Course10610870558 lectures
Artificial Intelligence: Concepts and Techniques
Prof. V. Susheela Devi · IISc Bangalore
About
Artificial Intelligence is found being increasing used nowadays to carry out tasks which used to be done by humans manually. This is a post graduate level course which teaches about the concepts and techniques employed in Artificial Intelligence. This covers concepts such as general problem solving, logic and reasoning, machine learning and deep learning, generative AI, and planning. Practical use of different deep learning architectures is taught in the hands-on sessions. Topics like genetic algorithms and natural language processing are also covered. Ethical concerns and multi-agent systems such as web-based agents, mobile agents and negotiating agents are touched upon towards the end of the course.
Intended audience: Instructors and students of academic institutes, employees in IT sector especially working in the Artificial Intelligence field
Prerequisites: Bachelors degree in engineering, MCA, M.Sc.(Maths)
Lectures
Week 1 Introduction
- Course overview & Introduction
- History & Applications of AI
- Agents and Environment
- General Problem Solving
- Introduction to Search Strategies
Week 2 Search Strategies
- Uninformed Search Strategies - I
- Uninformed Search Strategies - II
- Informed Search Strategies - I
- Informed Search Strategies - II
- Adversarial or Game-Playing Search
Week 3 Genetic Algorithms
- Game-Playing Search
- Introduction to Genetic Algorithms
- GA Operators
- Genetic Programming
- Knowledge-Base Agents
Week 4 Proposotional and Predicate Logic
- Proposotional Logic
- Predicate Logic - 1
- Predicate Logic - 2
- Inference in Predicate Logic
- Inference in First Order Logic
Week 5 Expert Systems and Planning
- Introduction to Expert Systems
- Applications of Expert Systems
- Introduction to Planning
- Planning Graph
- Planning and Scheduling
Week 6 Knowledge Representation
- Knowledge Representation
- Non Monotonic Reasoning
- Representation Schemes - 1
- Representation Schemes - 2
- Uncertanity in Knowledge Representation
Week 7 Decisions
- Bayesian Network
- Dynamic belief networks (DBN)
- Utility Theory
- Decision Theory - 1
- Decision Theory - 2
Week 8 Learning and Introduction to Neural Networks
- Introduction to Learning
- Learning Algorithms
- Learning Algorithms
- Ensemble Learning
- Introduction to Neural Networks
Week 9 Multilayer perceptron neural network and its Implementation
- Multilayer Perceptron Neural network
- Hypothesis Learning
- Practical session - 1
- Practical session - 2
Week 10 Deep Learning Hands-on and Models
- Introduction to deep learning
- Datasets for DL
- CNN and introduction to RNN
- RNN & LSTMs
- Practical session - 3
Week 11 Fuzzy Sets and NLP
- Practical Section - 4
- Practical Section - 5
- Generative AI
- Fuzzy Sets and Systems
- Fuzzification and Defuzzification methods
Week 12 Natural language processing, ethics, swarm intelligence and multi-agent systems
Syllabus and materials
At NPTEL, as the course publishes them.
Credits and licence
- Institution
- IISc Bangalore
- Department
- Computer Science and Engineering
- Teacher
- Prof. V. Susheela Devi
- Level
- Graduate
- Language
- English
- Subjects
- Computer science, Engineering
- Source
- NPTEL
- Licence
- CC BY-NC-SA, as NPTEL states it. Non-commercial use only. NPTEL's terms
- Attribution
- NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge.
- Who can watch
- NPTEL gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed