Scribd
Upload
82 views

Machine Learning Deep Learning

This document provides information on the course ECE 6093 Advanced Machine Learning and Deep Learning. The course aims to provide an understanding of fundamentals of machine learning and neural networks, knowledge of pattern recognition, and ability to apply deep learning algorithms to solve real-life problems. The course outcomes include comprehending machine learning algorithms and neural network architectures, understanding pattern association using neural networks, and adopting classification techniques. The course contains modules covering learning problems, neural networks, machine learning terminologies, feature selection, convolutional neural networks, RNNs, autoencoders and GANs.

Uploaded by

Professor's Tech Academy
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
82 views

Machine Learning Deep Learning

This document provides information on the course ECE 6093 Advanced Machine Learning and Deep Learning. The course aims to provide an understanding of fundamentals of machine learning and neural networks, knowledge of pattern recognition, and ability to apply deep learning algorithms to solve real-life problems. The course outcomes include comprehending machine learning algorithms and neural network architectures, understanding pattern association using neural networks, and adopting classification techniques. The course contains modules covering learning problems, neural networks, machine learning terminologies, feature selection, convolutional neural networks, RNNs, autoencoders and GANs.

Uploaded by

Professor's Tech Academy
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Course Code Course Title L T P J C

ECE 6093 Advanced Machine Leaning and Deep Learning 3 0 0 0 3


Pre-requisite Nil Syllabus Version : 1.0
Course Objectives:
The course is aimed at

[1] Understanding about the fundamentals of machine learning and neural networks

[2] Enabling the students to acquire knowledge about pattern recognition.

[3] Motivating the students to apply deep learning algorithms for solving real life problems.
Course Outcomes (CO):

At the end of the course the student will be able to

[1] Comprehend the categorization of machine learning algorithms.

[2] Understand the types of neural network architectures, activation functions

[3] Acquaint with the pattern association using neural networks

[4] Explore various terminologies related with pattern recognition

[5] Adopt different feature selection and classification techniques

[6] Understand the architectures of convolutional neural networks

[7] Comprehend advanced neural network architectures such as RNN, Autoencoders, and GANs.

Module:1 Learning Problems and Algorithms 4 hours


Various paradigms of learning problems, Supervised, Semi-supervised and Unsupervised
algorithms

Module:2 Neural Network – I 6 hours


Differences between Biological and Artificial Neural Networks - Typical Architecture, Common
Activation Functions, Multi-layer neural network, Linear Separability, Hebb Net, Perceptron,
Adaline, Standard Back propagation

Module:3 Neural Network – II 6 hours


Training Algorithms for Pattern Association - Hebb rule and Delta rule, Hetero associative, Auto
associative, Kohonen Self Organising Maps, Examples of Feature Maps, Learning Vector
Quantization, Gradient descent, Boltzmann Machine Learning
Module:4 Machine Learning: Terminologies 7 hours

Classifying Samples: The confusion matrix, Accuracy, Precision, Recall, F1- Score, the curse
of dimensionality, training, testing, validation, cross validation, overfitting, under-fitting the
data, early stopping, regularization, bias and variance

Module:5 Machine Learning: Feature Selection and


Classification 6 hours
Feature Selection, normalization, dimensionality reduction, Classifiers: KNN, SVM, Decision
trees, Naïve Bayes, Binary classification, multi class classification, clustering.

Module:6 Convolutional Neural Networks 7 hours


Feed forward networks, Activation functions, backpropagation in CNN, optimizers, batch
normalization, convolution layers, pooling layers, fully connected layers, dropout, Examples
of CNNs.

Module:7 RNNs, Autoencoders and GANs 7 hours


State, Structure of RNN Cell, LSTM and GRU, Time distributed layers, Generating Text,
Autoencoders: Convolutional Autoencoders, Denoising autoencoders, Variational autoencoders,
GANs: The discriminator, generator, DCGANs

Module:8 Contemporary issues: 2 hours


Total Lecture hours: 45 hrs

Text Book(s)

3. J. S. R. Jang, C. T. Sun, E. Mizutani, Neuro Fuzzy and Soft Computing - A


Computational Approach to Learning and Machine Intelligence, 2012, PHI
learning
4. Deep Learning, Ian Good fellow, Yoshua Bengio and Aaron Courville, MIT Press,
ISBN: 9780262035613, 2016.
Reference Books
6. The Elements of Statistical Learning. Trevor Hastie, Robert Tibshirani and Jerome
Friedman. Second Edition. 2009.
7. Pattern Recognition and Machine Learning. Christopher Bishop. Springer. 2006.
8. Understanding Machine Learning. Shai Shalev-Shwartz and Shai Ben-David. Cambridge
University Press. 2017.

You might also like