Nexus Learn

CS-511 Artificial Intelligence

BSCS30 lectures · 25 practicals

What you will learn

  1. CLO1. Explain the applications of AI and agent-based approach to AI.
  2. CLO2. Demonstrate first-order predicate calculus, logical reasoning and problem-solving using Prolog language.
  3. CLO3. Apply various techniques and algorithms of AI used in general problem solving, optimization problems, constraint satisfaction problems, and game programming.

Lectures

LectureNotesSlides
L01 · Introduction to AI: Intelligence and the Four Approaches Read notes View slides
L02 · History, Applications, Types and Ethics of AI Read notes View slides
L03 · Turing Machine and the Turing Test Read notes View slides
L04 · Intelligent Agents: PEAS, Environments and Agent Types Read notes View slides
L05 · Knowledge Representation Read notes View slides
L06 · Propositional Logic Read notes View slides
L07 · Predicate (First-Order) Logic Read notes View slides
L08 · Inference and Resolution for Problem Solving Read notes View slides
L09 · Logic Programming with Prolog Read notes View slides
L10 · Problem Solving as Search and Properties of Search Methods Read notes View slides
L11 · Breadth-First Search Read notes View slides
L12 · Depth-First Search and Iterative Deepening Read notes View slides
L13 · Heuristics, Best-First and Greedy Search Read notes View slides
L14 · A* Search and Designing Heuristics Read notes View slides
L15 · Hill Climbing and Beam Search Read notes View slides
L16 · Simulated Annealing and Parallel Search Read notes View slides
L17 · Game Playing: Minimax Read notes View slides
L18 · Alpha-Beta Pruning and Constraint Satisfaction Problems Read notes View slides
L19 · Rules and Expert Systems Read notes View slides
L20 · Probabilistic Reasoning and Bayes' Rule Read notes View slides
L21 · Bayesian Belief Networks Read notes View slides
L22 · Fuzzy Sets and Fuzzy Logic Read notes View slides
L23 · Fuzzy Inference: Mamdani and Sugeno Read notes View slides
L24 · Machine Learning: Supervised, Unsupervised and Reinforcement Read notes View slides
L25 · Decision Trees Read notes View slides
L26 · Neural Networks and the Perceptron Read notes View slides
L27 · Multilayer Networks and Back-propagation Read notes View slides
L28 · Recurrent Neural Networks Read notes View slides
L29 · Genetic Algorithms Read notes View slides
L30 · Natural Language Processing Basics Read notes View slides

Lab practicals

PracticalHandout
P01 Practical 1: Python Toolkit for AI: NumPy, pandas and Matplotlib
P02 Practical 2: Building a Perceptron from Scratch
P03 Practical 3: Designing and Training a Multilayer Network
P04A Practical 4A: Function Approximation I: Fitting a Curve with MLPRegressor
P04B Practical 4B: Function Approximation II: Predicting Electricity Units from Real Data
P05A Practical 5A: Pattern Recognition I: Reading Handwritten Digits
P05B Practical 5B: Pattern Recognition II: Confusion Matrix, Errors and Noisy Images
P06A Practical 6A: Clustering I: Grouping Households by Electricity Use
P06B Practical 6B: Time Series: Forecasting Tomorrow's Electricity Use
P07A Practical 7A: Fuzzy Sets I: Membership Functions
P07B Practical 7B: Fuzzy Sets II: Operations, Hedges and Defuzzification
P08A Practical 8A: Building a Fuzzy System I: Inputs, Rules and Simulation
P08B Practical 8B: Building a Fuzzy System II: Testing, Control Surface and Tuning
P09A Practical 9A: Mamdani Inference by Hand
P09B Practical 9B: Sugeno Inference and Comparison with Mamdani
P10A Practical 10A: A Fuzzy Controller on the Command Line
P10B Practical 10B: Custom Functions and a Rule File
P11A Practical 11A: ANFIS I: Learning the Rule Formulas by Least Squares
P11B Practical 11B: ANFIS II: Tuning the Membership Functions by Gradient Descent
P12A Practical 12A: Fuzzy C-Means I: Soft Groups of Households
P12B Practical 12B: Fuzzy C-Means II: Choosing c and m, and Grouping Cotton Fields
P13A Practical 13A: Deploying a Fuzzy System I: A Model File and a General Engine
P13B Practical 13B: Deploying a Fuzzy System II: Testing, Speeding Up and Running the Controller
P14A Practical 14A: Fuzzy Edge Detection I: Building the Detector
P14B Practical 14B: Fuzzy Edge Detection II: Tuning, Noise and a Leaf Image