Scribd Logo
Upload

Welcome to Scribd!

  • 207 views

    Introduction To Soft Computing: Practice Sheet: NN-1

    Uploaded by

    Ibrahim Anis
    An ANN learns quickly if the learning rate (ŋ) is less than 1. The training time of a neural network depends on its size, and neural networks can be simulated on a computer. Backpropagation is the transmission of error back through the network to allow weights to be adjusted so the network can learn. Neural networks are complex nonlinear functions with many parameters. Multilayer feedforward neural networks can be used to solve problems involving error calculation. Applications of neural networks include pattern recognition, classification, and clustering. A perceptron is a single layer feedforward neural network with preprocessing.

    Copyright:

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

    Introduction To Soft Computing: Practice Sheet: NN-1

    Uploaded by

    Ibrahim Anis
    207 views2 pages
    An ANN learns quickly if the learning rate (ŋ) is less than 1. The training time of a neural network depends on its size, and neural networks can be simulated on a computer. Backpropagation is the transmission of error back through the network to allow weights to be adjusted so the network can learn. Neural networks are complex nonlinear functions with many parameters. Multilayer feedforward neural networks can be used to solve problems involving error calculation. Applications of neural networks include pattern recognition, classification, and clustering. A perceptron is a single layer feedforward neural network with preprocessing.

    Original Description:

    best to study

    Original Title

    PS-NN-1

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    An ANN learns quickly if the learning rate (ŋ) is less than 1. The training time of a neural network depends on its size, and neural networks can be simulated on a computer. Backpropagation is the transmission of error back through the network to allow weights to be adjusted so the network can learn. Neural networks are complex nonlinear functions with many parameters. Multilayer feedforward neural networks can be used to solve problems involving error calculation. Applications of neural networks include pattern recognition, classification, and clustering. A perceptron is a single layer feedforward neural network with preprocessing.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    207 views2 pages

    Introduction To Soft Computing: Practice Sheet: NN-1

    Uploaded by

    Ibrahim Anis
    An ANN learns quickly if the learning rate (ŋ) is less than 1. The training time of a neural network depends on its size, and neural networks can be simulated on a computer. Backpropagation is the transmission of error back through the network to allow weights to be adjusted so the network can learn. Neural networks are complex nonlinear functions with many parameters. Multilayer feedforward neural networks can be used to solve problems involving error calculation. Applications of neural networks include pattern recognition, classification, and clustering. A perceptron is a single layer feedforward neural network with preprocessing.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    Introduction to Soft Computing

    Practice Sheet: NN-1


    Introduction to ANN

    1) An ANN learn quickly if ŋ, the learning rate assumes the following value(s).

    (a) ŋ=1
    (b) ŋ<1
    (c) ŋ>1
    (d) ŋ=0

    2) Which of the following is true for neural networks?


    i. The training time depends on the size of the network.
    ii. Neural networks can be simulated on a conventional computer.
    iii. Artificial neurons are identical in operation to biological ones.

    (a) i and ii are true


    (b) i and iii are true
    (c) ii is true.
    (d) all of them are true

    3) Which of the following is true for neural networks?


    i. The error calculation which is followed in “Back-propagation algorithm” is the
    steepest descent method.
    ii. Simulated annealing approach is followed in unsupervised learning.
    iii. A problem whose output is linearly separable can also be solved with MLFFNN.
    iv. The output of the perceptron with hard limit transfer function is more accurate than
    it is defined with any sigmoid transfer function.

    (a) i and iii are true


    (b) i and ii are true
    (c) ii and iv are true
    (d) all are true

    4) A possible neuron specification to solve the AND problem requires a minimum of


    (a) Single neuron
    (b) Two neurons
    (c) Three neurons
    (d) Four neurons

    5) What is back propagation?


    (a) It is another name given to the curvy function in the perceptron
    (b) It is the transmission of error back through the network to adjust the inputs
    (c) It is the transmission of error back through the network to allow weights to be
    adjusted so that the network can learn
    (d) None of the above
    6) Neural Networks are complex ______________ with many parameters
    (a) Linear Functions
    (b) Nonlinear Functions
    (c) Discrete Functions
    (d) Exponential Functions

    7) For problems, with error calculation, we solve using


    (a) Recurrent neural networks
    (b) Single layer feed forward neural network
    (c) Multilayer feed forward neural network
    (d) All of the above

    8) Application of Neural Network includes


    (a) Pattern Recognition
    (b) Classification
    (c) Clustering
    (d) All of the above

    9) If an individual 𝑥𝑖 is dominated by 𝑝𝑖 individuals in the current generation, then


    𝑟𝑎𝑛𝑘(𝑥𝑖 ) is

    (a) 0
    (b) 𝑝𝑖
    (c) 1
    (d) 1 + 𝑝𝑖

    10) What is perceptron in Neural network

    (a) It is an auto-associative neural network


    (b) It is a double layer auto-associative neural network
    (c) It is a single layer feed-forward neural network with pre-processing
    (d) It is a neural network that contains feedback

    You might also like