Definition: deep learning

An AI machine learning architecture employed in "neural networks." Emerging in the 2010s, deep learning is used in all forms of AI such as computer vision, self-driving cars, natural language processing and chatbots. When the resulting system is used to do work, a deep learning model has greater accuracy because the training data were analyzed in greater depth. See neural network and AI in a nutshell.

Phase I - Network Design
The neural network architecture consists of an input layer, "hidden" middle layers and an output layer. There can be dozens, hundreds or even thousands of hidden layers. The more layers, the "deeper" the learning.

Neurons in the Layer
Each layer consists of neurons, which are numerical units. The name was loosely derived from the human neural system, and there can be from a dozen to several thousand neurons in each layer. Also called "nodes" and "hidden units," each individual neuron is connected mathematically to all the neurons in the next layer. The numeric values assigned to these interconnections, known as "parameters," are preset at the design stage. See AI hyperparameter.

Phase II - Training
To train an AI model, countless examples of text or images are input to the network, and the connections are refined as examples move from one layer to the next. The more training data, the "deeper" the learning.

If the training is "supervised," the examples are identified; for example, images of dogs are named "dog." In an "unsupervised" approach, the deep learning model has to figure out which objects are similar. For text training, the model has to recognize all the patterns of word relationships in the sentences.

As data flows from the input layer through the hidden layers and finally to the output layer, each layer modifies the values passed to it based on the weights assigned to each neuron. The weights are constantly adjusted in the training stages to improve the accuracy and reliability of the model. See AI backpropagation and AI weights and biases.

Phase III - Inference
After the deep learning phase, the "inference engine" uses the model to do the processing for the user such as answering questions and generating original content. The higher the quality of the deep learning model, the more accurate the results. See AI inference and DLA.

Algorithms Make Mistakes

Deep learning networks can be fooled. A famous example is mistaking a muffin for a chihuahua dog. This CAPTCHA test is used to ensure the viewer is a human, but images such as these can confuse an algorithm. However, more advanced deep learning systems can, in fact, differentiate between them.

Deep Learning in the Hierarchy

Deep learning is a part of machine learning, which is the major category of artificial intelligence.