C2M1

• Come from the same distribution

• Come from the different distribution

Be identical to each other (same (x, y) pairs)

Nave the same number of example

Get more traininig data

Get more test data

Increase the regularization parameter lambda

Decrease the regularization parameter lambda

Gt more training data

Use a bigger neural network

• A regularization technique (such as L2 regularization) that results in gradient descent shrinking the weights on every iteration.

• Weights are pushed toward becoming smaller (closer to 0)

• Weights are pushed toward becoming bigger (closer to 0)

• You do not apply dropout (do not randomly eliminate units) and do not keep the 1/keep_prob factor in the calculations used in training

Dropout

L2 regularization

Data augmentation

Xavier initialization

Gradient Checking

It makes it easier to visualize the data

It makes the parameter initialization faster

It makes the cost function faster to optimize