A feedforward neural network has an input layer 5 hidden layers and an output layer. What is the depth of this neural network?

You finish training your traffic sign classifier, and want to evaluate its performance. You compute the classification accuracy on the training, validation, and testing data splits and get the following results:

You know that a human has an accuracy of around 98% on the traffic sign classification task. What are things you might try to achieve human level performance? (Check all that apply.)

When a neural network overfits the training data, the generalization gap is usually very small.

Which of the following strategies are used for regularization in neural networks? (Check all that apply.)

Dropout significantly limit the type of neural network models that can be used, and hence is usually used for specific architectures.

The name convolutional neural networks comes from the fact that these neural networks use a convolution operation instead of general matrix multiplication.