GI3018 AI / DL for Image Processing Syllabus:

GI3018 AI / DL for Image Processing Syllabus – Anna University Regulation 2021

COURSE OBJECTIVES:

 To familiarize the undergraduate level students to understand the concepts of AI/DL and their applications.

UNIT I EXPLORATORY DATA ANALYSIS

Inferential statistics – hypothesis testing – spectral divergence- spectral angle mapper – spectral correlation analysis – support vector machines- tree models – unsupervised learning – clusters –kmeans- fuzzy concepts – possibilistic k means – training date sets- random forest classifier – measures of accuracy: RMS, correlation co efficient, ROC

UNIT II ARTIFICIAL INTELLIGENCE

Foundation of AI and history of AI intelligent agents: Agents and Environments, the concept of rationality, the nature of environments, structure of agents, problem solving agents, problem formulation – AI problems

UNIT III LEARNING BASED CLASSIFIERS

Kernel concepts – Linear regression – logistics regression – ANN – variants of ANN – back propagation- weight update- CNN- supervised machine learning concepts- recurrent neural network – Hybrid learning network – prediction algorithms – exercise: building foot print extraction, wetland map generation

UNIT IV DEEP LEARNING CONCEPTS AND METHODS

Cloud essentials -Git hub – Concepts- convolution- pooling – activation functions – tensorsnormalisation- sampling- training – loss function- optimizer – inference – ensemble techniques – models with multiple sources- patch based mode vs. fully convolutional mode- Introduction to CNNsBack Propagation Algorithm, Vanishing and Exploding Gradients Overfitting Evolution of CNN Architectures: AlexNet, ZFNet, VGG Net, InceptionNets, ResNets, DenseNets.

UNIT V APPLICATIONS OF CNN

CNNs for Detection: Background of Object Detection, R-CNN, Fast R-CNN, Faster R-CNN, YOLO. CNNs for Segmentation: Types of Segmentation: Instance vs semantic segmentation. FCN, SegNet, U-Net, Mask-RCNN.

TOTAL:45 PERIODS
COURSE OUTCOMES:

On completion of the course, the student is expected
CO1 To provide Knowledge about exploratory data analysis
CO2 To understand concept of Artificial Intelligence
CO3 To understand about learning based classifiers
CO4 To learn concepts and various methods of deep learning
CO5 To learn about various applications of CNN

TEXTBOOKS:

1. S. Russell and P. Norvig, “Artificial Intelligence: A Modern Approach”, Prentice Hall, Third Edition, 2010.
2. Ian J. Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2017. 2.
3. Francois Chollet, “Deep Learning with Python”, Manning Publications, 2021, 2nd edition.

REFERENCES

1. Bratko, “Prolog: Programming for Artificial Intelligence”, Fourth edition, Addison Wesley Educational Publishers Inc., 2011.
2. M. Tim Jones, “Artificial Intelligence: A Systems Approach(Computer Science)”, Jones and Bartlett Publishers, Inc.; First Edition, 2008
3. Phil Kim, “Matlab Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence”, Apress, 2017.
4. Ragav Venkatesan, Baoxin Li, “Convolutional Neural Networks in Visual Computing”, CRC Press, 2017.