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

Axes in a Learning Curve

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?

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?

Which of the following statements is true about layers of a deep neural network?

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.

Learn Before

Related