Introduction

Artificial Intelligence (AI) has become an integral part of our daily lives, revolutionizing industries and transforming how we interact with technology. From voice assistants to recommendation systems and autonomous vehicles, AI is everywhere, driving innovation and solving complex problems. In this section, we introduce foundational concepts and mathematical preliminaries that form the backbone of modern AI systems. We will begin by exploring linear neural networks, one of the simplest yet most important building blocks of deep learning models, setting the stage for more advanced architectures and techniques in the field.

AI is Ubiquitous

You may find the applications of AI in every aspect of our lives these days.

AI Paradox

• Problems difficult for humans are easy for AI

• Problems easy for humans are difficult for AI

What tasks require Intelligence?

Knowledge-Based AI

• Disadvantage: Unwiedy Process
  • Time of human expert
  • People struggle to formalize rules with enough complexity to describe the world

The Machine Learning Approach

• Allow computers to learn from experience
• Determine what features to use
• Learn to map the features to output

Machine Learning Pipeline

Supervised Learning vs Unsupervised Learning

Supervised Learning

• Data-set: collection of labeled examples \(\left(\left\{\left(\mathbf{x}_{i}, y_{i}\right)\right\}_{i=1}^{N}\right)\)