Artificial Intelligence

Semester V · BCA 302 · 3 credits

6 units · 45 teaching hours · about 4 h of reading

0 / 6 chapters done

Introduction to Artificial Intelligence and Intelligent Agents 6 hrs · 36 min read · 13 figures
The syllabus asks for
- What is artificial intelligence?
- Foundations of AI
- Applications of AI
- Intelligent agents
- Seeing the ideas: people, machines, agents and environments
Key points
- AI is the study of agents that act rationally. Four definitions (thinking or acting, humanly or rationally) co-exist; the rational-agent view is the most used.
- Weak AI solves specific tasks and is the only AI that exists; strong AI is a general machine mind and remains a hypothesis.
- AI draws on philosophy, mathematics, economics, neuroscience, psychology and computing; its history alternates enthusiasm and AI winters.
- An agent maps percepts to actions; PEAS specifies its task; agents range from simple reflex to learning agents; the environment type determines how hard the task is.
Read the chapter
Problem Solving Methods 9 hrs · 49 min read · 15 figures
The syllabus asks for
- Formulating a search problem
- The example graph
- Uninformed (blind) search
- Informed (heuristic) search
- Local search and optimisation
- Constraint satisfaction problems
- Adversarial search and games
- Seeing the ideas: puzzles, people, games and traced searches
Key points
- A search problem is defined by states, actions, a goal test and path costs; the algorithm determines which frontier node is expanded next.
- BFS, UCS and IDDFS are complete; BFS and IDDFS are optimal for equal step costs and UCS for any positive costs; DFS saves memory but is neither.
- A* with an admissible (tree) or consistent (graph) heuristic is optimal and more efficient than blind search; a dominant heuristic expands fewer nodes.
- Local search keeps one state and suits optimisation; simulated annealing escapes local maxima by occasionally accepting worse moves.
- CSPs are solved by backtracking with MRV and forward checking. Games are searched by minimax; alpha–beta gives the same answer with far fewer nodes.
Read the chapter
Knowledge Representation and Reasoning 15 hrs · 53 min read · 16 figures
The syllabus asks for
- Knowledge and its importance
- Knowledge representation techniques
- Propositional logic
- First-order logic
- Reasoning under uncertainty
- Seeing the ideas: logicians, rules, networks and probabilities
Key points
- Knowledge can be held as rules, semantic networks, frames or logic; a good scheme is adequate, inferentially efficient and easy to extend.
- Propositional logic gives sound, complete reasoning by truth table or resolution; Horn clauses allow efficient forward and backward chaining.
- First-order logic adds objects, relations and quantifiers; unification and resolution (with Skolemisation) prove theorems mechanically; Prolog implements the idea.
- Under uncertainty, probability and Bayes' rule update beliefs; Bayesian networks factor the joint distribution into small CPTs and answer queries by enumeration or sampling.
Read the chapter
Learning 4 hrs · 41 min read · 15 figures
The syllabus asks for
- Concepts of machine learning
- Forms of learning in the syllabus
- Decision trees
- Naive Bayes
- k-nearest neighbours
- Clustering (unsupervised)
- Learning by evolution: genetic algorithms
- Seeing the ideas: pioneers, flowers, evolution and the algorithms
Key points
- Machine learning improves a task from data: supervised (labelled), unsupervised (structure), reinforcement (rewards); evaluate on unseen data to detect overfitting.
- Rote learning memorises, analogy reuses similar cases, induction generalises, explanation-based learning generalises from one explained example.
- Decision trees split on the attribute with the highest information gain; naive Bayes multiplies class-conditional probabilities; k-NN votes among nearest neighbours.
- Genetic algorithms evolve a population with selection, crossover and mutation.
Read the chapter
Neural Networks and Natural Language Processing 7 hrs · 52 min read · 17 figures
The syllabus asks for
- The artificial neuron
- The perceptron
- Multi-layer feed-forward networks
- Gradient descent and back-propagation
- Feedback networks: Hopfield network and Boltzmann machine
- Natural language processing
- Seeing the ideas: neurons, perceptrons, networks and language
Key points
- An artificial neuron sums weighted inputs and applies an activation; a perceptron learns linearly separable functions (AND, OR) but not XOR.
- Hidden layers and back-propagation (the chain rule applied layer by layer) let networks learn non-linear functions; training is gradient descent on a loss.
- Hopfield networks store patterns as energy minima and recall them from noisy input while the load stays below about 0.14 N patterns; Boltzmann machines add stochastic units.
- NLP converts text to meaning by lexical, syntactic, semantic, discourse and pragmatic analysis; n-gram, edit-distance and TF-IDF methods are the classical statistical tools.
Read the chapter
Expert Systems and Machine Vision 4 hrs · 38 min read · 18 figures
The syllabus asks for
- Expert systems
- Machine vision
- Seeing the ideas: expert systems and machine vision
Key points
- An expert system captures a specialist's rules in a knowledge base used by a general inference engine, explains its reasoning and handles uncertainty with certainty factors; it is brittle outside its domain and costly to maintain.
- Development goes from identification through formalisation to testing and maintenance, with the knowledge engineer bridging expert and program.
- Machine vision turns pixels into decisions by acquisition, preprocessing, segmentation, feature extraction and recognition; edge detection is a convolution with kernels such as Sobel's.
- Both technologies serve real applications in industry, health and agriculture, with privacy, bias and accountability concerns.
Read the chapter