artificial intelligence assignment pdf download

Artificial Intelligence: A Modern Approach, 4th US ed.

• Computer Science and Engineering
• NOC:An Introduction to Artificial Intelligence (Video) 
• Co-ordinated by : IIT Delhi
• Available from : 2019-11-13
• Intro Video
• Introduction: What to Expect from AI
• Introduction: History of AI from 40s - 90s
• Introduction: History of AI in the 90s
• Introduction: History of AI in NASA & DARPA(2000s)
• Introduction: The Present State of AI
• Introduction: Definition of AI Dictionary Meaning
• Introduction: Definition of AI Thinking VS Acting and Humanly VS Rationally
• Introduction: Definition of AI Rational Agent View of AI
• Introduction: Examples Tasks, Phases of AI & Course Plan
• Uniform Search: Notion of a State
• Uniformed Search: Search Problem and Examples Part-2
• Uniformed Search: Basic Search Strategies Part-3
• Uniformed Search: Iterative Deepening DFS Part-4
• Uniformed Search: Bidirectional Search Part-5
• Informed Search: Best First Search Part-1
• Informed Search: Greedy Best First Search and A* Search Part-2
• Informed Search: Analysis of A* Algorithm Part-3
• Informed Search Proof of optimality of A* Part-4
• Informed Search: Iterative Deepening A* and Depth First Branch & Bound Part-5
• Informed Search: Admissible Heuristics and Domain Relaxation Part-6
• Informed Search: Pattern Database Heuristics Part-7
• Local Search: Satisfaction Vs Optimization Part-1
• Local Search: The Example of N-Queens Part-2
• Local Search: Hill Climbing Part-3
• Local Search: Drawbacks of Hill Climbing Part-4
• Local Search: of Hill Climbing With random Walk & Random Restart Part-5
• Local Search: Hill Climbing With Simulated Anealing Part-6
• Local Search: Local Beam Search and Genetic Algorithms Part-7
• Adversarial Search : Minimax Algorithm for two player games
• Adversarial Search : An Example of Minimax Search
• Adversarial Search : Alpha Beta Pruning
• Adversarial Search : Analysis of Alpha Beta Pruning
• Adversarial Search : Analysis of Alpha Beta Pruning (contd...)
• Adversarial Search : Horizon Effect, Game Databases & Other Ideas
• Adversarial Search: Summary and Other Games
• Constraint Satisfaction Problems: Representation of the atomic state
• Constraint Satisfaction Problems: Map coloring and other examples of CSP
• Constraint Satisfaction Problems: Backtracking Search
• Constraint Satisfaction Problems: Variable and Value Ordering in Backtracking Search
• Constraint Satisfaction Problems: Inference for detecting failures early
• Constraint Satisfaction Problems: Exploiting problem structure
• Logic in AI : Different Knowledge Representation systems - Part 1
• Logic in AI : Syntax - Part - 2
• Logic in AI : Semantics - Part - 3
• Logic in AI : Forward Chaining - Part 4
• Logic in AI : Resolution - Part - 5
• Logic in AI : Reduction to Satisfiability Problems - Part - 6
• Logic in AI : SAT Solvers : DPLL Algorithm - Part - 7
• Logic in AI : Sat Solvers: WalkSAT Algorithm - Part - 8
• Uncertainty in AI: Motivation
• Uncertainty in AI: Basics of Probability
• Uncertainty in AI: Conditional Independence & Bayes Rule
• Bayesian Networks: Syntax
• Bayesian Networks: Factoriziation
• Bayesian Networks: Conditional Independences and d-Separation
• Bayesian Networks: Inference using Variable Elimination
• Bayesian Networks: Reducing 3-SAT to Bayes Net
• Bayesian Networks: Rejection Sampling
• Bayesian Networks: Likelihood Weighting
• Bayesian Networks: MCMC with Gibbs Sampling
• Bayesian Networks: Maximum Likelihood Learning"
• Bayesian Networks: Maximum a-Posteriori Learning 
• Bayesian Networks: Bayesian Learning
• Bayesian Networks: Structure Learning and Expectation Maximization
• Introduction, Part 10: Agents and Environments
• Decision Theory: Steps in Decision Theory
• Decision Theory: Non Deterministic Uncertainty
• Probabilistic Uncertainty & Value of perfect information
• Expected Utility vs Expected Value
• Markov Decision Processes: Definition
• Markov Decision Processes: An example of a Policy
• Markov Decision Processes: Policy Evaluation using system of linear equations
• Markov Decision Processes: Iterative Policy Evaluation
• Markov Decision Processes: Value Iteration
• Markov Decision Processes: Policy Iteration and Applications & Extensions of MDPs
• Reinforcement Learning: Background
• Reinforcement Learning: Model-based Learning for policy evaluation (Passive Learning)
• Reinforcement Learning: Model-free Learning for policy evaluation (Passive Learning)
• Reinforcement Learning: TD Learning
• Reinforcement Learning: TD Learning and Computational Neuroscience
• Reinforcement Learning: Q Learning
• Reinforcement Learning: Exploration vs Exploitation Tradeoff
• Reinforcement Learning: Generalization in RL
• Deep Learning : Perceptrons and Activation functions
• Deep Learning : Example of Handwritten digit recognition
• Deep Learning : Neural Layer as matrix operations
• Deep Learning : Differentiable loss function
• Deep Learning : Backpropagation through a computational graph
• Deep Learning : Thin Deep Vs Fat Shallow Networks
• Deep Learning : Convolutional Neural Networks
• Deep Learning : Deep Reinforcement Learning
• Ethics of AI : Humans vs Robots
• Ethics of AI : Robustness and Transparency of AI systems
• Ethics of AI : Data Bias and Fairness of AI systems
• Ethics of AI : Accountability, privacy and Human-AI interaction
• Watch on YouTube
• Assignments
• Download Videos
• Transcripts

Browse Course Material

Course info.

• Patrick Henry Winston

Departments

• Electrical Engineering and Computer Science

As Taught In

• Algorithms and Data Structures
• Artificial Intelligence
• Theory of Computation

Learning Resource Types

Mit6_034f10_final_2008.pdf.

This resource contains information related to forward chaining.

You are leaving MIT OpenCourseWare

• Lectures: Mon/Wed 1:30pm-2:50pm in NVIDIA Auditorium .
• Problem sessions: Fri 1:30-2:20pm in Thornton 102 .
• Office hours, homework parties: see the Calendar and the HW OH Queue .
• Try our new LLM powered bot on slack . Note: do not direct message any members of course staff on Slack.
• To contact all teaching staff, use Ed .
• For personal/sensitive matters, email [email protected] .
• Modules : All the course content has been broken up into short modules , which include slides, recorded videos, and notes.
• Lectures: Instructors go over the main modules more slowly and interactively. All lectures will be recorded and available on Canvas.
• Problem sessions: CAs work through practice homework and exam problems.
• Homework parties : CAs help students work through homework problems in small groups.
• Office Hours: Meet 1:1 with instructors and CAs. There are two types of CA office hours: homework OH (for help with homework questions) and general OH (to ask questions about course content from lecture).
• Looking at the writeup or code of another student.
• Showing your writeup or code to another student.
• Discussing homework problems in such detail that your solution (writeup or code) is almost identical to another student's solution.
• Uploading your writeup or code to a public repository (e.g., GitHub) so that it can be accessed by other students.
• Looking at solutions from previous years, either official or written up by another student, or found online.

Generative AI Policy: Each student is expected to submit their own solutions to the CS221 homeworks. You may use generative AI tools such as Co-Pilot and ChatGPT as you would use a human collaborator. This means that you may not directly ask generative AI tools for answers or copy solutions, and acknowledge generative AI tools as collaborators. The use of generative AI tools to substantially complete an assignment or exam (e.g. by directly copying) is prohibited and will result in honor code violations. We will be checking students' homework to enforce this policy.

Anyone violating the honor code policy will be referred to the Office of Judicial Affairs. If you think you violated the policy (it can happen, especially under time pressure!), please reach out to us; the consequences will be much less severe than if we approach you.

• Note that messages on public channels in slack are visible to other students and course staff.
• It is a strict violation of course policies to direct message course staff on slack, please keep interaction to public threads or reach out via Ed or the lead staff mailing list if you have questions.
• The student honor code still applies to messages and interactions on slack.
• (Required) Programming CS 106A , CS 106B
• (Required) Discrete math, mathematical rigor: CS 103
• (Required) Probability: CS 109
• (Required) Linear algebra: Math 51
• (recommended, but not required) Algorithms: CS 161
• (recommended, but not required) Systems: CS 107
• Russell and Norvig. Artificial Intelligence: A Modern Approach. A comprehensive reference for all the AI topics that we will cover.
• Koller and Friedman. Probabilistic Graphical Models. Covers factor graphs and Bayesian networks (this is the textbook for CS228 ).
• Sutton and Barto. Reinforcement Learning: An Introduction. Covers Markov decision processes and reinforcement learning (free online).
• Hastie, Tibshirani, and Friedman. The Elements of Statistical Learning. Covers machine learning from a rigorous statistical perspective (free online).
• Tsang. Foundations of Constraint Satisfaction. Covers constraint satisfaction problems (free online).
• Exam 1 (30%): Nov 2nd, 6-8 PM on Campus .
• Exam 2 (30%): Dec 13th, 3:30 - 5:30 PM on Campus .
• If you have a major time conflict for either exam, you should fill out this form by Friday, October 13 (week 3) .

Both exams will be in-person.

Exam Conflicts: Please reach out via the lead-staff mailing list if you have exam conflicts.

SCPD Students: SCPD students will need to nominate exam monitors for both exams and coordinate the exam process with the SCPD exams team . Please refer to this link for more information on the process. For any additional questions, please reach out to the SCPD exams team .

• Projects should be done in groups of 1-4 students.
• There are 5 milestones for the project throughout the quarter: interest form, proposal, progress report, video/poster, final report.
• Each project group will be assigned a CA mentor who will give feedback and answer questions.
• For inspiration, check out previous CS221 projects .
• See the project page for more details.
• --> Project interest form [p-interest] (due Tue Oct--> )--> Project proposal [p-proposal] (due Tue Oct--> )--> Project progress report [p-progress] (due Tue--> )--> Project final report and video [p-final] (due Tue--> )-->