Code No: R05411006 R05 Set No. 2Figure – 7b************2

Code No: R05411006 R05 Set No. 4Figure 1:IV B.Tech I Semester Examinations,December 2011ARTIFICIAL NEURAL NETWORKSCommon to Bio-Medical Engineering, Electronics And Telematics,Electronics And Instrumentation EngineeringTime: 3 hours Max Marks: 80Answer any FIVE QuestionsAll Questions carry equal marks⋆ ⋆ ⋆ ⋆ ⋆1. Explain the Widrow-Hoff learning rule for supervised learning in **neural** networkswith help of an example. Why is it sometimes called the LMS learning rule. [16]2. Explain about training and retrieval of Hopfield algorithm. [16]3. (a) Explain the classification of artificial **neural** networks(b) Explain the characteristics of artificial **neural** networks.(c) What are the popular nonlinear functions used in modeling artificial neuron?Explain each of them. [5+5+6]4. (a) Explain the architectures of Counter-Propagation Networks and their trainingalgorithms.(b) Consider the following full CPN shown in figure 4 using input pair x = (1, 1)y = (0, 1); perform first phase of training (one step only). Find the activationof the cluster layer units and update the weights using learning rates of 0.3.[8+8]5. (a) Explain the working of a Perceptron. Write the training algorithm of multicategory single layer Perceptron networks.(b) Explain about supervised and unsupervised training methods of artificial **neural**networks. [8+8]6. (a) Explain the steps in the solution of a general optimization problem by a **neural**network.(b) How an optimization problem formulated for solution using a **neural** networkModel? [8+8]23

Code No: R05411006 R05 Set No. 4Figure 42:(b) How an optimization problem formulated for solution using a **neural** networkmodel. [8+8]7. Explain Boltzmann machine algorithm and mention its applications. What are theissues in Boltzmann learning. [10+6]8. (a) Give a brief description of counter propagation network.(b) What are the two types of CPNs? Explain. [8+8]⋆ ⋆ ⋆ ⋆ ⋆43

Code No: R05411006 R05 Set No. 1IV B.Tech I Semester Examinations,December 2011ARTIFICIAL NEURAL NETWORKSCommon to Bio-Medical Engineering, Electronics And Telematics,Electronics And Instrumentation EngineeringTime: 3 hours Max Marks: 80Answer any FIVE QuestionsAll Questions carry equal marks⋆ ⋆ ⋆ ⋆ ⋆1. Explain the Widrow-Hoff learning rule for supervised learning in **neural** networkswith help of an example. Why is it sometimes called the LMS learning rule. [16]2. (a) Explain the classification of artificial **neural** networks(b) Explain the characteristics of artificial **neural** networks.(c) What are the popular nonlinear functions used in modeling artificial neuron?Explain each of them. [5+5+6]3. (a) Explain the steps in the solution of a general optimization problem by a **neural**network.(b) How an optimization problem formulated for solution using a **neural** networkmodel. [8+8]4. Explain about training and retrieval of Hopfield algorithm. [16]5. (a) Explain the working of a Perceptron. Write the training algorithm of multicategory single layer Perceptron networks.(b) Explain about supervised and unsupervised training methods of artificial **neural**networks. [8+8]6. Explain Boltzmann machine algorithm and mention its applications. What are theissues in Boltzmann learning. [10+6]7. (a) Explain the architectures of Counter-Propagation Networks and their trainingalgorithms.(b) Consider the following full CPN shown in figure 7b using input pair x = (1, 1)y = (0, 1); perform first phase of training (one step only). Find the activationof the cluster layer units and update the weights using learning rates of 0.3.[8+8]8. (a) Give a brief description of counter propagation network.(b) What are the two types of CPNs? Explain. [8+8]⋆ ⋆ ⋆ ⋆ ⋆54

Code No: R05411006 R05 Set No. 1Figure – 7b************6

Code No: R05411006 R05 Set No. 3Figure 3:IV B.Tech I Semester Examinations,December 2011ARTIFICIAL NEURAL NETWORKSCommon to Bio-Medical Engineering, Electronics And Telematics,Electronics And Instrumentation EngineeringTime: 3 hours Max Marks: 80Answer any FIVE QuestionsAll Questions carry equal marks⋆ ⋆ ⋆ ⋆ ⋆1. (a) Give a brief description of counter propagation network.(b) What are the two types of CPNs? Explain. [8+8]2. Explain Boltzmann machine algorithm and mention its applications. What are theissues in Boltzmann learning. [10+6]3. (a) Explain the steps in the solution of a general optimization problem by a **neural**network.(b) How an optimization problem formulated for solution using a **neural** networkmodel. [8+8]4. (a) Explain the working of a Perceptron. Write the training algorithm of multicategory single layer Perceptron networks.(b) Explain about supervised and unsupervised training methods of artificial **neural**networks. [8+8]5. (a) Explain the classification of artificial **neural** networks(b) Explain the characteristics of artificial **neural** networks.(c) What are the popular nonlinear functions used in modeling artificial neuron?Explain each of them. [5+5+6]6. Explain the Widrow-Hoff learning rule for supervised learning in **neural** networkswith help of an example. Why is it sometimes called the LMS learning rule. [16]7. Explain about training and retrieval of Hopfield algorithm. [16]57

Code No: R05411006 R05 Set No. 38. (a) Explain the architectures of Counter-Propagation Networks and their trainingalgorithms.(b) Consider the following full CPN shown in figure 8 using input pair x = (1, 1)y = (0, 1); perform first phase of training (one step only). Find the activationof the cluster layer units and update the weights using learning rates of 0.3.[8+8]Figure 8:⋆ ⋆ ⋆ ⋆ ⋆68