Question

Machine learning Neural Networks question:

Which of the following statements is (are) true about neural networks? There may be multiple correct statements, please give a reason why they are true or false
(A) The training time depends on the size of the network as well as the training data.
(B)The perceptron is a single layer recurrent neural network.
(C) In image processing, compared with fully connected networks, usually convolutional networks are preferred.
(D) Neural network cannot be used for solving Regression problems.

Answer 1

(A) The training time depends on the size of the network as well as the training data.:TRUE

training time depends on both the factors size of network and training data

(B)The perceptron is a single layer recurrent neural network.:FALSE

The perceptron is a single layered feed-forward neural network not single layer recurrent neural network

(C) In image processing, compared with fully connected networks, usually convolutional networks are preferred.:TRUE

In a fully connected layer, each neuron receives input from every element of the previous layer. In a convolutional layer, neurons receive input from only a restricted subarea of the previous layer.

convolution in neural networks is operation of finding patterns. It has kernel that with which it basically scan an image and place where kernel have 100% match is a place where pattern matched. And thus convolutional network are preffered

(D) Neural network cannot be used for solving Regression problems.:FALSE

Neural network can be used to solve the linear regression problem.neural network are reducible to regression model it can pretend to be any type of regression model

for example neural network with one input neuron one hidden neuron one output neuron is equivqlent to linear regression