Deep learning has become very famous in the last few decades, thanks to hundreds of applications that are changing the way we interact with many electronic (and non-electronic) systems. Speech, text, and image recognition; autonomous vehicles; and intelligent bots (just to name a few) are common applications normally based on deep learning models and have outperformed any previous classical approach.
To better understand what a deep architecture is (considering that this is only a brief introduction), we need to step back and talk about standard artificial neural networks.
An artificial neural network (ANN) or simply neural network is a directed structure that connects an input layer with an output one. Normally, all operations are differentiable and the overall vectorial function can be easily written as:
Here:
The adjective "neural" comes from two important elements: the internal structure of a basic computational unit and the interconnections...