https://www.coursera.org/learn/neural-networks-deep-learning/lecture/rz9xJ/why-deep-representations

University of Rochester

University of Michigan - Ann Arbor

Because deeper networks can learn more complicated functions. Exponentially more nodes would be needed in each layer to achieve the same level of complexity if the network was shallower.

Why deep networks instead of shallower networks?

Here You can see an example of some of the filters  that were learned by a CNN and how they have the representation of some shapes inside of them. This keeps on happening with more detailed forms as they move further into the layers.

An example of latent representations in deep networks

For a feedforward neural network, the depth of the network is the number of hidden layers plus one (as the output layer is also parameterized). The width of the network is the dimensionality of its hidden layers.

The main architectural considerations for designing a neural network are choosing the depth of the network and the width of each layer.


Learn Before

Related