Fundamentals of Machine Learning discusses the basics of python, use of python in computing and provides a general outlook on machine learning. This book provides an insight into concepts such as linear regression with one variable, linear algebra, and linear regression with multiple inputs. The classification with logistics regression model, regularization, neural networks, decision trees are explained in this book. The introduction to several concepts of machine learning such as component analysis, classification using k-Nearest Algorithm, k Means Clustering, computing with Tensor flow and natural language processing have been explained. This book explains the fundamental concepts of machine learning.
Author(s): Euan Russano; Elaine Ferreira Avelino
Publisher: Arcler Press
Year: 2019
Language: English
Pages: 290
Cover
Title Page
Copyright
ABOUT THE AUTHORS
TABLE OF CONTENTS
List of Figures
List of Tables
List of Abbreviations
Preface
Chapter 1 Introduction to Python
1.1. What Is Python
1.2. What Makes Python Suitable For Machine Learning?
1.3. What Are Other Computational Tools For Machine Learning?
1.4. How To Obtain And Configure Python?
1.5. Scientific Python Software Set
1.6. Modules
1.7. Notebooks
1.8. Variables And Types
1.9. Operators And Comparison
Chapter 2 Computing Things With Python
2.1. Formatting And Printing to Screen
2.2. Lists, Dictionaries, Tuples, And Sets
2.3. Handling Files
2.4. Exercises
2.5. Python Statements
2.6. For And While Loops
2.7. Basic Python Operators
2.8. Functions
Chapter 3 A General Outlook on Machine Learning
Chapter 4 Elements of Machine Learning
4.1. What Is Machine Learning?
4.2. Introduction To Supervised Learning
4.3. Introduction To Unsupervised Learning
4.4. A Challenging Problem: The Cocktail Party
Chapter 5 Linear Regression With One Variable
5.1. Introduction
5.2. Model Structure
5.3. Cost Function
5.4. Linear Regression Using Gradient Descent Method Using Python
Exercises
Chapter 6 A General Review On Linear Algebra
6.1. Introduction
6.2. Matrices And Vectors
6.3. Addition
6.4. Multiplication
6.5. Matrix-Vector Multiplication
6.6. Matrix-Matrix Multiplication
6.7. Inverse And Transpose
Exercises
Chapter 7 Linear Regression With Multiple Inputs/Features
7.1. Gradient Descent For Multiple Variables Linear Regression
7.2. Normal Equation
7.3. Programming Exercise: Linear Regression With Single Input And Multiple Inputs
Chapter 8 Classification Using Logistic Regression Model
8.1. Logistic Regression Model Structure
8.2. Concept Exercise: Classifying Success In Exam According Hours Of Study
8.3. Programming Exercise: Implementation Of The Exam Results Problem In Python From Scratch
8.4. Bonus: Logistic Regression Using Keras
Chapter 9 Regularization
9.1. Regularized Linear Regression
Chapter 10 Introduction To Neural Networks
10.1. The Essential Block: Neurons
10.2. How To Implement A Neuron Using Python And Numpy
10.3. Combining Neurons to Build a Neural Network
10.4. Example Of Feedforward Neural Network
10.5. How To Implement A Neural Network Using Python and Numpy
10.6. How To Train A Neural Network
10.7. Example Of Calculating Partial Derivatives
10.8. Implementation Of A Complete Neural Network With Training Method
Chapter 11 Introduction To Decision Trees and Random Forest
11.1. Decision Trees
11.2. Random Forest
11.3. Programming Exercise – Decision Tree From Scratch With Python
Chapter 12 Principal Component Analysis
12.1. Introduction
12.2. Mathematical Concepts
12.3. Principal Component Analysis Using Python
Chapter 13 Classification Using K-Nearest Neighbor Algorithm
13.1. Introduction
13.2. Principles and Definition of KNN
13.3. Algorithm
13.4. Example and Python Solution
Chapter 14 Introduction To Kmeans Clustering
14.1. How Kmeans Works?
14.2. Kmeans Algorithm
Chapter 15 Computing With Tensorflow: Introduction And Basics
15.1. Installing Tensorflow Library
15.2. Tensors
15.3. Computational Graph and Session
15.4. Operating With Matrices
15.5. Variables
15.6. Placeholders
15.7. Ways Of Creating Tensors
15.8. Summary
Chapter 16 Tensorflow: Activation Functions And Optimization
16.1. Activation Functions
16.2. Loss Functions
16.3. Optimizers
16.4. Metrics
Chapter 17 Introduction To Natural Language Processing
17.1. Definition Of Natural Language Processing
17.2. Usage Of NLP
17.3. Obstacles In NLP
17.4. Techniques Used In NLP
17.5. NLP Libraries
17.6. Programming Exercise: Subject/Topic Extraction Using NLP
17.7. Text Tokenize Using NLTK
17.8. Synonyms From Wordnet
17.9. Stemming Words With NLTK
17.10. Lemmatization Using NLTK
Chapter 18 Project: Recognize Handwritten Digits Using Neural Networks
18.1. Introduction
18.2. Project Setup
18.3. The Data
18.4. The Algorithm
Appendix A
Bibliography
Index
Back Cover
