University of Michigan - Ann Arbor

Google

A neural network configuration is called "shallow" if it has only a few hidden layers. In contrast, it's called "deep" if it has many hidden layers.

Deep vs. Shallow Neural Networks

The layer count of a feedforward neural network excludes the input layer but includes every hidden layer and the output layer. If the network has $$H$$ hidden layers, its total layer count is $$H+1$$. For example, a network with one hidden layer and one output layer is a two-layer network.

Counting Layers in a Feedforward Neural Network

Machine Learning Yearning, a free ebook from Andrew Ng, teaches you how to structure Machine Learning projects.
https://www.deeplearning.ai/machine-learning-yearning/

Note: The content of the book is aligned with the Coursera Deeplearning.ai specialization.  https://www.deeplearning.ai/deep-learning-specialization/ 

Machine Learning Yearning (Deeplearning.ai)

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?

Axes in a Learning Curve

What tends to happen when a supervised model is given more examples or a larger network?

A Comparison of Shallow and Deep Learning Methods for Predicting Cognitive Performance of Stroke Patients From MRI Lesion Images: 
https://www.frontiersin.org/articles/10.3389/fninf.2019.00053/full

A Comparison of Shallow and Deep Learning Methods for Predicting Cognitive Performance of Stroke Patients From MRI Lesion Images

Deep Learning is a sub-class of Machine Learning algorithms whose peculiarity is a higher level of complexity. So, Deep Learning belongs to Machine Learning and they are absolutely not opposite concepts. We refer to shallow learning to those techniques of machine learning that are not deep.
This increment in the number of layers and the networks’ complexity is known as deep learning, something like a conventional network on steroids.

What is  the difference between deep learning and Machine learning

how many layers is it considered Deep Learning?

Circuit theory offers an informal explanation for why deep neural networks can be more computationally efficient than shallow ones: some functions can be computed by a network with relatively few hidden units per layer when enough layers (depth) are used, whereas a shallower network computing the same function would need exponentially more hidden units.

Circuit Theory and Depth Efficiency in Neural Networks

- Single layer NN
- 2-layer NN
- N-layer NN

Learn Before

Related