the Web Ontology Language SPARQL query language

Generic structure of an SPARQL query Additional SPARQL features

Building intelligent machines with Ontologies Ontology learning

Ontology learning process

Frequently asked questions

Summary

Learning from Big Data

Supervised and unsupervised machine learning The Spark programming model The Spark MLlib library

The transformer function The estimator algorithm Pipeline

Regression analysis

Linear regression

Least square method

Generalized linear model Logistic regression classification technique

Logistic regression with Spark

Polynomial regression Stepwise regression

Forward selection Backward elimination

Ridge regression LASSO regression

Data clustering The K-means algorithm

K-means implementation with Spark ML

Data dimensionality reduction Singular value decomposition

Matrix theory and linear algebra overview The important properties of singular value decomposition SVD with Spark ML

The principal component analysis method

The PCA algorithm using SVD Implementing SVD with Spark ML

Content-based recommendation systems Frequently asked questions Summary

Neural Network for Big Data

Fundamentals of neural networks and artificial neural networks Perceptron and linear models

Component notations of the neural network Mathematical representation of the simple perceptron model

Activation functions

Sigmoid function Tanh function ReLu

Nonlinearities model Feed-forward neural networks Gradient descent and backpropagation

Gradient descent pseudocode Backpropagation model

Overfitting Recurrent neural networks

The need for RNNs Structure of an RNN Training an RNN

Frequently asked questions Summary

Deep Big Data Analytics

Deep learning basics and the building blocks

Gradient-based learning Backpropagation Non-linearities Dropout

Building data preparation pipelines Practical approach to implementing neural net architectures Hyperparameter tuning

Learning rate Number of training iterations Number of hidden units Number of epochs Experimenting with hyperparameters with Deeplearning4j

Distributed computing Distributed deep learning

DL4J and Spark

API overview

TensorFlow Keras

Frequently asked questions Summary

Natural Language Processing

Natural language processing basics Text preprocessing

Removing stop words Stemming

Porter stemming Snowball stemming Lancaster stemming Lovins stemming Dawson stemming

Lemmatization N-grams

Feature extraction

One hot encoding TF-IDF CountVectorizer Word2Vec

CBOW Skip-Gram model

Applying NLP techniques

Text classification

Introduction to Naive Bayes' algorithm Random Forest Naive Bayes' text classification code example

Implementing sentiment analysis Frequently asked questions Summary

Fuzzy Systems

Fuzzy logic fundamentals

Fuzzy sets and membership functions Attributes and notations of crisp sets

Operations on crisp sets Properties of crisp sets

Fuzzification Defuzzification

Defuzzification methods

Fuzzy inference

ANFIS network

Adaptive network ANFIS architecture and hybrid learning algorithm

Fuzzy C-means clustering NEFCLASS Frequently asked questions Summary

Genetic Programming

Genetic algorithms structure KEEL framework Encog machine learning framework

Encog development environment setup Encog API structure

Introduction to the Weka framework

Weka Explorer features

Preprocess Classify

Attribute search with genetic algorithms in Weka Frequently asked questions Summary

Swarm Intelligence

Swarm intelligence

Self-organization Stigmergy Division of labor Advantages of collective intelligent systems Design principles for developing SI systems

The particle swarm optimization model

PSO implementation considerations

Ant colony optimization model MASON Library

MASON Layered Architecture

Opt4J library Applications in big data analytics Handling dynamical data Multi-objective optimization Frequently asked questions Summary

Reinforcement Learning

Reinforcement learning algorithms concept Reinforcement learning techniques

Markov decision processes Dynamic programming and reinforcement learning

Learning in a deterministic environment with policy iteration

Q-Learning SARSA learning

Deep reinforcement learning Frequently asked questions Summary

Cyber Security

Big Data for critical infrastructure protection

Data collection and analysis Anomaly detection Corrective and preventive actions Conceptual Data Flow

Components overview

Hadoop Distributed File System NoSQL databases MapReduce Apache Pig Hive

Understanding stream processing

Stream processing semantics Spark Streaming Kafka

Cyber security attack types

Phishing Lateral movement Injection attacks AI-based defense

Understanding SIEM

Visualization attributes and features

Splunk

Splunk Enterprise Security Splunk Light

ArcSight ESM Frequently asked questions Summary

Cognitive Computing

Cognitive science Cognitive Systems

A brief history of Cognitive Systems Goals of Cognitive Systems Cognitive Systems enablers

Application in Big Data analytics Cognitive intelligence as a service

IBM cognitive toolkit based on Watson

Watson-based cognitive apps Developing with Watson

Setting up the prerequisites Developing a language translator application in Java

Frequently asked questions Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

← Prev
Back
Next →

← Prev
Back
Next →