APPLICATION OF SUPERVISED LEARNING
NEURAL NETWORK
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
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
|
|
|
None of the above
|
Explanation:
Detailed explanation-1: -The spatial correlation characteristic of CNNs can be ex-ploited in different ways. We exploit it to dynamically predict zero-valued ofmap activations, thereby saving MAC operations of entire ifmap-filter convolutions.
Detailed explanation-2: -THE MISNOMER: The Convolutional operation widely used in CNN is a misnomer. The operation that is used is strictly speaking a correlation instead of convolution.
Detailed explanation-3: -This translation invariance in the convolutional NN is achieved by a combination of convolutional layers and max pooling layers.
There is 1 question to complete.