book

Machine Learning for Industrial Applications

Name: Machine Learning for Industrial Applications
Author: Kolla Bhanu Prakash
ISBN: 9781394268962

by Kolla Bhanu Prakash

September 2024

Beginner

352 pages

7h 19m

English

Wiley-Scrivener

Read now

Unlock full access

Cover
Table of Contents
Series Page
Title Page
Copyright Page
Dedication Page
Preface
1 Overview of Machine Learning
1.1 Introduction1.2 Sorts of Machine Learning1.3 Regulated Gaining Knowledge of Dog and Human1.4 Solo Learning1.5 Support Mastering1.6 Bundles or Applications of Machine Learning1.7 Challenges in Machine Learning1.8 Limitations of Machine Learning1.9 Projects in Machine LearningReferences
2 Machine Learning Building Blocks
2.1 Data Collection2.2 Data Preparation2.3 Data Wrangling2.4 Data Analysis2.5 Model Selection2.6 Model Building2.7 Model Evaluation2.8 DeploymentBibliography
3 Multilayer Perceptron (in Neural Networks)
3.1 Multilayer Perceptron for Digit Classification3.2 Training Multilayer Perceptron3.3 BackpropagationReferences

4 Kernel Machines
4.1 Different Kernels and Their Applications4.2 Some Other Kernel FunctionsReferences
5 Linear and Rule-Based Models
5.1 Least Squares Methods5.2 The Perceptron5.3 Support Vector Machines5.4 Linearity with Kernel MethodsReferences
6 Distance-Based Models
6.1 Introduction6.2 K-Means Algorithm6.3 Elbow Method6.4 K-Median6.5 K-Medoids, PAM (Partitioning Around Medoids)6.6 CLARA (Clustering Large Applications)6.7 CLARANS (Clustering Large Applications Based on Randomized Search)6.8 Hierarchical Clustering6.9 Agglomerative Nesting Hierarchical Clustering (AGNES)6.10 DIANAReferences
7 Model Ensembles
7.1 Bagging7.2 Boosting7.3 StackingReferences
8 Binary and Beyond Binary Classification
8.1 Binary Classification8.2 Logistic Regression8.3 Support Vector Machine8.4 Estimating Class Probabilities8.5 Confusion Matrix8.6 Beyond Binary Classification8.7 Multi-Class Classification8.8 Multi-Label ClassificationReference
9 Model Selection
9.1 Model Selection Considerations9.2 Model Selection Strategies9.3 Types of Model Selection9.4 The Principle of Parsimony9.5 Examples of Model Selection Criterions9.6 Other Popular Properties9.7 Key Considerations9.8 Model Validation9.9 Self-Driving Cars9.10 K-Fold Cross Validation9.11 No One-Size-Fits-All Model Validation9.12 Validation Strategies9.13 K-Fold Cross-Validation9.14 Capture Confirmation Using Hold-Out Validation9.15 Comparison of Validation StrategyReferences
10 Support Vector Machines
10.1 History10.2 Model10.3 Kinds of Support Vector Machine10.4 Hyperplane and Support Vectors Inside the SVM Set of Rules10.5 Support Vectors10.6 SVM Kernel10.7 How Can It Function?10.8 SVM for Classification10.9 SVM for Regression10.10 Python Implementation of Support Vector MachineReferences
11 Clustering
11.1 Example11.2 Kinds of Clustering11.3 What are the Utilization of Clustering?11.4 Models11.5 Uses of Clustering11.6 Bunching Algorithms or Clustering Algorithms11.7 Instances of Clustering Algorithms11.8 Python Implementation of K-MeansReferences
12 Reinforcement Learning
12.1 Model12.2 Terms Utilized in Reinforcement Learning12.3 Key Elements of Reinforcement Learning12.4 Instances of Reinforcement Learning12.5 Advantages of Reinforcement Learning12.6 Challenges with Reinforcement Learning12.7 Sorts of Reinforcement12.8 What are the Useful Utilizations of Reinforcement Learning?12.9 How is Reinforcement Learning Extraordinary from Supervised and Unsupervised Learning?12.10 Ways to Deal with Execute Reinforcement Learning12.11 Components of Reinforcement Learning12.12 Typical Reinforcement Learning Algorithms12.13 Support Learning Algorithm: Python Implementation Utilizing Q-LearningReferences
13 Recommender Systems
13.1 Recommender Frameworks13.2 Use-Instances of Suggestion Framework13.3 Phases of Proposal Technique13.4 How Does a Recommender Device Create Artistic Creations?13.5 Kinds of Recommendation System13.6 Half and Half Proposal Contraption13.7 What Strategies are Utilized to Develop Recommender Frameworks?13.8 Evaluation Metrics13.9 Python Implementation of Recommendation Systems13.10 Forcing Recommender Structures with MarvselReferences
14 Advancements in Deep Learning
14.1 What is Deep Learning?14.2 The Difficulties of Deep Learning14.3 Upgrades in Deep Learning14.4 Consideration and Transformers14.5 Generative Ill-Disposed Networks (GANs)14.6 Vehicle Encoders14.7 Python Code for Profound LearningReferences
15 Advanced Deep Learning Using Julia Programming
15.1 Convolutional Neural Network15.2 Deep Neural Network Implementation15.3 Recurrent Neural Network Implementation15.4 Long Short-Term Memory Implementation15.5 Generative Adversarial Network (GAN) Implementation15.6 Gated Recurrent Unit (GRU) Implementation15.7 Radial Basis Function Network (RBFN) Implementation15.8 Multilayer Perceptron (MLP) Implementation15.9 Self-Organizing Map (SOM) Implementation15.10 Deep Belief Network (DBN) Implementation15.11 Restricted Boltzmann Machine (RBM) Implementation15.12 Autoencoder Implementation
16 Machine Learning for Industrial Applications
16.1 Python Code for Generating Music Using Neural Networks16.2 Image Caption Generator16.3 Image Classification Using Julia16.4 BERT Text Classifier on Tensor Processing Unit16.5 Python Program for Reinforcement Learning Agent for Atari 260016.6 Python Program for Multi-Lingual ASR with Transformers16.7 Python Program for Reinforcement Learning for Connect X16.8 Stock Market Analysis and Forecasting Using Deep Learning16.9 ASL Recognition with Deep Learning16.10 Build Rick Sanchez Bot Using Transformers
Index
End User License Agreement

Content preview from Machine Learning for Industrial Applications

Index

Agglomerative clustering, 189
Alexa, 5
AlphaGo, 19
ANOVA, 69
Artificial Intelligence, 1
Autoencoder, 294

Backpropagation, 60
Bagging, 104
Boosting, 107
Bootstrap, 132
Bootstrapping, 107
Brier score, 120

CLARA, 97
Clustering, 89, 177
Confusion matrix, 121
Convolutional neural network, 277

Data exploration, 22
Data wrangling, 22
DataLoader, 301
Deep belief network, 290
Deep learning, 245–255
Deep neural network, 278
Dropout, 298

EfficientNet, 251
Elbow method, 92
Ensemble modeling, 103

Flux, 301

Gated recurrent unit, 285
Generative adversarial network, 283
Gradient descent, 54
GrowNet, 247

Hyperparameter tuning, 16
Hyperplane, 153

Image caption generator, 299

Julia, 277

Keras, 297
Kernel machines, 63
K-means clustering, 90
K-median, 94

Laplace RBF Kernel, 68
logistic regression, 55
Long short term memory, 281

Malware, 8
Manhattan distance, 87
Mean absolute error, 227
Minkowski distance, 87
Multi-label classification, 124
Multilayer perceptron, 52

OPTICS, 197, 198
Overfitting, 2

Partitioning clustering, 179
Perceptron, 73

Radial basis function, 64
Random separation, 130
RBFN, 286
Recommender frameworks, 225
Recurrent neural network, 279
Reinforcement learning, 3, 205–209
ReLU, 78
Restricted Boltzmann machine, 292

Self-organizing map, 289
Sigmoid Kernel, 63
Softmax, 81
Stochastic gradient descent, 59
StyleGAN, 19
Support vector machines, 149, 150
Swish, 80

TabNet, 249
TensorFlow, 56
Tokenizer, 302
Transformers, ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Algorithms and Data Structures for Massive Datasets

Publisher Resources

ISBN: 9781394268962Purchase Link

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Machine Learning for Industrial Applications

by Kolla Bhanu Prakash

Index

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.