DS4003 Neural Networks and Applications Syllabus:

DS4003 Neural Networks and Applications Syllabus – Anna University PG Syllabus Regulation 2021

COURSE OBJECTIVES:

 To introduce neural networks as means for computational learning.
 To present the basic network architectures for classification and regression
 To provide knowledge of computational and dynamical systems using neural networks,
 To perform algorithmic training of various neural networks.
 To understand training and limitations of learning self organizing systems

UNIT I BASIC LEARNING ALGORITHMS

Biological Neuron – Artificial Neural Model – Types of activation functions – Architecture: Feed forward and Feedback – Learning Process: Error Correction Learning –Memory Based Learning – Hebbian Learning – Competitive Learning – Boltzmann Learning – Supervised and Unsupervised Learning – Learning Tasks: Pattern Space – Weight Space – Pattern Association – Pattern Recognition – Function Approximation – Control – Filtering – Beamforming – Memory – Adaptation – Statistical Learning Theory – Single Layer Perceptron – Perceptron Learning Algorithm – Perceptron Convergence Theorem – Least Mean Square Learning Algorithm – Multilayer Perceptron – Back Propagation Algorithm – XOR problem – Limitations of Back Propagation Algorithm.

UNIT II RADIAL-BASIS FUNCTION NETWORKS AND SUPPORT VECTOR MACHINES

Cover’s Theorem on the Separability of Patterns – Exact Interpolator – Regularization Theory – Generalized Radial Basis Function Networks – Learning in Radial Basis Function Networks Applications: XOR Problem – Image Classification. Optimal Hyperplane for Linearly Separable Patterns and Nonseparable Patterns – Support Vector Machine for Pattern Recognition – XOR Problem -insensitive Loss Function –Support Vector Machines for Nonlinear Regression.

UNIT III COMMITTEE MACHINES AND NEURODYNAMICS SYSTEMS

Ensemble Averaging – Boosting – Associative Gaussian Mixture Model – Hierarchical Mixture of Experts Model(HME) – Model Selection using a Standard Decision Tree – A Priori and Posteriori Probabilities – Maximum Likelihood Estimation – Learning Strategies for the HME Model – EM Algorithm – Applications of EM Algorithm to HME Model. Dynamical Systems – Attractors and Stability – Non-linear Dynamical Systems- Lyapunov Stability – Neurodynamical Systems – The Cohen Grossberg T theorem.

UNIT IV ATTRACTOR NEURAL NETWORKS AND ADAPTIVE RESONANCE THEORY

Associative Learning – Attractor Neural Network Associative Memory – Linear Associative Memory – Hopfield Network – Content Addressable Memory – Strange Attractors and Chaos- Error Performance of Hopfield Networks – Applications of Hopfield Networks – Simulated Annealing – Boltzmann Machine – Bidirectional Associative Memory – BAM Stability Analysis – Error Correction in BAMs – Memory Annihilation of Structured Maps in BAMS – Continuous BAMs – Adaptive BAMs – Applications. Noise Saturation Dilemma – Solving Noise-Saturation Dilemma – Recurrent On-center – Off surround Networks – Building Blocks of Adaptive Resonance – Adaptive Resonance Theory – Applications.

UNIT V SELF ORGANISING MAPS AND PULSED NEURON MODELS

Self-organizing Map – Maximal Eigenvector Filtering – Sanger’s Rule – Generalized Learning Law – Competitive Learning – Vector Quantization – Mexican Hat Networks – Self – organizing Feature Maps – Applications. Spiking Neuron Model – Integrate-and-Fire Neurons – Conductance Based Models – Computing with Spiking Neurons.

TOTAL:45 PERIODS

COURSE OUTCOMES:

CO1:deduce the basic Computational Algorithms
CO2:explore mathematical based computational Algorithms
CO3:knowledge of computational and dynamical systems using neural networks,
CO4:perform algorithmic training of various neural networks and training of learning self organizing systems
CO5:understand Use different methods for the various applications

REFERENCES

1. James A. Freeman and David M. Skapura, “Neural Networks Algorithms, Applications, and Programming Techniques, Pearson Education (Singapore) Private Limited, Delhi,2003.
2. Martin T.Hagan, Howard B. Demuth, and Mark Beale, “Neural Network Design”, Thomson Learning, New Delhi, second edition 2014.
3. Satish Kumar, “Neural Networks: A Classroom Approach”, Tata McGraw-Hill Publishing Company Limited, New Delhi, 2017.
4. Simon Haykin, “Neural Networks: A Comprehensive Foundation”, 2ed., Addison Wesley Longman (Singapore) Private Limited, Delhi, 2001.

Related posts:

  1. RS4004 GIS Applications Syllabus
  2. AO4202 CFD for Aerospace Applications Syllabus
  3. MX4001 Nanotechnology and its Applications Syllabus
  4. SF4002 Geology for Geotechnical Applications Syllabus
  5. SF4009 Rock Mechanics and Applications Syllabus
  6. ED4153 Computer Applications in Design Syllabus
  7. DS4072 Wavelet Transforms and Applications Syllabus
  8. CS8591 Computer Networks Syllabus
  9. EC3401 Networks and Security Syllabus
  10. EL4391 Optical Networks Syllabus
  11. NC4003 Broadband Networks Syllabus
  12. RS4006 Disaster Management and Geomatics Applications Syllabus
  13. ET4017 Embedded System for Biomedical Applications Syllabus
  14. AP4001 Applications Specific Integrated Circuits Syllabus
  15. MX4074 Pattern Recognition Techniques and Applications Syllabus
  16. CU4202 Advanced Wireless Networks Syllabus
  17. NC4251 Cognitive Radio Networks Syllabus
  18. MP4003 Body Area Networks Syllabus
  19. NC4101 High Performance Networks Syllabus
  20. NC4004 Virtual Private Networks Syllabus