question is given in the image.Please do no use other websites(coursehero,etc) or chatgpt to solve.other solutions given for this were wrong.

n 1 Gradient back-propagation technique is one of the fundamental algorithms for training feedforward neural networks. Using the chain rule, this algorithm calculates the gradient of the loss function at different layers of the network. In subsequent stages, computed gradients will be used to update weights with optimizers such as gradient descent or stochastic gradient descent to minimize a loss function. In this question, we want to drive an expression for the gradient of a cost function with respect to the weights and biases of a simple neural network. Consider a 1-hidden layer neural network as follows where xRN1 is the input feature vector and yR is the network output. The network's weights are W1RNM and w2RM, biases are b1RM and b2R and activation function . (a) Following the Neural Network lecture from your course, derive the feedforward equation that maps the input to the output i.e. y=f(x;), where ={W1,w2,b1,b2} is the set of all learnable parameters. (b) Consider a cost function J=B1i=1Bl(y^i,yi),wherel(y^,y)=(y^y)2, where B is the batch size for optimization. Using the chain-rule, derive the expressions for the following gradients w1J,w2J,b1J,b2J