Foundations of Artificial Intelligence: Agent Systems, Neural Networks, and Deep Learning for Beginners

Foundations of Artificial Intelligence: Agent Systems, Neural Networks, and Deep Learning for Beginners is your friendly doorway into AI. This beginner-friendly video course covers agent systems, neural networks, deep learning, machine learning, and computer vision, with a clear historical perspective to show how AI arrived here—and why it still matters.

Key Features & Design

• Beginner-friendly video course covering agent systems, neural networks, deep learning, machine learning, and computer vision.
• Historical Perspective helps you understand AI's evolution—from the earliest problem solvers to modern intelligent systems.
• Structured topics aligned with the course outline: Introduction and Historical Background of AI; The General Problem Solver; Expert Systems; Neural Networks; Machine Learning: Deep Learning & Computer Vision.
• No prior knowledge required (Requirements: No prior knowledge of AI required).
• Core concepts made practical including forward and backward chaining, probabilities in expert systems, neural signals, perceptron, layers of deep learning networks, and Convolutional Neural Networks (CNNs).
• Real-world applications with case studies and examples in speech and image recognition, plus a case study: Optimizing potato harvesting.
• What you’ll learn— a clear, actionable outcome set: the structure and design of modern AI systems; differences between strong and weak AI; fundamentals of deep learning and machine learning; problem structures and solving techniques; machine vision and computer vision basics.

What You’ll Learn

• The structure and design of modern AI systems
• Differences between strong and weak AI
• Fundamentals of deep learning and machine learning
• Problem structures and solving techniques
• Forward and backward chaining in AI logic
• Probabilities in expert systems
• The function of human neurons and their digital equivalents
• Layers of deep learning networks
• Machine vision and computer vision basics

Course Topics & Lessons

• I. Introduction and Historical Background — Philosophical perspective: What is AI? Strong AI vs. Weak AI; The Turing Test; The origins of AI; The era of high expectations and its reality check; How machines learn; Distributed systems in AI; Deep Learning, Machine Learning, and Natural Language Processing.
• II. The General Problem Solver — Logical Theorist: The first proof program; Human problem-solving examples (Simon); Analyzing the structure of a problem; foundational AI techniques shaping early optimism.
• III. Expert Systems — Factual and heuristic knowledge; Frames, slots, and fillers; Forward and backward chaining; The MYCIN program; Probabilities in expert systems; Real-world application: Calculating the probability of hairline cracks.
• IV. Neural Networks — Understanding the human neuron; Neuron signal processing; The perceptron; early approaches and the missing links that led to breakthroughs in neural network development.
• V. Machine Learning: Deep Learning & Computer Vision — Case study: Optimizing potato harvesting; The birth of deep learning; Layers in deep learning networks; Machine vision and computer vision; Convolutional Neural Networks (CNNs); multi-agent systems and real-world AI applications such as speech and image recognition.