Scribd
Upload
13 views3 pages

Csen3011 Ann

This document outlines the course details for an Artificial Neural Networks course offered as part of a Computer Science and Engineering degree program. The course introduces students to the architecture, learning algorithms, and applications of various neural networks. It covers topics like backpropagation, common neural network architectures, shallow neural networks, deep neural networks, attractor neural networks, and self-organizing feature maps. The course aims to help students understand the concepts and techniques of different neural networks and apply them to real-world problems.

Uploaded by

Durgadevi Paramasivam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
13 views3 pages

Csen3011 Ann

This document outlines the course details for an Artificial Neural Networks course offered as part of a Computer Science and Engineering degree program. The course introduces students to the architecture, learning algorithms, and applications of various neural networks. It covers topics like backpropagation, common neural network architectures, shallow neural networks, deep neural networks, attractor neural networks, and self-organizing feature maps. The course aims to help students understand the concepts and techniques of different neural networks and apply them to real-world problems.

Uploaded by

Durgadevi Paramasivam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Department of Computer Science and Engineering (AIML), GITAM Deemed to be University

L T P S J C
CSEN3011 ARTIFICIAL NEURAL NETWORKS
3 0 2 0 0 4
Pre-requisite MATH2291:Linear Algebra
Co-requisite CSEN2031:Artificial Intelligence
Preferable None
exposure

Course Description:
Artificial Neural Networks to be more precise, represent a technology that is rooted in many
disciplines: neurosciences, mathematics, statistics, physics, computer science and engineering.
ANN find applications in such diverse fields as modelling, time series analysis, pattern
recognition, signal processing and control by virtue of an important property: the ability to learn
from input data with or without a teacher.
Course Educational Objectives:
• To understand the architecture, learning algorithm and issues of various neural networks.
• Analyse ANN learning, Error correction learning, Memory-based learning, Competitive
learning and Boltzmann learning
• To adopt gradient - descent techniques in real time applications
• Provide knowledge on Generalization and function approximation and various
architectures of building an ANN
• Implement and learn the applications of Self-organization Map

UNIT 1 Introduction to Neural Networks 9 hours, P - 6 hours


Introduction, The Basic Architecture of Neural Networks, Training a Neural Network with
Backpropagation, Practical Issues in Neural Network Training, Common Neural Architectures.

UNIT 2 Shallow Neural Networks 9 hours, P - 6 hours


Neural Architectures for Binary Classification Models, Neural Architectures for Multiclass
Models, Autoencoder: Basic Principles, Neural embedding with continuous bag of words,
Simple neural architectures for graph embeddings

UNIT 3 Deep Neural Networks 9 hours, P - 6 hours


Introduction, Backpropagation, Setup and Initialization Issues, Gradient-Descent strategies,
the bias-variance trade-off, Generalization Issues in Model Tuning and Evaluation, Ensemble
Methods

B Tech. Computer Science and Engineering (AIML) w.e.f. 2021-22 admitted batch
Department of Computer Science and Engineering (AIML), GITAM Deemed to be University

UNIT 4 Attractor Neural Networks 9 hours, P - 6 hours


Associative Learning, Attractor Associative Memory, Linear Associative memory, Hopfield
Network, application of Hopfield Network, Brain State in a Box neural Network, Simulated
Annealing, Boltzmann Machine, Bidirectional Associative Memory.

UNIT 5 Self-organization Feature Map 9 hours, P - 6 hours


Maximal Eigenvector Filtering, Extracting Principal Components, Generalized Learning Laws,
Vector Quantization, Self-organization Feature Maps, Application of SOM.

Textbooks:
1. Neural Networks and Deep Learning - Charu C. Aggarwal, Springer International Publishing AG,
part of Springer Nature 2018 (Chapters 1, 2, 3)
2. Neural Networks A Classroom Approach– Satish Kumar, McGraw Hill Education (India) Pvt. Ltd,
Second Edition. (Chapters 4, 5)
References:
1. Neural Networks: A Comprehensive Foundation - Simon Haykin PHI, 2nd Edition 2005.
2. Introduction to Artificial Neural Systems-J.M. Zurada, Jaico Publications 1994.
3. Artificial Neural Networks-B. Yegnanarayana, PHI, New Delhi 1998.
Course Outcomes:
After successful completion of the course the student will be able to:
1. Understand the origin, ideological basics, Learning process and various Neural Architectures of
ANN.
2. Understand the concepts and techniques of Shallow neural networks through the study of
important neural network models.
3. Training Deep Neural Networks and Teaching Deep Learners to Generalize.
4. Apply Attractor neural networks to particular application.
5. Design a self-organizing system that are capable of extracting useful information from the
environment within which they operate.

B Tech. Computer Science and Engineering (AIML) w.e.f. 2021-22 admitted batch
Department of Computer Science and Engineering (AIML), GITAM Deemed to be University

CO-PO Mapping:
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 3 2 2 1 2 2 2 3
CO2 3 2 2 1 2 2 2 3
CO3 3 3 1 1 2 1 2 2 2 3
CO4 3 3 2 3 2 1 2 2 2 3
CO5 3 3 2 1 2 2 2 3

Note: 1 - Low Correlation 2 - Medium Correlation 3 - High Correlation

APPROVED IN:
BOS : 06-09-2021 ACADEMIC COUNCIL: 22nd AC (01-04-2022)

SDG No. & Statement:


SDGs: 3, 9
SDG:3 Good Health and Well-being
Statement: Artificial Neural Networks can be applied across all levels of health care
organizational decision-making. Influenced by advancements in the field, decision-makers are
taking advantage of hybrid models of neural networks in efforts to tailor solutions to a given
problem and well-being.
SDG:9 Industry, Innovation and Infrastructure
Statement: The holistic understanding of Artificial Neural Networks has lead to develop various
new models like CNN, RNN, RCNN, and GANs for achieving outstanding results on several
complex cognitive tasks, matching or even beating those provided by human performance

SDG Justification:

B Tech. Computer Science and Engineering (AIML) w.e.f. 2021-22 admitted batch

You might also like