Recognizing the vast potential in analyzing big data through machine learning (ML) and artificial intelligence (AI) technologies, companies are acknowledging these technologies as essential for maintaining relevance. A prevailing trend is emerging towards the adoption of distributed open-source computing for storing big data assets and performing advanced ML/AI analytics to predict future trends and risks for businesses. This book offers readers an overview of the essentials of big data and ML/AI, while acknowledging that the field is extensive and evolving. Rather than focusing on theory, the book shares real-life experiences building AI and big data analytics systems of value to practitioners.
• Features practical case studies on building big data and AI models for large scale enterprise solutions.
• Discusses the use of design patterns for architecting AI that are safe, secure, and testable.
• Covers an array of concepts including deep big data analytics, natural language processing, transformer architecture and evolution of ChatGPT, swarm intelligence, and genetic programming.
Informed by the authors' many years of teaching ML, AI, and working on predictive data analytics/AI projects, this book is suitable for use by graduates, professionals, and researchers within the field of data science and engineers and scientists interested in learning more about these essential technologies.
This book covers the essentials of big data and ML/AI to predict trends and risks for business while acknowledging that the field is extensive and evolving. Rather than focusing on theory, it shares real-life experiences building AI and big data analytics systems of value to practitioners.
0. Front Matter. Part I. Foundations & Platforms, Automation & Data
Quality at Scale.
1. Fundamental concepts in AI.
2. Big Data and Artificial
Intelligence Systems.
3. Architecting Big Data pipelines.
4. Big Data
Frameworks and Data Cleaning Strategies.
5. Building Automated Pipelines for
Data Cleaning. Part II. Optimization & Search.
6. Swarm Intelligence.
7.
Genetic Programming. Part III. Learning Systems.
8. Foundations on Machine
Learning and Artificial Learning.
9. Reinforcement Learning.
10. Deep
Reinforcement Learning.
11. Natural Language Modelling.
12. Transformer
Architecture and Evolution of LLMs. Part IV. Systems in the Real World.
13.
Architecting Distributed AI Systems using Design Patterns.
14. Securing AI
Systems.
15. AI System Safety in Practice.
16. Testing Strategies for AI
Applications. End Matter. Answer Keys for
Chapter Questions.
Satish Mahadevan Srinivasan is an Associate Professor of Information Science at Pennsylvania State University, Great Valley. He teaches courses related to database design, data mining, data collection and cleaning, data visualization, computer, network and web securities, network analytics and business process management.
Raghvinder S. Sangwan is a Professor of Software Engineering at Pennsylvania State University with expertise in analysis, design, and development of largescale softwareintensive systems, and the use of AI engineering to design and develop intelligent systems that are safe, secure, and trustworthy.
