A complete guide that will help you get familiar with Machine Learning models, algorithms, and optimization techniques.
Key Features
- Understand the core concepts and algorithms of Machine Learning.
- Get started with your Machine Learning career with this easy-to-understand guide.
- Discover different Machine Learning use cases across different domains.
Description
Since the last two decades, there have been many advancements in the field of Machine Learning. If you are new or want a comprehensive understanding of Machine Learning, then this book is for you.
The book starts by explaining how important Machine Learning is today and the technology required to make it work. The book then helps you get familiar with basic concepts that underlie Machine Learning, including basic Python Programming. It explains different types of Machine Learning algorithms and how they can be applied in various domains like Recommendation Systems, Text Analysis and Mining, Image Processing, and Social Media Analytics. Towards the end, the book briefly introduces you to the most popular metaheuristic algorithms for optimization.
By the end of the book, you will develop the skills to use Machine Learning effectively in various application domains.
What you will learn
- Discover various applications of Machine Learning in social media.
- Explore image processing techniques that can be used in Machine Learning.
- Learn how to use text mining to extract valuable insights from text data.
- Learn how to measure the performance of Machine Learning algorithms.
- Get familiar with the optimization algorithms in Machine Learning.
Who this book is for
This book delivers an excellent introduction to Machine Learning for beginners with no prior knowledge of coding, maths, or statistics. It is also helpful for existing and aspiring data professionals, students, and anyone who wishes to expand their Machine Learning knowledge.
Author(s): Deepali R Vora, Gresha S Bhatia
Publisher: BPB Publications
Year: 2023
Language: English
Pages: 302
Cover Page
Title Page
Copyright Page
Dedication Page
About the Authors
About the Reviewer
Acknowledgements
Preface
Errata
Table of Contents
1. Introduction to ML
Introduction
Structure
Objectives
Introduction to Machine Learning (ML)
Models in Machine Learning
Supervised machine learning model through training
Unsupervised machine learning model: Self-sufficient learning
Semi-supervised machine learning model
Reinforcement machine learning model: Hit and Trial
Types of Machine Learning Algorithms
Working of Machine Learning algorithm
Challenges for Machine Learning Projects
Limitations of machine learning
Application areas of ML
Difference between the terms data science, data mining, machine learning and deep learning
Conclusion
Questions and Answers
2. Python Basics for ML
Introduction
Structure
Objectives
Spyder IDE
Jupyter Notebook
Python: Input and Output Commands
Logical Statements
Loop and Control Statements
Functions and Modules
Class Handling
Exception Handling
File Handling
String functions
Conclusion
Questions and Answers
3. An Overview of ML Algorithms
Introduction
Structure
Objectives
Machine learning modeling flow
Terms used in preprocessing
Raw data (or just data)
Prepared data
Need for Data Preprocessing
Preprocessing in ML
Researching the best model for the data
Training and testing the model on data
Evaluation
Hyperparameter tuning
Prediction
Metrics Used
Regression algorithms
Types of regression techniques
Linear Regression
Logistic Regression
Polynomial Regression
Stepwise Regression
Ridge Regression
Lasso Regression
ElasticNet Regression
Classification
Terminology used in Classification Algorithms
Types of classification algorithms
Performance measures for classification
Clustering
Clustering algorithms
K-Means Clustering
Mean-Shift Clustering
Agglomerative Hierarchical Clustering
Clustering Validation
Neural Network and SVM
Building Blocks: Neurons
Combining Neurons into a Neural Network
Training the neural network
Neural Network Architectures
Support vector machine (SVM)
Machine Learning Libraries in Python
Numpy
Pandas
Populating the Dataframe
Displaying the Data Using Dataframe
Accessing the Data Selectively in Dataframe
Basic Descriptive Statistics using Pandas
Data transformation
Data Preprocessing – Handling missing values
MatplotLib
Line Graph
Scatter Plot
Bar plot
Histogram
Pie Chart
Evaluation of ML Systems
Test and Train Datasets
Performance Measure
Model Evaluation Techniques
Model evaluation metrics
Classification Metrics
Regression Metrics
Conclusion
Questions
4. Case Studies and Projects in Machine Learning
Introduction
Structure
Objectives
Recommendation Generation
Importance of recommendation systems
Key terms used
Items/Documents
Query/Context
Approaches for building recommendation systems
Basic recommendation systems
Candidate Generation
Recommendation generation
Information collection phase
Learning phase
Prediction/recommendation phase
Evaluation metrics for recommendation algorithms
Statistical accuracy metric
Case study on Recommendation system: E-learning system domain
Recommender systems
Problem definition
Objective of the case study
Considerations for the case study
System development
Constraints / limitations while developing the recommendation system
Text Analysis and Mining
Importance of text mining
Basic blocks of text mining system using ML
Steps involved in preparing an unstructured text document for deeper analysis
Text mining techniques
Information Retrieval (IR)
Natural language processing (NLP)
Sentiment analysis
Naive Bayes
Linear regression
Support Vector Machines (SVM)
Deep learning
Case study on product recommendation system based on sentiment analysis
Product recommendation
Problem definition
System development
Considerations for the case study
Opinion mining
Image processing
Importance of image processing
Purpose of image processing
Basic Image Processing System
Image Processing using popular ML algorithms
Real Time case studies of Image Processing using ML
Problem definition
Objective of the case study
Considerations for the case study
System development
Algorithms that can be employed
Tool Utilization
Constraints/Limitations while developing the system
Evaluation Measures
Predictive analytics
Importance of predictive analytics
Need for predictive analysis
Machine Learning vs Predictive Modeling
Building a predictive model
Types of predictive algorithms
Types of Predictive Analytical Models
Comparison of Predictive Modeling and Predictive Analytics
Predictive modeling vs data analytics
Comparison between and Predictive Analytics and Data Analytics
Uses or applications of Predictive Analytics
Benefits of predictive analytics
Challenges of predictive modeling
Limitations of predictive modeling
Case studies
Social media analytics
Case study of Instagram
Case study on Customer churning analytics
Building the hypothesis
Case study on learning analytics in education systems
Challenges faced
Approach
Other case studies
Conclusion
5. Optimization in ML Algorithm
Introduction
Structure
Objectives
Optimization – Need of ML projects
Types of optimization techniques
Conventional Approach
Metaheuristic Approach
Basic Optimization Techniques
Backpropagation optimization
Gradient descent optimization
Metaheuristic approaches to optimization
Types of metaheuristic algorithms
Single solution-based algorithms
Population-based algorithms
Improvisation of ML algorithms by optimizing the learning parameters
Case study 1: Metaheuristic Optimization Techniques in Healthcare
Case Study 2: Genetic Algorithm (GA) in Batch Production
Optimization using Python
Conclusion
Questions
Index
