Deep Learning Quiz

Question 1

What if we set all the weights of a neural network to 0?

Accepted Answer

The equations of the learning algorithm would fail to make any changes to the network weights, and the model will be stuck.

Question 2

Softmax is an activation function that always returns the input value if it’s positive and zeroes otherwise.

Accepted Answer

false

Question 3

Dropout is an excellent regularization technique that speeds the training process.

Accepted Answer

false

Question 4

Type of layer that tipically has a reset gate and a output gate?

Accepted Answer

A GRU — though the two gates are properly the reset and the update gate. It folds the LSTM's cell and hidden state into one and drops a gate, so it has fewer parameters and trains faster, usually matching LSTM accuracy on short and medium sequences.

Question 5

What does GRU means?

Accepted Answer

Gated Recurrent Unit.

Question 6

Initializing a neural network’s weights with zero is our best bet to allow the network to converge.

Accepted Answer

False — with zero weights every unit in a layer computes the same thing and receives the same gradient, so the symmetry never breaks and the layer behaves like a single neuron. Use small random values scaled to fan-in: He for ReLU, Xavier for tanh. Biases can start at zero.

Question 7

What’s pooling in CNN? Why do we need it?

Accepted Answer

Pooling is a technique to downsample the feature map. It allows layers which receive relatively undistorted versions of the input to learn low level features such as lines.

Question 8

Autoencoders are one of the most popular supervised learning methods.

Accepted Answer

false

Question 9

The type of problem where you need to classify the input into a single class is called multi class classification.

Accepted Answer

true

Question 10

What happens when the learning rate is too small?

Accepted Answer

Takes more time to train but it is possible to find a more precise minimum. The downside can be that the solution is stuck in a local minimum.

About the deep learning quiz

More quizzes

Deep Learning Quiz

Keyboard shortcuts

About the deep learning quiz

More quizzes