Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 82 views

    PS NN 2

    Uploaded by

    Tapas Kumar
    This document discusses artificial neural networks (ANNs) and their applications. It provides multiple choice questions about ANN training techniques, including supervised training with error correction being the fastest method. Hebbian learning is a form of unsupervised learning. Backpropagation is used to train multi-layer feedforward neural networks. ANNs are examples of soft computing techniques as they do not require precise mathematical models.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    PS NN 2

    Uploaded by

    Tapas Kumar
    82 views3 pages
    This document discusses artificial neural networks (ANNs) and their applications. It provides multiple choice questions about ANN training techniques, including supervised training with error correction being the fastest method. Hebbian learning is a form of unsupervised learning. Backpropagation is used to train multi-layer feedforward neural networks. ANNs are examples of soft computing techniques as they do not require precise mathematical models.

    Original Title

    PS-NN-2

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses artificial neural networks (ANNs) and their applications. It provides multiple choice questions about ANN training techniques, including supervised training with error correction being the fastest method. Hebbian learning is a form of unsupervised learning. Backpropagation is used to train multi-layer feedforward neural networks. ANNs are examples of soft computing techniques as they do not require precise mathematical models.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    82 views3 pages

    PS NN 2

    Uploaded by

    Tapas Kumar
    This document discusses artificial neural networks (ANNs) and their applications. It provides multiple choice questions about ANN training techniques, including supervised training with error correction being the fastest method. Hebbian learning is a form of unsupervised learning. Backpropagation is used to train multi-layer feedforward neural networks. ANNs are examples of soft computing techniques as they do not require precise mathematical models.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    Introduction to Soft Computing

    Practice Sheet: NN-2

    Training of ANNs and Applications of ANNs

    1. For the same size of training data as input, the fastest learning techniques
    is

    (a) Supervised training with error correction.


    (b) Supervised training with stochastic method.
    (c) Supervised training without error calculation.
    (d) Supervised training with Hebbian method.

    2. Hebbian learning is a form of

    (a) Supervised Learning


    (b) Unsupervised learning
    (c) Reinforced learning
    (d) Stochastic learning

    3. In case of layer calculation, the maximum time involved in

    (a) Output layer computation.


    (b) Hidden layer computation.
    (c) Equal effort in each layer.
    (d) Input layer computation.

    4. The Back Propagation Learning algorithm is used to train

    (a) a single layer feed forward neural network only


    (b) a multiple layer feed forward neural network only
    (c) a recurrent neural network only
    (d) any artificial neural network

    5. In this learning method, those neurons which responds strongly to input


    stimuli have their weights updated

    (a) Competitive learning


    (b) Stochastic Learning
    (c) Hebbian Leaning
    (d) Gradient Descent Learning

    6. Training Perceptron is based on

    (a) Supervised learning technique.


    (b) Unsupervised learning
    (c) Reinforced learning
    (d) Stochastic learning

    7. A batch mode of training is generally implemented through the


    _______________________ in error calculation

    (a) Minimization of median square error


    (b) Maximization of median square error
    (c) Maximization of mean square error
    (d) Minimization of mean square error

    8. Command to start matlab fuzzy toolbox is

    (a) fis
    (b) fuzzy
    (c) fuzzybox
    (d) fuzzytool

    9. Which of the following is not a hybrid system?

    (a) Embedded hybrid system


    (b) Sequential hybrid system
    (c) Auxiliary hybrid system
    (d) Parallel hybrid system

    10.In which of the following, one technology calls the other technology as
    subroutine to process or manipulate information needed

    (a) Embedded hybrid system


    (b) Sequential hybrid system
    (c) Auxiliary hybrid system
    (d) Parallel hybrid system

    11. Fuzzy – Genetic Hybrid system is a

    (a) Fuzzy logic in parallel with the Genetic algorithm


    (b) Fuzzy logic controlled Genetic algorithm
    (c) Genetic algorithm controlled Fuzzy logic
    (d) None of the above

    𝜕𝐸
    12.In Supervised learning − 𝑣𝑒 sign is used to signify the fact that if > 0,
    𝜕𝑉
    then we have to

    (a) Increase V
    (b) Decrease V
    (c) Increase E
    (d) Decrease E

    13. Both fuzzy logic and artificial neural network are soft computing
    techniques because,

    (a) Both gives precise and accurate results.


    (b) Artificial neural network gives accurate result but fuzzy logic
    does not.
    (c) In each, no precise mathematical model of the problem is
    required.
    (d) Fuzzy gives exact result but artificial neural network does
    not.

    14.In supervised learning, training set of data includes

    (a) Input
    (b) Output
    (c) Both input and output
    (d) None

    You might also like