
	Trending ▼ ICSE CBSE 10th ISC CBSE 12th CTET GATE UGC NET Vestibulares ResFinder

2003 Course ANN & It's Application in Electrical Eng.

3 pages, 23 questions, 0 questions with responses, 0 total responses,

	pune_eng	+Fave Message
	Profile Timeline Uploads Q & A

Home > pune_eng >

Instantly get Model Answers to questions on this ResPaper. Try now!
NEW ResPaper Exclusive!

Formatting page ...

Total No. of Questions : 12] [Total No. of Pages : 3 [3864] - 236 P 1068 B.E. (Electrical) ANN & IT S APPLICATION IN ELECTRICAL ENGG. (2003 Course) Time : 3 Hours] [Max. Marks : 100 Instructions to the candidates: 1) Answer 3 questions from Section I and 3 questions from Section II. 2) Answers to the two sections should be written in separate books. 3) Neat diagrams must be drawn wherever necessary. 4) Figures to the right indicate full marks. 5) Your answers will be valued as a whole. SECTION - I Q1) a) b) c) Define Artificial intelligence. [2] List Activation function with input, output limit. [8] What are the different architecture neural network, explain any one in detail with neat sketch. [8] OR Q2) a) b) Q3) a) b) Write the topology for a simple model of an artificial neural network mimic with human brain. [10] Compare, knowledge based system, fuzzy system, ANN and evolution computing. [8] Draw Hebbian Network and Hence discuss it s advantages & drawbacks in learning the Neural Nets. [8] Explain in detail about learning tasks. [8] OR Q4) a) b) Explain Transfer function shown in fig 4.1. Explain it s applicability with example. [8] Write in detail about learning without teacher. [8] P.T.O. Q5) a) b) c) Draw single layer feedforward N/W with four inputs and three outputs. [4] Draw perceptron architecture and hence discuss about role of weight matrix. [6] Write short notes on learning curves. [6] OR Q6) a) b) What are the learning rate Annealing techniques. [6] 1 0.5 P 0 = [1 0.2 0.5] ; W = 0.5 1 ; b = 0.5 apply perceptron network 1 2 to get target output 0 for apple and target output 1 for mango. T Train with P1 = [ 0.8 0.7 0.2 ] P 2 = [ 0.5 0.6 0.4 ] P 3 = [ 0.2 0.9 0.6 ] [10] SECTION - II Q7) Consider five training sets as shown in table 1. Table 1 - Training sets Sr. Inputs Outputs I2 O No. I1 1 0.4 0.7 0.1 2 0.3 0.5 0.05 3 0.6 0.1 0.3 4 0.2 0.4 0.25 5 0.1 0.2 0.12 Draw MFNN architectures. Find the updated weights if initially 0.1 0.4 0.2 V0 = W0 = ; 0.2 0.2 0.5 Assume = 0.6 . [16] OR Q8) a) b) Explain Back-propagation learning with Input, Hidden and Output layer computations. [8] Explain method of steppest descent. How it is used to evaluate learning rate coefficient. [8] [3864] - 236 -2- Q9) Write short notes with neat sketches and their learning / training set for the following : [18] a) Recurrent Network. b) Hopfield Network. OR Q10)a) b) Define the term resonance and hence give the details of cluster structure in Adoptive Resonance theory with the help of vector quantization.[10] Draw and explain architecture of ART1. [8] Q11)Develop algorithms in back-propagation to learn and train Neural Network for the reactive power dispatch program in the feeder substation of 33 KV with 50 MW balanced linear loud. KvAr varies between 0 to 16 MvAr in each feeder. [16] OR Q12)Considering radial distribution system with five branches, develop algorithm for service restoration and hence apply Hebbian learning Neural Network to verify service restoration algorithm to find optimization of sectionalizing switches connected between branches. [16] [3864] - 236 -3-

Formatting page ...

Tags : Pune, Engineering, University of Pune, Engineering question papers, Pune University, previous year question papers, question papers, india, model question paper, pune university paper pattern, pune university syllabus, old question papers

pune_eng chat

Horizontal lines at:
Guest Horizontal lines at:
AutoRM Data:
Box geometries: