Scribd
Upload
5 views1 page

Course-Topics-for-EEE-511

EEE511 is a course on artificial neural networks (ANN) focusing on engineering aspects and statistical machine learning. It covers a range of topics including perceptrons, multilayer perceptrons, support vector machines, self-organizing maps, and various optimization methods. The course aims to provide a comprehensive overview of ANN principles and their applications in solving complex problems.

Uploaded by

Nitish Jolly
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
5 views1 page

Course-Topics-for-EEE-511

EEE511 is a course on artificial neural networks (ANN) focusing on engineering aspects and statistical machine learning. It covers a range of topics including perceptrons, multilayer perceptrons, support vector machines, self-organizing maps, and various optimization methods. The course aims to provide a comprehensive overview of ANN principles and their applications in solving complex problems.

Uploaded by

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

EEE511: Artificial Neural Computation

PREREQUISITES:
Signals and systems, random signal analysis, linear systems, or instructor approval

COURSE DESCRIPTION
This course covers the principles of artificial neural networks (ANN), collective computational
phenomena emerging from simple interconnected elements. Biological neural motivation will be
introduced. However, the course emphasis is on "artificial" with a focus on engineering aspects of the
field. Our approach is based on engineering systems theory and statistical machine learning. We
address how do we make a network of neuron-like elements learn from a set of data that is
representative of the problem, to solve complex problems in life, such as pattern classification
(speech recognition, and target recognition), function approximation and system identification, control
of a robot or a plant, or anything else among a myriad of possible applications. Our purpose is to
obtain a coherent overview of the field, an ability to find and digest deeper knowledge in any
particular subfield, and most importantly, ability to apply an appropriate type of an ANN model to a
given problem.

COURSE TOPICS
 Introduction of ANN, inspirations from biological neural networks, neuron models, relations to
other disciplines, applications, motivating demonstrations
 Perceptrons, historical significance in learning, convergence theorem, perceptron vs. statistical
pattern recognition
 Single layer networks and unconstrained optimization methods, Single layer networks: LMS,
LMS vs. Wiener filter
 Multilayer perceptrons and back-propagation
 Representational capabilities of MLPs, training issues
 Generalization, overfitting with multilayer networks
 Regularization, Cross-Validation
 Optimization methods for MLPs
 Regularization theory
 Radial basis function networks, Introduction, Exact interpolation
 Radial basis function networks, Regularization, Model selection
 Radial basis function networks, Learning basis functions
 Support vector machines, introduction
 Support vector machines: Separable and nonseparable cases
 Support vector machines: More on VC-dimension, the kernel trick
 Support vector machines: Regression, examples
 The self-organizing map, Introduction, The basic algorithm
 The self-organizing map, Some example applications, Analysis of the algorithm
 The self-organizing map, Variants of SOMs
 The self-organizing map: Tree-Structurd SOMs, Applications in optimization.
 Learning vector quantization, principal-component analysis
 Information theoretic learning
 Stochastic optimization methods
 Dynamic Programming and Reinforcement learning
 Temporal processing with feedforward networks
 Filtering of stochastic processes
 Neurodynamics and Recurrent networks

You might also like