Deep learning is a machine learning research area that is based on a particular type of learning mechanism. It is characterized by the effort to create a learning model at several levels, in which the most profound levels take as input the outputs of previous levels, transforming them and always abstracting more. This insight on the levels of learning is inspired by the way the brain processes information and learns, responding to external stimuli.

Each learning level corresponds, hypothetically, to one of the different areas which make up the cerebral cortex.

The visual cortex, which is intended to solve image recognition problems, shows a sequence of sectors placed in a hierarchy. Each of these areas receives an input representation, by means of flow signals that connect it to other sectors.

Each level of this hierarchy represents a different level of abstraction, with the most abstract features defined in terms of those of the lower level. At a time when the brain receives an input image, the processing goes through various phases, for example, detection of the edges or the perception of forms (from those primitive to those gradually more and more complex).

As the brain learns by trial and activates new neurons by learning from the experience, even in deep learning architectures, the extraction stages or layers are changed based on the information received at the input.

The scheme, on the next page shows what has been said in the case of an image classification system, each block gradually extracts the features of the input image, going on to process data already preprocessed from the previous blocks, extracting features of the image that are increasingly abstract, and thus building the hierarchical representation of data that comes with on deep learning based system.

More precisely, it builds the layers as follows along with the figure representation:

• Layer 1: The system starts identifying the dark and light pixels
• Layer 2: The system identifies edges and shapes
• Layer 3: The system learns more complex shapes and objects
• Layer 4: The system learns which objects define a human face

Here is the visual representation of the process:

The development of deep learning consequently occurred parallel to the study of artificial intelligence, and especially neural networks. After beginning in the 50 s, it is mainly in the 80s that this area grew, thanks to Geoff Hinton and machine learning specialists who collaborated with him. In those years, computer technology was not sufficiently advanced to allow a real improvement in this direction, so we had to wait until the present day to see, thanks to the availability of data and the computing power, even more significant developments.

As for the areas of application, deep learning is employed in the development of speech recognition systems, in the search patterns, and especially, in the image recognition, thanks to its learning characteristics for levels, which enable it to focus, step by step, on the various areas of an image to be processed and classified.