E-Book, Englisch, 578 Seiten
Rothman Artificial Intelligence By Example
2. Auflage 2024
ISBN: 978-1-83921-281-9
Verlag: De Gruyter
Format: EPUB
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
Acquire advanced AI, machine learning, and deep learning design skills
E-Book, Englisch, 578 Seiten
ISBN: 978-1-83921-281-9
Verlag: De Gruyter
Format: EPUB
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
Understand the fundamentals and develop your own AI solutions in this updated edition packed with many new examples
Key Features
AI-based examples to guide you in designing and implementing machine intelligence
Build machine intelligence from scratch using artificial intelligence examples
Develop machine intelligence from scratch using real artificial intelligence
Book Description
AI has the potential to replicate humans in every field. Artificial Intelligence By Example, Second Edition serves as a starting point for you to understand how AI is built, with the help of intriguing and exciting examples.
This book will make you an adaptive thinker and help you apply concepts to real-world scenarios. Using some of the most interesting AI examples, right from computer programs such as a simple chess engine to cognitive chatbots, you will learn how to tackle the machine you are competing with. You will study some of the most advanced machine learning models, understand how to apply AI to blockchain and Internet of Things (IoT), and develop emotional quotient in chatbots using neural networks such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).
This edition also has new examples for hybrid neural networks, combining reinforcement learning (RL) and deep learning (DL), chained algorithms, combining unsupervised learning with decision trees, random forests, combining DL and genetic algorithms, conversational user interfaces (CUI) for chatbots, neuromorphic computing, and quantum computing.
By the end of this book, you will understand the fundamentals of AI and have worked through a number of examples that will help you develop your AI solutions.
What you will learn
Apply k-nearest neighbors (KNN) to language translations and explore the opportunities in Google Translate
Understand chained algorithms combining unsupervised learning with decision trees
Solve the XOR problem with feedforward neural networks (FNN) and build its architecture to represent a data flow graph
Learn about meta learning models with hybrid neural networks
Create a chatbot and optimize its emotional intelligence deficiencies with tools such as Small Talk and data logging
Building conversational user interfaces (CUI) for chatbots
Writing genetic algorithms that optimize deep learning neural networks
Build quantum computing circuits
Who this book is for
Developers and those interested in AI, who want to understand the fundamentals of Artificial Intelligence and implement them practically. Prior experience with Python programming and statistical knowledge is essential to make the most out of this book.
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
Table of Contents - Getting Started with Next-Generation Artificial Intelligence through Reinforcement Learning
- Building a Reward Matrix – Designing Your Datasets
- Machine Intelligence – Evaluation Functions and Numerical Convergence
- Optimizing Your Solutions with K-Means Clustering
- How to Use Decision Trees to Enhance K-Means Clustering
- Innovating AI with Google Translate
- Optimizing Blockchains with Naive Bayes
- Solving the XOR Problem with a Feedforward Neural Network
- Abstract Image Classification with Convolutional Neural Networks (CNN)
- Conceptual Representation Learning
- Combining Reinforcement Learning and Deep Learning
- AI and the Internet of Things (IoT)
- Visualizing Networks with TensorFlow 2.x and TensorBoard
- Preparing the Input of Chatbots with Restricted Boltzmann Machines (RBMs) and Principal Component Analysis (PCA)
- Setting Up a Cognitive NLP UI/CUI Chatbot
- Improving the Emotional Intelligence Deficiencies of Chatbots
- Genetic Algorithms in Hybrid Neural Networks
- Neuromorphic Computing
- Quantum Computing
- Appendix - Answers to the Questions
Preface
This second edition of will take you through the main aspects of present-day artificial intelligence (AI) and beyond!
This book contains many revisions and additions to the key aspects of AI described in the first edition:
- The theory of machine learning and deep learning including hybrid and ensemble algorithms.
- Mathematical representations of the main AI algorithms including natural language explanations making them easier to understand.
- Real-life case studies taking the reader inside the heart of e-commerce: manufacturing, services, warehouses, and delivery.
- Introducing AI solutions that combine IoT, convolutional neural networks (CNN), and Markov decision process (MDP).
- Many open source Python programs with a special focus on the new features of TensorFlow 2.x, TensorBoard, and Keras. Many modules are used, such as scikit-learn, pandas, and more.
- Cloud platforms: Google Colaboratory with its free VM, Google Translate, Google Dialogflow, IBM Q for quantum computing, and more.
- Use of the power of restricted Boltzmann machines (RBM) and principal component analysis (PCA) to generate data to create a meaningful chatbot.
- Solutions to compensate for the emotional deficiencies of chatbots.
- Genetic algorithms, which run faster than classical algorithms in specific cases, and genetic algorithms used in a hybrid deep learning neural network.
- Neuromorphic computing, which reproduces our brain activity with models of selective spiking ensembles of neurons in models that reproduce our biological reactions.
- Quantum computing, which will take you deep into the tremendous calculation power of qubits and cognitive representation experiments.
This second edition of will take you to the cutting edge of AI and beyond with innovations that improve existing solutions. This book will make you a key asset not only as an AI specialist but a visionary. You will discover how to improve your AI skills as a consultant, developer, professor, a curious mind, or any person involved in artificial intelligence.
Who this book is for
This book contains a broad approach to AI, which is expanding to all areas of our lives.
The main machine learning and deep learning algorithms are addressed with real-life Python examples extracted from hundreds of AI projects and implementations.
Each AI implementation is illustrated by an open source program available on GitHub and cloud platforms such as Google Colaboratory.
is for developers who wish to build solid machine learning programs that will optimize production sites, services, IoT and more.
Project managers and consultants will learn how to build input datasets that will help the reader face the challenges of real-life AI.
Teachers and students will have an overview of the key aspects of AI, along with many educational examples.
What this book covers
, , covers reinforcement learning through the Bellman equation based on the MDP. A case study describes how to solve a delivery route problem with a human driver and a self-driving vehicle. This chapter shows how to build an MDP from scratch in Python.
, , demonstrates the architecture of neural networks starting with the McCulloch-Pitts neuron. The case study describes how to use a neural network to build the reward matrix used by the Bellman equation in a warehouse environment. The process will be developed in Python using logistic, softmax, and one-hot functions.
, , shows how machine evaluation capacities have exceeded human decision-making. The case study describes a chess position and how to apply the results of an AI program to decision-making priorities. An introduction to decision trees in Python shows how to manage decision-making processes.
, , covers a k-means clustering program with Lloyd's algorithm and how to apply it to the optimization of automatic guided vehicles. The k-means clustering program's model will be trained and saved.
, , begins with unsupervised learning with k-means clustering. The output of the k-means clustering algorithm will provide the labels for the supervised decision tree algorithm. Random forests will be introduced.
, , explains the difference between a revolutionary innovation and a disruptive innovation. Google Translate will be described and enhanced with an innovative k-nearest neighbors-based Python program.
, , is about mining blockchains and describes how blockchains function. We use naive Bayes to optimize the blocks of supply chain management (SCM) blockchains by predicting transactions to anticipate storage levels.
, , is about building a feedforward neural network (FNN) from scratch to solve the XOR linear separability problem. The business case describes how to group orders for a factory.
, , describes CNN in detail: kernels, shapes, activation functions, pooling, flattening, and dense layers. The case study illustrates the use of a CNN using a webcam on a conveyor belt in a food-processing company.
, , explains conceptual representation learning (CRL), an innovative way to solve production flows with a CNN transformed into a CRL metamodel (CRLMM). The case study shows how to use a CRLMM for transfer and domain learning, extending the model to other applications.
, , combines a CNN with an MDP to build a solution for automatic planning and scheduling with an optimizer with a rule-based system.
The solution is applied to apparel manufacturing showing how to apply AI to real-life systems.
, , explores a support vector machine (SVM) assembled with a CNN. The case study shows how self-driving cars can find an available parking space automatically.
, , extracts information of each layer of a CNN and displays the intermediate steps taken by the neural network. The output of each layer contains images of the transformations applied.
, , explains how to produce valuable information using an RBM and a PCA to transform raw data into chatbot-input data.
, , describes how to build a Google Dialogflow chatbot from scratch using the information provided by an RBM and a PCA algorithm. The chatbot will contain entities, intents, and meaningful responses.
, , explains the limits of a chatbot when dealing with human emotions. The Emotion options of Dialogflow will be activated along with Small Talk to make the chatbot friendlier.
, , enters our chromosomes, finds our genes, and helps you understand how our reproduction process works. From there, it is shown how to implement an evolutionary algorithm in Python, a genetic algorithm (GA). A hybrid neural network will show how to optimize a neural network with a GA.
, , describes what neuromorphic computing is and then explores Nengo, a unique neuromorphic framework with solid tutorials and documentation.
This neuromorphic overview will take you into the wonderful power of our brain structures to solve complex problems.
, , will show quantum computers are superior to classical computers, what a quantum bit is, how to use it, and how to build quantum circuits. An introduction to quantum gates and example programs will bring you into the futuristic world of quantum mechanics.
, , provides answers to the questions listed in the section in...
