

A glimpse inside

Negnevitsky’s book stands out for its balance between foundational AI theory and practical implementation. Rather than focusing solely on abstract concepts, the author connects ideas like search algorithms, knowledge representation, and learning with real-world problems and coding examples. This approach helps readers not only grasp what AI is, but also how to apply it in diverse domains, making the book especially valuable for students and professionals who want to move from understanding to doing.
A major focus of the book is on expert systems—AI programs that simulate the decision-making ability of human experts. Negnevitsky explains how knowledge can be represented, acquired, and reasoned with, emphasizing rule-based systems and inference engines. The book explores the challenges of capturing human expertise and the practicalities of building systems that can explain their reasoning, which remains highly relevant in today’s explainable AI movement.
- 1Bridging Theory and Practice
- 2Expert Systems and Knowledge Engineering
- 3Soft Computing: Fuzzy Logic and Neural Networks
- 4Evolutionary Computation and Learning
- 5Ethics, Limitations, and the Future of AI