Methods of Artificial Intelligence

Abstract

Arti cial Intelligence (AI) plays a strategic role today in many elds of engineering and applied sciences. Whether in process optimization, autonomous decision-making, or the modeling of complex systems, AI methods o er powerful and adaptive tools. For future engineers, mastering these techniques has become essential. This coursebook is intended for 4th-year students in Industrial Engineering at the Higher School of Applied Sciences. It has been designed as a pedagogical and structured learning support, o ering a gradual understanding of the main arti cial intelligence methods currently used, both in the industrial sector and across other technical disciplines. The document is organized into ve chapters: Chapter 1 Introduction to Arti cial Intelligence: This introductory chapter presents the foundations, history, and application domains of AI, laying out the essential theoretical background. Chapter 2 Machine Learning and Neural Networks: This chapter covers fundamental machine learning algorithms such as the perceptron, logistic regression, gradient descent, and the backpropagation algorithm used in neural networks. It includes solved exercises to help reinforce the key concepts. Chapter 3 Fuzzy Logic and Fuzzy Inference Systems: This chapter introduces the basics of fuzzy logic, fuzzy sets, and the construction of fuzzy inference systems. It also contains exercises with solutions to illustrate the modeling process in uncertain or imprecise environments. Chapter 4 Intelligent Agents and Multi-Agent Systems: This chapter explores the concept of autonomous agents, the characteristics of intelligent agents, and the principles behind multi-agent systems, which are increasingly applied in distributed intelligent environments. Chapter 5 Deep Learning. Convolutional Neural Networks:This chapter introduces Convolutional Neural Networks (CNNs), highlighting their core operations and architectures for feature extraction and learning. This chapter provides students with a solid introduction to deep learning, which they will need for their nal year projects in the coming academic year. This course material does not aim to be exhaustive but provides a solid foundation to address real-world AI problems. It can also serve as a reference for practical assignments, projects, or further studies in the field.