Scribd
Upload
8 views1 page

IS2231

Uploaded by

vasudevanitk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views1 page

IS2231

Uploaded by

vasudevanitk
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

IS2231-1 ARTIFICIAL INTELLIGENCE

Course Outcomes: At the end of the course student will be able to


1. Explain the fundamental understanding of the history of artificial intelligence (AI), agent
and its foundation.
2. Interpret the basic principles of AI in solutions that require problem solving using
searching.
3. Understand the various applications of AI techniques in quantifying uncertainty and
probability reasoning.
4. Developing simple applications in an AI language, using reinforcement learning.
5. Describe the concepts of q-learning intuition and Artificial neural networks.

Course Description
Introduction: what is AI, Acting Humanly: The Turing Test approach, Thinking Humanly: The cognitive
modelling approach, thinking rationally: The laws of thought approach, Acting Rationally: The rational
agent approach. The state of art. Intelligent Agents: Agents and Environments, Good behaviour: The
concept of rationality, The nature of environments, properties of task environments, Structure of
Agents: Agent Programs, Types of agent programs. Solving Problems by Searching: Problem solving
Agents, well defined problems and solutions, formulating problems, Example problems: Toy problems:
Vacuum world, 8-Queen’s problem, Real world problem: Airline Route finding problem. Searching for
solutions: Infrastructure for search algorithms, measuring problem solving performance, Uninformed
search strategies: Breadth first search, Cost search, Depth first search, Informed search strategies:
Greedy best search, A* algorithms, Heuristic functions.

Quantifying Uncertainty: Acting under uncertainty, summarizing uncertainty, Uncertainty and rational
decisions, Basic probability notation, what probabilities are about. The language of propositions in
probability assertions, Inference using full joint distribution, Bayes’ rule and its use, Applying Bayes’
rule for simple use case. Probability Reasoning Over time: Time and Uncertainty, States and
observations, Transition and Sensor models, Inference in temporal models, Smoothing, Hidden
Markov model, Simplified matrix algorithms, Hidden Markov model: Localization, Kalman Filter basics.
Reinforcement Learning: Introduction, Passive reinforcement learning, Generalization in
reinforcement learning, Applications of reinforcement learning.

Q-Learning Intuition: Plan of attack, Bellman Equation, The Plan, Markov Decision Process, Policy vs
Plan, Adding Living penalty, Temporal Difference Artificial Neural Networks: Introduction, Neural
network representation, Appropriate problems for neural network learning, Perceptron:
Representational power of perceptron, The perceptron training rule, gradient descent and delta rule

The course gives the theoretical background of AI with different methods and examples. The course
is a mix theoretical descriptions, algorithms and problems. The course requires basic knowledge and
interest in mathematical concepts like logic, probability and linear algebra. The course introduces the
basics of AI, different algorithms used in AI without any practical implementations. It highlights the
expectations from AI applications and how they are met. The aspirants who have studied and excelled
in the Machine Learning course may take up this course to get more in depth knowledge on AI to take
up career in AI related fields.

You might also like