[programming]
In image analysis, a machine learning technique that teaches a computer to filter inputs through layers to learn how to predict and classify information in imagery. Deep learning relies on a large number of training samples representing features and objects of interest, then employs complex algorithms to predict outcomes that are compared to training data iteratively to develop a training model. The training model is then run against new imagery with characteristics similar to the training samples in order to predict and identify features and objects defined by the training samples.