CSB 210: AI [2024]

Artificial Intelligence

Students will learn about a variety of issues in the development of AI solutions to the real world problems, particularly knowledge representation, search strategies and machine learning along with applications.

Subject aims to give understanding of the main abstractions and reasoning techniques used in artificial intelligence including representation and inference in first-order logic; modern deterministic, decision-theoretic, planning techniques, and basic machine learning methods.

Announcements

Classes started from 01 Jan 2024. 

Schedule: Mon-Friday

Evaluation : Project , Quiz,  Assignment, Mid Term, End Term

Teaching Assistants: 

  • Prachee Patel  <ta2_2024_coed@coed.svnit.ac.in>

Lecture Notes

All the lecture notes and handouts will be updated soon as per class and schedule.

pwd : cs210

Content[ links] Reference
[L1 – L3] Module 1 : Introduction to AI 
2,3,4 Jan PART 1.1 : What is Artificial Intelligence
PART 1.2 : History of AI
PART 1.3 : Possible Approaches in AI
PART 1.4 : Application Domains and Modern AI
PART 1.5 : Areas Contributing to AI
PART 1.6 : Current AI systems		[Slides]B1 : Ch 1
03 JanHW 1 :  AI_HW- ASSIGNMENT- 1   Due : 24-Jan 
AI PROJECT :  LINK  
Step 1: Fill the details : 28 Jan 
Step 2:  Discussion : 5,6 Feb  
Step 3:  Final Presentation:  24 March onwards  
[L4 – L6] Module 2: Automated Problem Solving Agent
5 JanPART 2.1: Intelligent Agent & Environment [Slides]B1 : Ch 2
10 JanPART 2.2: Complex Problems and AI [Slides] B2: Ch 2
11 JanPART 2.3: Problem Representation in AI[Slides]B2: Ch 2
[ L7 – L18]Module 3: Search Strategies
16,17 JanPART 3.1 : Search introduction
PART 3.2 : Uninformed Search		[Slides]B1: Ch 3
18, 23 JanPART 3.3 : Informed (Heuristic) Search[Slides]B1: Ch 3
24,25,30 JanPART 3.4 : Beyond Classical Search
 •   Local Search
 •   Genetic Algorithm
 •   Problem Reduction		[Slides]B1: Ch4
31 Jan
1,6 Feb		PART 3.5 : Adversarial Search 
Quiz 1		[Slides]B1: Ch6
7,8 FebPART 3.6 : Constraint Satisfaction Problems[Slides]B1: Ch5
[L19 – L22]Module 4: Logic and Deduction 
13,14 Feb–  PART 4.1: Logical Agents
–  PART 4.2: Propositional logic and Predicate Logic		[Slides]B1:Ch7,8
14 Feb Expert Talk :
from AI to AGI : Navigating the transformative landscape of generative AI in the era of large language models
by Prof. Swagatam Das
15,20 Feb–  PART 4.3: Forward & Backward Chaining
–  PART 4.4 : Inferencing By Resolution Refutation
[Slides] B1:Ch9
[L23 – 26]Module 5: Planning in AI
21,22 Feb
5,6 Mar		–  PART 5.1 : Automated Planning,
–  PART 5.2 : Robot introduction and types ,
–  PART 5.3 : Steps in Robot Motion Planning,
    •   Graph-based Planning (Grassfire , Dijkstra & A* Algorithm)
–  PART 5.4 : Graph Construction &path planning in C-Space
–  PART 5.5 : Intruder Finding Problem,
    •   Probabilistic roadmaps(PRM)
    •   Rapidly Exploring Random Trees (RRT)		[Slides]B1:Ch11,25
MID TERM
[ L27 – L30] Module 6: Reasoning Under Uncertainty 
7,12,12 Mar–  PART 6.1 : Quantifying Uncertainty
 •  Basic of Probability
–  PART 6.2 : Probabilistic Reasoning
 •  Bayes Net
 •  Bayesian Network		[Slides]B1: Ch12
13 Mar–  PART 6.3 : Fuzzy Logic[Slides]
13,14,18 Mar  PART 6.4 : Decisions Theory
 •  Utility Function
 •  Decision Network
 •  Markov Decision Process		[Slides]B1: Ch 16
[ L31- L32]Module 7: Reinforcement Learning
19,19 Mar–  PART 7.1 : Learning Agent
–  PART 7.2 : Introduction to Machine Learning
–  PART 7.3 : Types of Machine Learning
–  PART 7.4 : Learning from experience :
 •  Reinforcement Learning
 •  Background
– PART 7.5 : Model based and Model free learning
– PART 7.6 : TD and Q Learning
– PART 7.7 : RL Applications		[Slides]B1: Ch 22
[L33 – L35]Module 8: Learning from Example
20,21,21 Mar–  PART 8.1 : Supervised learning : Introduction
–  PART 8.2 : Introduction to Perceptrons, Neural Network and Deep Learning		[Slides]
AI PROJECT :  LINK  
Step 1: Fill the details : 28 Jan 
Step 2:  Discussion : 5,6 Feb  
Step 3:  Final Presentation:  24 March onwards  
[L36 – L40]Module 9: AI Applications and Ethics
26,26 Mar–  PART 9.1 : Computer Vision and Robotics
–  PART 9.2 : Natural language understanding		[Slides]
27 Mar–  PART 9.3 : AI in Healthcare
–  PART 9.4 : Ethics of AI		[Slides]
28 MarDiscussion session
Where on Earth is AI Headed?
Speakers: Tom M. Mitchell		Video
3,4,5,8,
9,10 Apr		Project Presentation
9_2_ai_ethicsDownload

*This is a tentative list of topics that will be covered during the semester. The topics and schedule can change according to the need at the discretion of the instructor.

LAB

DateContent / LAB Assignment[ links ] 
1 JanLAB 1: AI and Python
–  Introduction to Python [Practice_Book ]
–  Introduction to Google CoLab [ Slides ]
–  Python Tutorial (with Jupyter and Colab) [ Slides ]		LAB_1
8JanLAB 2 : INTELLIGENT AGENT & PROBLEM FORMULATIONLAB_2
15JanLAB 3: AI Simulation Tool and Configuration Spaces
– Explore Robotic Operating System (ROS) [ROS Tutorials]
– Explore Gazebo [ Tutorial link ]
– Installation Help Filex

Online editor : https://app.theconstructsim.com/

Help file for TURTLESIM CONTROL		LAB_3

22,29
Jan		LAB 4_5: Uninformed and Informed Search Techniques
–  Introductory Problem: Vacuum World, Maze Problem
–  Exploratory Problem: Search in Pac-Man		LAB_4-5
Project Discussion
– Topic
5 FebLAB 6: Adversarial Search and Genetic Algorithm LAB-6
12 FebLAB 7: LOGICAL Agent
–  Online editor (Link)
–  Classics Example ( Link)
•   Movie database / Expert system / Eliza		LAB-7
19 FebMid- LAB TEST
4,9 MarLAB 8_9 : Robot path planning (Link)
– Explore Motion Planning with MATLAB (ebook)
– Apply any two motion planning algorithms available in Matlab Navigation Toolbox		LAB-8_9
11,18 MarLAB 10 : Learning Agent
–  Bayesian Network (data Link)
–  Fuzzy Logic 
–  Reinforcement Learning (Link )
–   NN 		LAB-10
Project PPT

1,2 AprilEND SEM LAB TEST

Books and References