A lot of the recent advancements in AI are based upon deep learning technology.
While there are many classic machine learning algorithms based around statistical algorithms, deep learning works by mimicking the human brain.
Or, more specifically, around how neuroscientists believed how the human brain worked in the 80s.
Models built on deep learning frameworks can do astonishing things when finding and creating patters from data.
Here’s a great primer on the most basic type of deep learning structure: the feed forward neural network.
Feedforward neural networks were among the first and most successful learning algorithms. They are also called deep networks, multi-layer perceptron (MLP), or simply neural networks. As data travels through the network’s artificial mesh, each layer processes an aspect of the data, filters outliers, spots familiar entities and produces the final output.