INDUS INSTITUTE OF TECHNOLOGY & ENGINEERING

Constituent Institute of Indus University

Subject Name: Machine Learning and Deep Learning

Program: B. TECH. Subject Code: CE0733 Semester: 7
Teaching Scheme (Hours per week) Examination Evaluation Scheme (Marks)
Continuous Continuous
University University Internal Internal
Lecture Tutorial Practical Credits Theory Practical Evaluation Evaluation Total
Examination Examination (CIE)- (CIE)-
Theory Practical
3 0 2 4 40 40 60 60 200

Course Objective:

1 Classifying and identifying objects in images

2 Advanced image and pattern recognition with neural networks
3 Analysing and understanding human language, Deep understanding, generation, and processing of
human language
4 Enhanced recommendations with complex behavioural analysis
5 Forecasting future trends or outcomes based on historical data
6 Advanced predictive modelling with deep neural networks

CONTENTS

UNIT-I [10 hours]

Fundamentals of Machine Learning and Algorithms Learning Outcomes

Machine Learning Problems: Classification, Regression, Interpolation, and Density Estimation ,Linear
Regression Model, Classification Model, and Classification Evaluation.

Learning Algorithms: Supervised and Unsupervised and reinforcement learning ,Bayesian Decision Theory:
Bayesian Classifier, Discriminant Functions, Minimum Error Rate Classification, Naïve Bayes Classifier, Logistic
Regression Model and Parameter Estimation (Maximum-Likelihood), Dimensionality Reduction Technique:
Principal Component Analysis (PCA)

UNIT-II [10 hours]

Non-parametric Techniques: K-Nearest Neighbour (KNN), Density Estimation ,K-means Clustering ,Decision
Tree (Entropy, Gini Impurity Index) ,Support Vector Machine (SVM), Random Forest, Ensemble Learning,
Bagging, Boosting.

Introduction to Neural Networks: Neurons, Perceptron Convergence Theorem, Relation Between the
Perceptron and Bayes' Classifier, Multilayer Perceptron, Feedforward Operation, Batch and On-line Learning,
Activation Function, Backpropagation Algorithm, Rate of Learning, Stopping Criteria, XOR Problem, Loss
Function, Bias and Variance, Regularization, Cross-Validation, Early-Stopping Criteria.
UNIT-III [10 hours]

Fundamentals of Deep Learning: Importance of deep learning ,Learning from large datasets ,Types of data and
architectures ,Architecture of CNN ,Training methodology of CNN ,Use cases ,State-of-the-art CNN models ,
Modeling of time-series data Architecture design of RNN ,Training methodology of RNN ,Architectures of
LSTM and advantages over RNN ,Use cases ,Autoencoder (AE),Deep learning for unsupervised learning,
Architecture design of AE, Convolutional AE, Training with unlabelled data

UNIT-IV [10 hours]

Advanced Learning Techniques: Generative Modelling, Variational Autoencoder (VAE), Generative

Adversarial Network (GAN), Diffusion, high-quality image generation, Transfer learning, Leverage knowledge
from one task to improve performance on another task, Pre-training on large datasets, Fine-tuning DL models on
small datasets, Use cases Optimization of DL models, Transfer knowledge from a complex teacher model to a
simpler student model, Training methodology for distillation, Use cases.

Course Outcomes:
After learning the course, the students should be able to:
1 Gain proficiency in data analysis and visualization techniques essential for extracting insights from datasets.
2 Gain the necessary practical skills to implement all the algorithms using Python libraries like NumPy, pandas,
scikit-learn, and Keras.
3 A theoretical and practical understanding of the architectures, along with insights into design choices for
better model development.
4 Understanding the advantages of deep learning. Gain in-depth knowledge of deep architectures such as CNNs,
RNNs, LSTMs, GRUs, Attention mechanisms, Transformers, and Autoencoders.
5 Essential model training concepts like regularization, dropout, data augmentation, batch normalization, and
hyperparameter tuning are explored for effective optimization.

Textbooks:
1. Machine Learning Saikat Dull, S. Chjandramouli Das, Pearson
2. Machine Learning Using Python Pradhan Manaranjan, U Dinesh Kumar Wiley India Pvt. Ltd
3. Machine Learning with Python Cookbook_ Practical Solutions from Preprocessing to Deep Learning.
Chris Albon O’Reilly Media,
4. Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press, 2016.
5. S.N. Sivanandan and S.N. Deepa, Principles of Soft Computing, Wiley India, 2007. ISBN: 10: 81-265-
1075-7.
References:
1. Neural Networks: A Systematic Introduction, Raúl Rojas, 1996
2. Introduction to Machine Learning Jeeva Jose Khanna Publishers
3. Machine Learning in Action Peter Harrington Manning , dreamtech press
4. Machine Learning_ Step-by-Step Guide To Implement Machine Learning Algorithms with Python.
Rudolph Russell Rudolph Russell Publications
5. Pattern Recognition and Machine Learning, Christopher Bishop, 2007

Web Resources
Links for the several useful tools and lecture videos:
1. SOFTWARE/LEARNING WEBSITES
 https://www.geeksforgeeks.org/machine-learning/
 https://www.tutorialspoint.com/machine_learning_with_python/index.htm
 https://www.javatpoint.com/machine-learning
 https://scikit-learn.org/
 https://www.w3resource.com/python-exercises/pandas/index.php
 https://machinelearningforkids.co.uk/
 https://monkeylearn.com/machine-learning/
  http://appinventor.mit.edu/explore/ai-with-mit-app-inventor

2. NPTEL Course
o Neural Network and Its Applications , Prof. Somnath Sengupta , IIT Kharagpur.
3. Useful link for Learning Programming
o Python Tutorial
o Introduction to the numpy library
o MATLAB Tutorial
o Learning MATLAB (Video Tutorials)
4. Optimization problem solver (Matlab)
o Optimization Toolbox
o Choosing a Solver
5. Optimization problem solver (Python)
o Optimization and root finding
o pyOpt
Links specific to Deep Learning:
1. Links to Deep learning softwares
2. Torch
1. Deep Learning with Toch
2. Cheatsheet
3. Caffe
1. Tutorial
2. Deep learning tutorial on Caffe
4. Matlab
1. Toolbox
2. Deep Learning for Computer Vision with MATLAB and cuDNN

List of Practical:

Sr. Hrs.
No. Practical Exercises Required
1 MNIST digit recognition using DNN, CNN, and SVM. 4
2 Classification of Real news and Fake news using decision trees. 4
3 Prediction of the iris flower species using Naive Bayes classification. 2
4 Classify Photos of Dogs and Cats using Deep Convolutional Neural Network. 4
To build a movie recommender model using K-means clustering.
5 4
Identification of IoT devices using experimental radio spectrum dataset and
6 4
deep learning.
German Traffic Sign Recognition Benchmark: Develop a Feed Forward Neural Network
and then a Convolutional Neural Network to classify between the different Road Signs in
7 4
the dataset given below. Test it using images from the
internet to validate the functioning of your model.
CIFAR-10 Object Recognition: Develop a Convolutional Neural Network to classify
8 between the different classes of the Dataset given below. Test it using 4
images from the internet.
9 Sentiment Analysis using Naive Bayes Classifier. 2
10 Application of Deep Learning in Medical Diagnosis using Health Data. 2
11 Credit Card Fraud Detection using Random Forest Classifier. 4
12 Music Recommendation System using K-NN Algorithm. 4