AI Fundamentals

Introduction to Artificial Intelligence

• What is Artificial Intelligence and why it matters

• AI goals and the concept of rational agents 

• Narrow AI vs General AI vs Superintelligence

• AI vs Machine Learning vs Deep Learning

• Career opportunities in AI

• Assignment: Research AI applications in various industries

History and Evolution of AI

• Historical evolution of AI from early rule-based systems to modern AI 

• Key milestones in AI development

• AI winters and breakthroughs

• Contributions of Alan Turing, John McCarthy, and other pioneers

• Assignment: Create a timeline of AI history

Philosophy and Foundations of AI

• Philosophical foundations of AI

• The Turing Test and its implications

• The Chinese Room argument

• Can machines think? Classical debates

• Assignment: Write a reflection paper on AI philosophy

Applications of Artificial Intelligence

• Common AI application domains 

• AI in healthcare, finance, education, and retail

• Computer vision, NLP, and recommendation systems 

• Generative AI and creative applications

• Assignment: Analyze an AI application case study

 The AI Development Lifecycle

• From problem identification to deployment

• Data collection and preprocessing

• Model selection and training

• Evaluation and iteration

• Assignment: Map the AI lifecycle for a use case

Intelligent Agents

• What are intelligent agents and their role in AI 

• Agent architectures and environments

• Rationality and performance measures

• Types of agents (simple reflex, model-based, goal-based, utility-based)

• Assignment: Design a simple intelligent agent

Agent Environments and Problem Formulation

• Environment types (observable vs unobservable, deterministic vs stochastic)

• Problem formulation for AI solutions 

• Formalizing problems as search spaces

• Assignment: Formulate a real-world problem

Agent Types and Applications

• Software agents vs physical agents

• Autonomous systems and robotics

• Multi-agent systems

• Assignment: Compare different agent types

 Introduction to Search Problems

• Why search is fundamental to AI

• Problem formulation as search 

• Search spaces and state spaces

• Assignment: Identify search problems

Uninformed Search

• Breadth-First Search (BFS) 

• Depth-First Search (DFS)

• Uniform-Cost Search 

• Assignment: Implement BFS and DFS

Informed Search and Heuristics

• Heuristic search techniques

• A* Search Algorithm 

• Greedy Best-First Search

• Assignment: Implement A* search

Adversarial Search and Game Playing

• Minimax algorithm 

• Alpha-beta pruning

• Game playing AI (Chess, Go)

• Assignment: Implement a game AI

• Function overloading 

• Recursion in C++ 

• Default parameters 

• Function scope and namespaces

• Assignment: Implement recursive functions

Namespaces

• Creating namespaces

• Using namespaces 

• Argument-dependent lookup (ADL)

• Organizing code with namespaces

• Assignment: Organize code with namespaces

 Introduction to Pointers

• Understanding pointers and addresses 

• Declaring and using pointers

• Pointers vs references 

• Assignment: Work with pointers

Planning and Decision Making

• Classical planning representations

• Planning graphs and Graphplan 

• Decision-making under uncertainty 

• Assignment: Create a planning solution

 Introduction to Machine Learning

• What is Machine Learning and why it matters

• Types of learning: supervised, unsupervised, reinforcement 

• The machine learning workflow

• Assignment: Research ML applications

Supervised Learning - Part 1

• Regression and classification 

• Linear regression and logistic regression 

• Naive Bayes classifier 

• Assignment: Implement a linear regression model

Supervised Learning - Part 2

• Support Vector Machines (SVM) 

• Decision trees and random forests

• K-Nearest Neighbors (KNN)

• Assignment: Build a classification model

Unsupervised Learning

• Clustering algorithms: K-Means 

• Dimensionality reduction

• PCA and t-SNE

• Assignment: Implement clustering

Reinforcement Learning

• Introduction to reinforcement learning 

• Rewards and state transitions 

• The Bellman equation 

• Q-learning fundamentals 

• Assignment: Train a simple RL agent

Evaluation and Model Selection

• Model evaluation metrics

• Overfitting and underfitting

• Cross-validation

• Assignment: Evaluate and select a model

 Introduction to Neural Networks

• The Perceptron: building block of neural networks 

• Activation functions and layers

• How neural networks learn

• Assignment: Build a perceptron

Neural Networks in Depth

• Feedforward networks

• Backpropagation and gradient descent 

• Training neural networks

• Assignment: Train a simple neural network

Convolutional Neural Networks (CNNs)

• Convolutional layers and filters 

• Pooling layers 

• Classical CNN architectures 

• CNN applications in computer vision

• Assignment: Build a CNN for image classification

Recurrent Neural Networks (RNNs) and LSTMs

• Sequence data and RNNs 

• Long Short-Term Memory (LSTM) 

• Applications in NLP and time series

• Assignment: Implement an RNN

Transformer Architecture

• The Transformer architecture 

• Self-attention mechanism 

• Transfer learning and fine-tuning 

• Assignment: Explore a transformer model

Introduction to Generative AI

• What is generative AI and why it matters 

• Overview of foundational models 

• Generative AI use cases and applications

• Assignment: Explore generative AI tools

Large Language Models (LLMs)

• LLMs: capabilities and limitations 

• Pre-training and fine-tuning 

• Prompt engineering basics 

• Assignment: Interact with an LLM

Advanced Prompt Engineering

• Prompt engineering strategies 

• Chain-of-thought prompting 

• Retrieval-Augmented Generation (RAG) 

• Assignment: Master prompt engineering

AI Productivity Tools and Assistants

• AI assistants and copilots 

• Embedded AI tools in productivity applications

• Automated content creation with AI

• Assignment: Use AI tools for productivity

 Image Generation and Diffusion Models

• Diffusion models for image generation 

• Applications in creative design

• Assignment: Generate images with AI

Natural Language Processing (NLP)

• What is NLP and why it matters 

• NLP fundamentals: tokenization, embeddings 

• NLP applications: chatbots, sentiment analysis, translation 

• Assignment: Build an NLP application

Computer Vision

• What is Computer Vision 

• Image classification and object detection 

• Practical applications across industries 

• Assignment: Build a computer vision application

Responsible AI and Ethics

• Risks associated with AI: bias, hallucination, explainability 

• Fairness, transparency, and accountability 

• Data privacy and security concerns 

• AI governance and regulatory compliance 

• Assignment: Analyze an AI ethics case study

 Final Assessment and Capstone Project

• Comprehensive revision of all modules

• Capstone project: Build a complete AI solution

• Problem identification, data preparation, model selection, and evaluation

• Final presentation and feedback

• Certification