Suppose your input is a 300 by 300 color (RGB) image, and you use a convolutional layer with 100 filters that are each 5x5. How many parameters does this hidden layer have (without bias)

• 2501

• 2600

• 7500

• 7600

You have an input volume that is 63x63x16, and convolve it with 32 filters that are each 7x7, using a stride of 2 and no padding. What is the output volume?

• 16x16x32

• 29x29x16

• 29x29x32

• 16x16x16

You have an input volume that is 15x15x8, and pad it using “pad=2.” What is the dimension of the resulting volume (after padding)?

• 19x19x12

• 17x17x10

• 19x19x8

• 17x17x8

You have an input volume that is 32x32x16, and apply max pooling with a stride of 2 and a filter size of 2. What is the output volume?

• 15x15x16

• 16x16x16

• 32x32x8

• 16x16x8

The most suitable activation function for hidden layer

• Sigmoid

• Softmax

• ReLu

• tanh

When an ENTIRE dataset is passed forward and backward through the neural network only ONCE.

• One epoch

• One batch

• One iteration

exploit spatially-local correlation by enforcing a local connectivity pattern between neurons of adjacent layers.

• RNN or Recurrent Neural Network

• CNN or Convolution Neural Network

• LSTMor Long-Short Term Memory

Your feedback is very important to improve the sessions. Thank you so much for attending the day-1 session.