After initialization, we found our convolutional neural network’s training loss does not go down, list 2 ways to fix this problem, briefly explain each. (

1) design an artificial neural network with two inputs (X1 and X2). She won't have the bias. This network will have a hidden layer with two neurons (N1 and N2), plus an output layer, with one neuron (N3). The output of the network is called Y. Make the weights (W's) of each neuron explicit in the network, as well as the interconnections between all parts of the ANN.

do not copy from internet

Assume that we have a neuron Y which accepts inputs from neurons X1, X2, X3,X4 Let's symbolize byW1, W2, W3,W4 Weights for interconnections between Y and X1, X2, X3 Using MATLAB program toDefine and custom Artificial Neural network (ANN) , compute and plot neuron output .(using LinearFunction and Bipolar Sigmoid and 3D plotting)When:-