2010 Jawaharlal Nehru Technological University, Hyderabad M.C.A JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD MCA-IV Semester Supplementary Examinations July/August 2010 ARTIFICIAL NEURAL NETWORKS Question paper
code No: 49
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD
MCA-IV Semester Supplementary Examinations July/August 2010
ARTIFICIAL NEURAL NETWORKS
Time: 3hours Max.Marks:60
Answer any Five questions
All questions carry equal Marks
- - -
1.a) Explain the characteristics of artificial neural networks.
b) Determine the weights of a network with 4 input and 2 output units using
Perception learning law for the following input-output pairs:
Input: [1 1 0 0] [1 0 0 1] [0 0 1 1] [0 1 1 0] T T T T
Output: [1 1]T [1 0]T [0 1]T [0 0]T
2.a) Explain an Activation and Synaptic dynamics models.
b) State and explain the Cohen-Grossberg-Kosko theorem.
3.a) With suitable example explain the LMS learning rule.
b) What are the applications of pattern recognition tasks? Explain.
4. Explain the structure of functional units. Explain how to solve pattern recognition
tasks using functional units.
5.a) Explain the general concept of associate memory. Define associate matrix.
b) Explain the associate rules.
c) Explain the hetero-associate memories.
6. Derive update equations for weight elements of multi-layer feed-forward neural
network. Explain its applicability for the problems of pattern recognition.
7.a) Explain the concepts of statistical mechanics.
b) Explain the basic architecture and processing of Boltzmann's machines.
c) Explain the CPN data processing.
8.a) Explain the architecture and processing algorithm of the ART2.
b) Explain the ART1 simulator.
c) Explain the SOM learning algorithm.
KEYWORDS:ARTIFICIAL NEURAL NETWORKS,ARTIFICIAL NEURAL NETWORKS QUESTION PAPER,JNTU,JNTU QUESTION PAPER,JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD MCA-IV SEMESTER SUPPLEMENTARY EXAMINATIONS JULY/AUGUST ARTIFICIAL NEURAL NETWORKS
code No: 49
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD
MCA-IV Semester Supplementary Examinations July/August 2010
ARTIFICIAL NEURAL NETWORKS
Time: 3hours Max.Marks:60
Answer any Five questions
All questions carry equal Marks
- - -
1.a) Explain the characteristics of artificial neural networks.
b) Determine the weights of a network with 4 input and 2 output units using
Perception learning law for the following input-output pairs:
Input: [1 1 0 0] [1 0 0 1] [0 0 1 1] [0 1 1 0] T T T T
Output: [1 1]T [1 0]T [0 1]T [0 0]T
2.a) Explain an Activation and Synaptic dynamics models.
b) State and explain the Cohen-Grossberg-Kosko theorem.
3.a) With suitable example explain the LMS learning rule.
b) What are the applications of pattern recognition tasks? Explain.
4. Explain the structure of functional units. Explain how to solve pattern recognition
tasks using functional units.
5.a) Explain the general concept of associate memory. Define associate matrix.
b) Explain the associate rules.
c) Explain the hetero-associate memories.
6. Derive update equations for weight elements of multi-layer feed-forward neural
network. Explain its applicability for the problems of pattern recognition.
7.a) Explain the concepts of statistical mechanics.
b) Explain the basic architecture and processing of Boltzmann's machines.
c) Explain the CPN data processing.
8.a) Explain the architecture and processing algorithm of the ART2.
b) Explain the ART1 simulator.
c) Explain the SOM learning algorithm.
KEYWORDS:ARTIFICIAL NEURAL NETWORKS,ARTIFICIAL NEURAL NETWORKS QUESTION PAPER,JNTU,JNTU QUESTION PAPER,JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD MCA-IV SEMESTER SUPPLEMENTARY EXAMINATIONS JULY/AUGUST ARTIFICIAL NEURAL NETWORKS