Scribd
Upload
168 views2 pages

ANN Updated Syllabus

The document discusses an advanced neural networks course. It covers 5 units - neural networks, Boltzmann machines, recurrent neural networks, belief networks, and modern statistical concepts. It provides course objectives, unit details, textbooks, reference books, course outcomes and mapping of outcomes to program outcomes and program specific outcomes.

Uploaded by

Sinthuja
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
168 views2 pages

ANN Updated Syllabus

The document discusses an advanced neural networks course. It covers 5 units - neural networks, Boltzmann machines, recurrent neural networks, belief networks, and modern statistical concepts. It provides course objectives, unit details, textbooks, reference books, course outcomes and mapping of outcomes to program outcomes and program specific outcomes.

Uploaded by

Sinthuja
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/ 2

IT1701 ADVANCED NEURAL NETWORK L T PC

3 0 0 3
OBJECTIVES
 To explain different network architectures and how these are used in current applications.
 To introduce major learning algorithms, the problem settings, and their applications to solve real
world problems.
 To understand the concept behind neural networks for learning non-linear functions
 To understand the role of neural networks in engineering, artificial intelligence, and cognitive
modeling.
UNIT I NEURAL NETWORKS 9
Introduction to Neural Networks - Multilayer Perceptron - Universal Approximation Theorem -
Estimation of Parameters- Gradient Descent- Stochastic Gradient Descent- ADAM-
CO1
Optimization Algorithms- CNN-Architecture- Back Propagation – Chain Rule- Hyper
Parameters

UNIT II BOLTZMANN MACHINES 9


Introduction to Boltzmann Machines, Contrastive Divergence (CD) in Restricted Boltzmann
Machines, Collaborative filtering using Boltzmann Machines, Deep Boltzmann Machines CO2

UNIT III RECURRENT NEURAL NETWORK 9


Recurrent Network Architectures -Backpropagation through time (BPTT) – Vanishing and
Exploding Gradients, Truncated BPTT, Gated Recurrent Unit- Long Short Term Memory
CO3
Networks (LSTM)

UNIT IV BELIEF NETWORKS 9


Introduction to Deep Belief Networks-Stacking RBMs to make Deep Belief Nets- Learning
Sigmoid Belief Nets - The wake-sleep algorithm- Mode Averaging CO4

UNIT V MODERN STATISTICAL CONCEPT 9


Model Free Confidence Interval- Jackknife Regression- Hidden Decision Trees- Bayesian
Networks- Better Goodness of Fit and Yield Metrics- R Squared -Akaike’s Information Criterion CO5
(AIC)

TOTAL : 45 PERIODS

TEXT BOOKS

1. Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2016.
2. Phil Kim, “MATLAB Deep Learning with Machine Learning, Neural Networks and Artificial
Intelligence”,Apress, 2017
REFERENCE BOOKS
1. Daniel Graupe,” Principles of Artificial Neural Networks”, World Scientific Publishing
Company;2013.
2. Yoav Goldberg,” Neural Network Models in Natural Language Processing”, Morgan &
Claypool,2017.
3. Simon O. Haykin,” Neural Networks and Learning Machines”, 3rd Edition. Prentice Hall, 2008.

COURSE OUTCOMES
Upon completion of the course, students will be able to
CO1 Identify the learning algorithms which are more appropriate for various types of learning tasks
in various domains
CO2 Implement, train, and evaluate neural networks using existing software libraries.
CO3 Present and critically assess current research on neural networks and their applications.
CO4 Analyze and predict various classification problem.
CO5 Apply neural networks to particular applications to know what steps to take to improve
performance.
MAPPING OF COs WITH POs AND PSOs
PROGRAM SPECIFIC
PROGRAM OUTCOMES (POs)
OUTCOMES (PSOs)
COs
PO PO PO PO PO PO PO PO PO PO PO PO
PSO1 PSO2 PSO3
1 2 3 4 5 6 7 8 9 10 11 12
CO1 1 1 1 1 1 1 1 2 1 1 1 2 2 2 2

CO2 2 2 1 2 2 1 1 2 1 1 1 2 2 2 2

CO3 2 2 2 2 2 `1 1 2 1 1 1 2 2 2 2

CO4 2 2 2 2 2 1 1 2 1 1 1 2 2 2 2

CO5 2 2 2 2 2 1 1 2 1 1 1 2 2 2 2

You might also like