CS370 - Introduction to Artificial Intelligence - Fall'2021

• This course introduces concepts, approaches and techniques of artificial intelligence, and focuses on materials that are fundamental and have a broad scope of applications.  Topics include Planning, such as Problem Solving, Searching, Knowledge and Reasoning, Logical Agents, First-Order Logic and Inference; Perceiving; Learning; Communicating; and Acting.

• Prerequisites: CS 114 and (Math 226 or CS 241)

Specific Goals for the Course

• Students are prepared to work on AI related projects, such as problem solving, knowledge representation and reasoning, perception, learning, and search.
• Students learn the introductory concepts and methodologies for artificial intelligence.
• Students learn the fundamental materials with a broad scope of applications.

Measurable Learning Outcomes

• Students learn the concepts, approaches and techniques of artificial intelligence.
• Students learn the materials that are fundamental and have a broad scope of applications in artificial intelligence, such as Problem Solving, Search, Knowledge and Reasoning, Logical Agents, First-Order Logic and Inference, Perception, Pictorial Knowledge Representation, and Search in Frequency and Spatial Domains.

• S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th edition, Prentice Hall, 2020.
  
• Selected papers and handouts.

1. Introduction
• AI Fundamentals: AI, Cognitive Science, Turing Test
• Planning (Problem Solving, Searching, Knowledge and Reasoning), Perceiving, Learning, Acting
  
• Programming Languages: Lisp, Prolog, C/C++, Java, Matlab
  
• Related Fields: Machine Learning, Neural Networks, Evolutionary Computation, Computer Vision
2. Planning: Problem Solving by Searching
• Intelligent Agent: Sensors, Actuators, Agent Program
• Blind Search Strategies vs. Informed Search Strategies
  
• Greedy Best-first Search
  
• A* Search (completeness, optimality, complexity)
3. Planning: Knowledge and Reasoning - Propositional Logic and Logical Agents
• Knowledge Base, Models, and Knowledge-Based Agents; Syntax and Semantics
• Logical Reasoning: Entailment and Inference (soundness, completeness)
  
• Propositional Theorem Proving: Validity, Satisfiability, Reduction to Absurd
  
• MP Inference Rule, Resolution Inference Rule, Horn Form, CNF
4. Planning: Knowledge and Reasoning - First-Order Logic; Inference in First-Order Logic
• First-Order Logic: Syntax and Semantics (predicates, variables, quantifiers)
  
• First-Order Logic Knowledge Representation Language, Model, Interpretation
• Universal Instantiation, Existential Instantiation; Substitution and Unification
• Generalized MP Rule, Soundness of GMP; Resolution Inference Rule, CNF
5. Perceiving - Pictorial Knowledge Representation
• Digital Image Fundamentals
• Image Formation; Digital Image Formats/Protocols
  
• Digital Video Fundamentals
  
6. Perceiving - Image Search
   
• FT/FFT; Lowpass and Highpass Filtering
• Convolution, Correlation, and Autocorrelation Theorems
• Geometric Feature Representation: Edge Detection (Canny, Zero-crossing, LOG, Prewitt, etc.); Line and Curve Detection (Hough Transform)
7. Perceiving - Video Analytics
• Tesla's Full Self-Driving, Google's Waymo (robotaxi in SF), Uber -> Aurora
  
• Mixture of Gaussian Background Modelling
• Global Foreground Modelling
  
8. Learning
   
• Inductive Learning
• Decision Tree Learning
• Neural Networks Learning
9. Learning
   
• Deep Learning: DNN, CNN, Faster R-CNN, YOLO
• Statistical Learning Theory
• Structural Risk Minimization
10. Learning (optional)
• Reinforcement Learning
• Q-Learning, SARSA Learning
• Evolution, Genetic Algorithms, Evolutionary Pursuit
  
11. Robotics (optional)
• Sensors and Vision
• Path Planning
• Moving and Control
  

Homework 20%

Midterm exam 20%

Project and presentation (topics are related to our course Contents) 20%

Class attendance and participation 10%

Final exam 30%

• Berkeley AI Course Materials
• Prolog:
  
• J.R. Fisher, The Prolog Tutorial
  
• Lisp:
  
• Paul Graham, ANSI Common Lisp, Prentice Hall, 1995.
• MATLAB
• Matlab Primer (Third Edition, By Kermit Sigmon)