BM4251 AI and Machine Learning Syllabus:
BM4251 AI and Machine Learning Syllabus – Anna University PG Syllabus Regulation 2021
COURSE OBJECTIVES:
To introduce the concept of machine learning
To learn and apply neural networks for pattern classification and regression problems
To introduce the ideas of fuzzy sets, fuzzy logic
To familiarize with genetic algorithms for seeking global optimum in self-learning situations
To introduce the Deep learning concept for medical image analysis
UNIT I INTRODUCTION TO MACHINE LEARNING
Machine Learning – Basic Concepts in Machine Learning – Types of Machine Learning – Examples of Machine Learning – Applications – Linear Models for Regression – Linear Basis Function Models – The Bias-Variance Decomposition – Bayesian Linear Regression – Dimensionality Reduction.
UNIT II NEURAL NETWORKS
Biological Neurons and their Artificial models, Learning Rules, Single Layer Perceptron Classifiers., Back Propagation Network, generalized delta rule, Associative Memory, Adaptive Resonance Theory (ART) Network Descriptions
UNIT III FUZZY LOGIC SYSTEMS
Fuzzy Logic System: Basic of fuzzy logic theory , crisp and fuzzy sets, Basic set operation like union , interaction , complement , T-norm , T-conorm , fuzzy relations, fuzzy if-then rules , fuzzy reasoning, Neuro-Fuzzy Modeling: Adaptive Neuro-Fuzzy Inference System (ANFIS) , ANFIS architecture , Hybrid Learning Algorithm
UNIT IV EVOLUTIONARY COMPUTATION & GENETIC ALGORITHMS
Evolutionary Computation (EC) – Features of EC – Classification of EC – Advantages – Applications. Genetic Algorithms: Introduction – Biological Background – Operators in GA-GA Algorithm – Classification of GA – Applications
UNIT V ADVANCES AND APPLICATIONS
Support Vector Machines, RBF Network. Introduction to Deep Learning – Convolutional Neural Network. Case Study – Neural Network based Classification of Bio signal and Medical Images.
45 PERIODS
PRACTICAL EXERCISES: 30 PERIODS
1. Implement Simple Programs like vector addition in Tensor Flow.
2. Implement a simple problem like regression model in Keras.
3. Implement a perceptron in TensorFlow/Keras Environment.
4. Implement a Feed-Forward Network in TensorFlow/Keras.
5. Implement an Image Classifier using CNN in TensorFlow/Keras.
6. Develop an abnormal detection system for bio signal data using fuzzy logic.
7. Develop a system to implement Neural Networks techniques to define predictive models for Abnormal detection.
8. Develop a system that can optimize the solution of the abnormal detection system developed by fuzzy logic
9. Implement a biosignal/medical image Classifier using CNN.
COURSE OUTCOMES:
On completion of this course the student will be able to:
CO1: Identify and describe machine learning techniques and their roles in building intelligent system
CO2: Design neural networks for pattern classification and regression problems
CO3: Apply fuzzy logic and reasoning to handle uncertainty and solve engineering problems.
CO4: Apply genetic algorithms to optimization problems.
CO5: Apply Deep learning concept for biomedical signal analysis and Medical image analysis
TOTAL:75 PERIODS
REFERENCES
1. Tom M. Mitchell, “Machine Learning”, McGraw-Hill Education (INDIAN EDITION), 2013
2. Ethem Alpaydin, “Introduction to Machine Learning”, 2nd Ed., PHI Learning Pvt. Ltd., 2013.
3. T. Hastie, R. Tibshirani, J. H. Friedman, The Elements of Statistical Learning, Springer; 1st edition, 2001.
4. Wolfgang Ertel, “Introduction to Artificial Intelligence”, Springer, 2nd Edition, 2017
5. Nello Cristianini, John Shawe-Taylor, “An Introduction to Support Vector Machines and Other Kernel-based Learning Methods”,Cambridge University Press. 2013
6. Timothy Ross, “Fuzzy Logic with Engineering Applications”, Wiley, 2016
7. David E. Goldberg, “Genetic Algorithms in search, Optimization & Machine Learning”, Pearson Education, 2006
8. Neural Networks and Deep Learning by Michael Nielsen., March 2017.