What is the difference between Deep Learning and traditional Artificial Neural Network machine learning

Question

Can you offer a concise explanation of the differences between Deep Learning and Traditional Machine Learning that utilize neural networks? How many levels are need to make a neural network "deep"? Is this all just marketing hype?

Answer 1

A large number of layers causes serious problems with standard backpropagation algorithms. One of the drawbacks of backward propagation is the problem of local minima. The local minimum of the error function increases at each layer. Not only does the mathematical minimum cause problems, but  there may be flat areas of the error function where the steepest descent method does not work (changing one or more weights does not  change much). 

 In a network with many layers, each cell layer can now also provide an abstraction layer that can solve more difficult problems. Deep learning addresses exactly this issue. The basic idea is to perform  unsupervised learning at each layer in addition to using the steepest descent method across the network. The goal of  unsupervised learning is to extract characteristic features from each layer. 
Over the years, several ways have been established to achieve even better results. Techniques such as: 

•  Residual Network 
•  Batch Normalization 
•  Normalization Linear Unit
  So no longer a hype now!

Unleash your potential with our Artificial Intelligence Course and master the future of technology!