Artificial Intelligence

6 subjects · 15 chapters · 60 topics

1. 01

   Foundations of AI

   1.1 What AI is

   • History and the AI winters
   • Narrow, general and applied AI
   • Where AI fits beside software
   • Ethics and limits from day one

   1.2 Mathematics you actually need

   • Vectors, matrices and dot products
   • Probability and Bayes' rule
   • Derivatives and gradients
   • Reading a loss curve

   1.3 Python for AI

   • NumPy arrays and broadcasting
   • Pandas for tabular data
   • Matplotlib for quick plots
   • Notebooks and reproducible runs
2. 02

   Search and Problem Solving

   2.1 Uninformed search

   • State spaces and goal tests
   • Breadth-first and depth-first
   • Uniform cost search
   • Complexity and memory limits

   2.2 Informed search

   • Heuristics and admissibility
   • A* search
   • Greedy best-first
   • Local search and hill climbing

   2.3 Games and adversarial search

   • Minimax
   • Alpha-beta pruning
   • Evaluation functions
   • Monte Carlo tree search
3. 03

   Knowledge and Reasoning

   3.1 Logic

   • Propositional logic
   • First-order logic
   • Inference and resolution
   • Forward and backward chaining

   3.2 Uncertainty

   • Bayesian networks
   • Conditional independence
   • Inference by enumeration
   • Markov decision processes
4. 04

   Learning from Data

   4.1 Supervised learning

   • Regression and classification
   • Decision trees and random forests
   • Support vector machines
   • Evaluation metrics

   4.2 Unsupervised learning

   • K-means and hierarchical clustering
   • Dimensionality reduction with PCA
   • Anomaly detection
   • Choosing the number of clusters

   4.3 Neural networks

   • Perceptrons and layers
   • Backpropagation
   • Convolutional networks for images
   • Recurrent networks and sequences
5. 05

   Perception

   5.1 Computer vision

   • Image representation and filters
   • Object detection basics
   • Image classification with transfer learning
   • Common vision pitfalls

   5.2 Natural language

   • Text preprocessing and tokenisation
   • Word embeddings
   • Sentiment and classification
   • An introduction to transformers
6. 06

   Responsible and Applied AI

   6.1 Fairness and safety

   • Bias in data and in models
   • Explainability techniques
   • Privacy and consent
   • Regulation and standards

   6.2 Putting AI to work

   • Framing a business problem as an AI problem
   • Data collection and labelling
   • Deployment and monitoring
   • A capstone project, end to end