Reading one of the answers, about Algorithm to detect nudity with good precision , I saw that a term that is very quoted and referred to is Deep Learning . For me, translating Deep Learning, it did not make much sense.
Deep learning is associated with artificial intelligence and mainly allied to neural networks , the goal of a neural network is to learn and recognize patterns, for this makes use of several neurons, which form a network, such as the following image 
.
The values of W represent the input of data in a neuron and the output of it will be connected in other neurons, each neuron has a "weight" that is called a threshold and that defines the function made by it.
Important to point out that they are unsupervised networks, they learn alone without human supervision.
Deep Learning-inspired machines can learn complex abstractions of data through a hierarchical learning process very similar to what occurs in the human brain - especially in the visual cortex.
Assoonasanetworkismountedandtheneuronsintheinnerlayersareresponsibleforidentifyingsmallpatternsinsomethinglarger,forexampleinthe"7" character check, a part of the network recognizes the angles and directions of each pixel in the image.
In its quoted case of pornography, the neural network is able to identify small patterns and that if added they can affirm that, for example, what appears in the image is a penis. There are several neural network evaluation techniques, I think this is a bit outside the scope of your question, however I suggest reading about Perceptron / a> and Backpropagation .
Deep learning can have the input of many things, mainly unstructured data and can be used for recognition of photos, sound, videos, texts and others.
For more details on Deep Learning I suggest this post.
Deep Learning are artificial neural networks with many layers. These layers when cleverly combined have resulted in major breakthroughs in the area of artificial intelligence.
Typically in machine learning problems it is necessary for a human to determine features describing a set of data. A feature is, for example, what Luiz describes about color histograms in this answer a>. The big advantage of Deep Learning is the ability of these models to extract features from the raw data without the need for human intervention.
Although simple models such as a Multilayer Perceptron with 3 layers are already considered Deep Learning , there is no big success there. What has really revolutionized this field are more advanced network architectures like:
And many others that come up every month. From the examples I've shown, you can see how much Google uses Deep Learning in their research projects, but it's not the only one. Just enter the site of the research group of other major technology companies:
And many others.
Deep learning is influencing the area of computer vision. There is no autonomous car company, for example, that does not use deep-learning as the core technology of automated steering software.
Currently, the best framework for getting started with Deep Learning is keras . Both python and R .
It's worth remembering that Deep Learning can be used in all forms of machine learning: unsupervised, supervised, and reinforcement learning.
