BN4301 Artificial Intelligence and Machine Learning Syllabus:
BN4301 Artificial Intelligence and Machine Learning Syllabus – Anna University PG Syllabus Regulation 2021
OBJECTIVES:
➢ To expose various algorithms related to Artificial Intelligence machine learning.
➢ To prepare students to apply suitable algorithm for the specified applications.
➢ To introduce Learners to the basic concepts and techniques of Machine Learning.
➢ To give new insights on how to apply machine learning to solve a new problem.
UNIT – I INTELLIGENT SYSTEMS
Introduction to Artificial Intelligence: Intelligent Systems – Foundations of AI – Applications – Tic-Tac-Toe Game Playing – Problem Solving: State-Space Search and Control Strategies: Introduction – General Problem Solving – Exhaustive Searches – Heuristic Search Techniques.
UNIT – II KNOWLEDGE REPRESENTATION
Advanced Problem-Solving Paradigm: Planning: Introduction – Types of Planning Systems – Knowledge Representation: Introduction – Approaches to Knowledge Representation – Knowledge Representation using Semantic Network – Knowledge Representation using Frames. Expert Systems and Applications: Blackboard Systems – Truth Maintenance Systems – Applications of Expert Systems.
UNIT – III INTRODUCTION TO MACHINE LEARNING
Human Learning – Types of Human Learning, Machine Learning – Types of Machine Learning, Applications, Tools, Issues, Types of Data in Machine Learning, Exploring Structure of Data, Data Quality and Remediation, data Pre-Processing, Selecting and Training a Model, Model Representation and Interpretability, Evaluating and Improving performance of a Model.
UNIT- IV BAYESIAN LEARNING
Bayes Theorem and Concept Learning, Maximum Likelihood and Least-squared Error Hypotheses, Maximum Likelihood Hypotheses for Predicting Probabilities, Minimum Description Length Principle, Bayes Optimal Classifier, Gibbs Algorithm, Naive Bayes Classifier, Bayesian Belief Networks, EM Algorithm.
UNIT- V SUPERVISED AND UNSUPERVISED LEARNING
Classification Model, Classification Learning Steps, Common Classification Algorithms, Understanding the Biological Neuron, Exploring the Artificial Neuron, Types of Activation Functions, Early Implementations of Artificial Neural Networks, Architectures of Neural Networks, Learning Process in Artificial Neural Networks. Unsupervised vs Supervised Learning, Applications of Unsupervised Learning, Clustering, Finding pattern using Association Rule, Other Unsupervised Learning Problems – Principal Component Analysis, Topic Modeling.
TOTAL: 45 PERIODS
COURSE OUTCOMES :
➢ Knowledge of Algorithms of Artificial Intelligence and machine learning.
➢ Knowledge of applying Algorithm to specified applications.
➢ Ability to understand intelligent systems and Heuristic Search Techniques
➢ Understanding of Knowledge Representation, Semantic Networks and Frames
➢ Understand complexity of Machine Learning algorithms and their limitations.
➢ Be capable of performing experiments in Machine Learning using real-world data.
➢ Knowledge of Expert systems, applications and Machine learning.
REFERENCES :
1. SarojKaushik, “Artificial Intelligence”, Cengage Learning India Pvt. Ltd.
2. Deepak Khemani, “A First Course in Artificial Intelligence”, McGraw Hill Education(India) Private Limited, NewDelhi.
3. Elaine Rich, Kevin Night, Shivashankar B Nair, “Artificial Intelligence” Third Edition, McGraw Hill, 2008.
4. YoshuaBengio, “Learning Deep Architectures for AI”, Foundations and Trends in Machine Learning.
5. Saikat Dutt, Subramanian Chandramouli and Amit Kumar Das, Machine Learning, Pearson Education, 2019
6. Anuradha Srinivasaraghavan, Vincy Elizabeth Joseph, Machine Learning, Wiley,2019
7. Gopinath Rebala, Ajay Ravi, Sanjay Churiwala, An Introduction to Machine Learning Springer, 7 May 2019
8. Thom Mitchell, Machine Learning, McGraw Hill Education, 2017
9. Oliver Theobald, Machine Learning for Absolute Beginners, 2017
10. Ethem Alpaydin, Introduction to Machine Learning, 3rd edition, 2014