2007 Anna University Chennai B.E Biomedical Engineering Neural Networks Question paper for exam preparation. Question paper for 2007 Anna University Chennai B.E Biomedical Engineering Neural Networks Question paper, Exam Question papers 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2012 university in india question papers. SiteMap
K2Questions Logo


2007 Anna University Chennai B.E Biomedical Engineering Neural Networks Question paper

University Question Papers
2007 Anna University Chennai B.E Biomedical Engineering Neural Networks Question paper
<span id="ContentPlaceHolder1_lblDescription">B.E. BIOMEDICAL ENGINEERING<br />
6TH SEM<br />
NEURAL NETWORKS<br />
MAX:100<br />
ANSWER THE FOLLOWING:<br />
<br />
<br />
PART A-(10*2=20)<br />
1. Draw the stimulated structure of a neuron.<br />
<br />
2. What is meant by learning rate parameter?<br />
<br />
3. How weights are initialized by BAM?<br />
<br />
4. Mention the special features of Boltzman machine.<br />
<br />
5. Draw any two activation functions.<br />
<br />
6. What is an instar?<br />
<br />
7. Compare ART 1 and ART 2 (any 2)<br />
<br />
8. State the significance of Mexican hat function in SOM.<br />
<br />
9. Define spatiotemporal pattern<br />
<br />
10. What are ‘S’ cells? <br />
PART-B (5*16 -80)<br />
<br />
11. (a) (i) Describe the biological neuron and brief the feature of artificial neural networks.<br />
<br />
(ii) Solve the EXOR problem with perceptron. <br />
<br />
(Or)<br />
<br />
(b) Explain the madaline architecture and describe the MR II learning algorithm. How madaline is used for translation invariant pattern recognition?<br />
<br />
12 (a) (i) Describe the learning expressions in the back propagation network.<br />
<br />
(ii) Describe the generalized delta rule.<br />
<br />
(Or)<br />
<br />
(b) Describe the structure and operation of continuous Hopfield network. &amp; Construct an autoassociative BAM using the following training vectors. X1 = (1,-1,-1,1,-1,1)t and x2 = (1,1,1,-1,-1,-1)t . Determine the output using xo =(1,1,1,1,-1,1)t <br />
<br />
13 (a) Describe the concept of simulated annealing. How this is applied in Boltzman machine to overcome the drawbacks of Hopfield network. Also ngive the procedure for retrieving the stored vector with partial knowledge in Boltzmann machine.<br />
<br />
. (Or)<br />
<b


About us | SiteMap | Terms of use | Privacy Policy | Disclaimer | Contact us | ©2010 K2Questions.com