Artificial Neural Networks Mid - II, April - 2015

1.Hessian Matrix is will support to study of neural networks specially for _____
  • Pruning
  • Second order
  • Optimization
  • Above ALL
Answer: D
2.The Learning process may be viewed as a ______ problem.
  • Curve-cutting
  • Curve-Fitting
  • Over-Fitting
  • Over Training
Answer: B
3.When a Network is ______, it loses the ability to generalize between similar input-output patterns.
  • Over trained
  • Curve-trained
  • Cost fitting
  • Above ALL
Answer: A
4.The ____ curve decreases monotonically to a minimum, it then start to increase as the training continues.
  • Early stopping point
  • training sample
  • validation learning
  • None
Answer: C
5.A neural network with minimum size is likely to learn _____
  • Idiosyncrasies
  • noise in the trained data
  • Generalize better to new data
  • Above ALL
Answer: D
6.In _____, the winning neuron determines the spatial location of a topological neighbourhood of exited neurons.
  • Competition
  • Synaptic adaptation
  • Cooperation
  • Above ALL
Answer: C
7.The ____ is importance because it provides a visual tool for analyzing the dynamics of a non-linear system.
  • State space
  • Lipschitz condition
  • Divergence theorem
  • Lyapunov’s theorem
Answer: A
8.Computational benefit of back propagation learning is/are ______
  • Sensitivity analysis
  • Efficiency
  • Robustness
  • Above ALL
Answer: D
9.In order to study of neuro dynamics, we need a _____ model.
  • Computational
  • Mathematical
  • Scientific
  • Above ALL
Answer: B
10.The training set is partitioned in to _____
  • Essential subset
  • Validation subset
  • Validate the model
  • Above ALL
Answer: D
11.____________________ is a specific technique for implementing gradient descent in weight space for a multilayer feed forward network.
Answer: Back propagation
12.SOM stands ____________________________
Answer: Self Organizing Map
13.A Vector quantizer with minimum encoding distortion is called a ________________
Answer: Voronoi
14.The Back propagation algorithm is an example of _________________ paradigm.
Answer: Connectionist
15.Codebook members are called ________________
Answer: Code words
16.In ________________ , every learning rate parameter should be allowed to vary from one iteration to the next.
Answer: Heuristic2
17.A Neuro dynamical system is ________________, in fact it is essential to create a universal computing machine.
Answer: Non-Linearity
18.The _________________ network consists of a set of neurons and a corresponding set of unit delays, forming a multiple loop feedback system.
Answer: Hop field
19.Hop field network is used in the experiment consists of N =120 neurons, therefore it has ________________ weights.
Answer: 12,280
20.A major limitation of the Hopfield network is that its ________________ capacity must be maintained small for the fundamental memories to be recoverable.
Answer: Storage