Given the following neural network: model3=Sequential() model3.add(layers. Conv1D(filters=1, kernel_size=2, strides=1, padding='same', input_shape=(785,1), , activation='sigmoid')) model3.add(layers. Flatten()) model3.add(layers.Dense(1, activation='sigmoid')) Let the outputs of the layers in the network be denoted using X,c(X), 0;(X) for the INPUT, CONV1 and OUTPUT layers respectively where i is the index of the neuron in the layer. You may use those without explicitly calculating them. In addition the weights can be denoted w, w for the CONV1 and OUTPUT layers respectively. The learning rate is set to a. Given a labeled datapoint (r,y), show how you would calculate the following: (a) The update to the weight i of the output node layer. (b) The update to the bias of the output node layer. (c) The update to the weights we, w of the convolutional layer. (d) The update to the bias of the convolutional layer. Given the following neural network: model3=Sequential() model3.add(layers. Conv1D(filters=1, kernel_size=2, strides=1, padding='same', input_shape=(785,1), , activation='sigmoid')) model3.add(layers. Flatten()) model3.add(layers.Dense(1, activation='sigmoid')) Let the outputs of the layers in the network be denoted using X,c(X), 0;(X) for the INPUT, CONV1 and OUTPUT layers respectively where i is the index of the neuron in the layer. You may use those without explicitly calculating them. In addition the weights can be denoted w, w for the CONV1 and OUTPUT layers respectively. The learning rate is set to a. Given a labeled datapoint (r,y), show how you would calculate the following: (a) The update to the weight i of the output node layer. (b) The update to the bias of the output node layer. (c) The update to the weights we, w of the convolutional layer. (d) The update to the bias of the convolutional layer