MAHENDRA ENGINEERING COLLEGE(Autonomous)

Syllabus R-2024
ProgrammeCod
Department 5041
e
Elective
Course code Course Name Hours/week Credit Maximum marks
ARTIFICIAL L T P C
INTELLIGENC 3 0 0 3
24COM13022 E AND 100
MACHINE
LEARNING
 Study about uninformed and Heuristic search techniques.
 Learn techniques for reasoning under uncertainty
Objective(s)  Introduce Machine Learning and supervised learning algorithms
 Study about ensembling and unsupervised learning algorithms
 Learn the basics of deep learning using neural networks
UNIT-I PROBLEM SOLVING 9
Introduction to AI - AI Applications - Problem solving agents – search algorithms –
uninformed search strategies – Heuristic search strategies – Local search and optimization
problems – adversarial search – constraint satisfaction problems (CSP)
UNIT-II PROBABILISTIC REASONING 9

Acting under uncertainty – Bayesian inference – naïve bayes models. Probabilistic reasoning –
Bayesian networks – exact inference in BN – approximate inference in BN – causal networks.

UNIT-III SUPERVISED LEARNING 9

Introduction to machine learning – Linear Regression Models: Least squares, single &
multiple variables, Bayesian linear regression, gradient descent, Linear Classification Models:
Discriminant function – Probabilistic discriminative model - Logistic regression, Probabilistic
generative model – Naive Bayes, Maximum margin classifier – Support vector machine,
Decision Tree, Random forests
UNIT-IV ENSEMBLE TECHNIQUES AND 9
UNSUPERVISED LEARNING
Combining multiple learners: Model combination schemes, Voting, Ensemble Learning -
bagging, boosting, stacking, Unsupervised learning: K-means, Instance Based Learning: KNN,
Gaussian mixture models and Expectation maximization
UNIT-V NEURAL NETWORKS 9
Perceptron - Multilayer perceptron, activation functions, network training – gradient descent
optimization – stochastic gradient descent, error backpropagation, from shallow networks to
deep networks –Unit saturation (aka the vanishing gradient problem) – ReLU, hyperparameter
tuning, batch normalization, regularization, dropout.
Total 45
 Use appropriate search algorithms for problem solving
 Apply reasoning under uncertainty
Outcome(s  Build supervised learning models
)
 Build ensembling and unsupervised models
 Build deep learning neural network models

MAHENDRA ENGINEERING
COLLEGE
(Aut
S
Computer Science and y Programme
Department 50
Engineering Code
32
Program
Elective Maximu
Course code Course Name Hours/week Credit
m
marks
24CSE15127 COMPUTER VISION L T P C 10
3 0 0 3 0
The student should be made to:
● To review image processing techniques for computer vision.
● To understand shape and region analysis.
Objective(s)
● To learn Hough Transform and its applications to detect
lines, circles, ellipses.
● To understand motion analysis.
● To study some applications of computer vision algorithms.
 Upon completion of this course, students will be able to
● Implement fundamental image processing techniques required for
computer
Outcome(s) vision.
● Perform shape analysis.
● Apply Hough Transform for line, circle, and ellipse detections.
● Apply 3D vision techniques.
UNIT-I ● Develop
IMAGE applications
PROCESSING using computer vision techniques.
FOUNDATIONS 9
Review of image processing techniques – classical filtering operations – thresholding
techniques – Edge detection techniques–corner and interest point detection–mathematical
morphology–texture.
UNIT-II SHAPES AND REGIONS 9
Binary shape analysis – connectedness – object labeling and counting – size filtering –
distance functions
– skeletons and thinning – deformable shape analysis – boundary tracking procedures – active
contours –
shape models and HOUGH
UNIT-III shape recognition
TRANSFORM– centroidal profiles – handling occlusion – 9
Line detection – Hough Transform (HT) for line detection – foot-of-normal
method – line Localization – line fitting – RANSAC for straight line detection – HT based
circular object detection– accurate center location–speed problem– ellipse detection –Case
study: Human Iris location–hole detection–generalized Hough Transform (GHT) – spatial
matched filtering–GHT for ellipse detection– object location–GHT for feature collation.
UNIT-IV 3D VISION AND MOTION 9
Methods for 3D vision – projection schemes – shape from shading – photometric stereo –
shape from texture – shape from focus – active range finding – surface representations –
point-based representation – volumetric representations – 3D object recognition – 3D
reconstruction – introduction to motion – triangulation – bundle adjustment – translational
alignment – parametric motion – spline-based motion – Optical flow – layered motion.

UNIT-V APPLICATIONS 9
Application: Photo album – Face detection – Face recognition – Eigen faces – Active
appearance and 3D shape models of faces Application: Surveillance – foreground-
background separation – particle filters – Chamfer matching, tracking, and occlusion –
combining views from multiple cameras – human gait analysis Application: In-vehicle
vision system: locating roadway – road markings – identifying road signs – locating
pedestrians. 45 HOURS
Total ho
 MAHENDRA ENGINEERING
COLLEGE
(Autono
Sy
lla
Computer Science Programme
Department 503
and Code
2
Engineeri
Program
Elective
Maximu
Course code Course Name Hours/week Credit
m
mark
L T P C
24CSE15131 DEEP LEARNING 10
3 0 0 3 0
The student should be made to:
 To learn and develop and Train Deep Neural Networks.
 To understand a CNN, R-CNN, Fast R-CNN, Faster-R-CNN, Mask-
Objective(s) RCNN for detection and recognition.
 To explore and train RNNs, work with NLP and Word Embeddings
 To familiarize internal structure of LSTM and GRU and the
differences between them
 To know Auto Encoders for Image Processing

Upon completion of this course, students will be able to

 Explain Feature Extraction from Image and Video Data
 Implement Image Segmentation and Instance Segmentation in Images
Outcome(s)  Implement image recognition and image classification using a
pretrained network (Transfer Learning)
 Traffic Information analysis using Twitter Data
 Develop Autoencoder for Classification & Feature Extraction
UNIT-I DEEP LEARNING CONCEPTS 9

Fundamentals about Deep Learning. Perception Learning Algorithms. Probabilistic

modelling. Early Neural Networks. How Deep Learning different from Machine Learning.
Scalars. Vectors. Matrixes, Higher Dimensional Tensors. Manipulating Tensors. Vector
Data. Time Series Data. Image Data. Video Data.
UNIT-II NEURAL NETWORKS 9
About Neural Network. Building Blocks of Neural Network. Optimizers. Activation
Functions. Loss Functions. Data Pre-processing for neural networks, Feature
Engineering. Overfitting and Underfitting. Hyperparameters.
UNIT-III CONVOLUTIONAL NEURAL NETWORK 9
About CNN. Linear Time Invariant. Image Processing Filtering. Building a convolution
neural network. Input Layers, Convolution Layers. Pooling Layers. Dense Layers.
Backpropagation Through the Convolutional Layer. Filters and Feature Maps.
Backpropagation Through the Pooling

Layers. Dropout Layers and Regularization. Batch Normalization. Various Activation

Functions.
Various Optimizers. LeNet, AlexNet, VGG16, ResNet. Transfer Learning with Image Data.
Transfer Learning using Inception Oxford VGG Model, Google Inception Model and
Microsoft
UNIT-IV ResNet Model. R- LANGUAGE
NATURAL CNN, Fast R-CNN, Faster R-CNN,
PROCESSING USINGMask-RCNN,
RNN YOLO 9
About NLP & its Toolkits. Language Modeling. Vector Space Model (VSM). Continuous
Bag of Words (CBOW). Skip-Gram Model for Word Embedding. Part of Speech (PoS)
Global Co- occurrence Statistics–based Word Vectors. Transfer Learning. Word2Vec.
Global Vectors for Word Representation GloVe. Backpropagation Through Time.
Bidirectional RNNs (BRNN). Long Short Term Memory (LSTM). Bi-directional LSTM.
Sequence-to-Sequence Models (Seq2Seq). Gated recurrent unit GRU.
UNIT-V DEEP REINFORCEMENT & UNSUPERVISED LEARNING 9
About Deep Reinforcement Learning. Q-Learning. Deep Q-Network (DQN). Policy Gradient
Methods. Actor-Critic Algorithm. About Autoencoding. Convolutional Auto Encoding.
Variational Auto Encoding. Generative Adversarial Networks. Autoencoders for Feature
Extraction. Auto Encoders for Classification. Denoising Autoencoders. Sparse Autoencoders
Total hours 45 HOURS