Deep Learning consists of algorithms that permit software to train itself— by exposing multilayered neural networks to vast amounts of data. It is most frequently used to perform tasks like speech and image recognition.
The intelligence in the process sits within the deep learning software frameworks themselves— which develop that neural model of understanding by building weights and connections between many, many data points— often millions in a training data set.
Deep learning thrives when other traditional techniques to solving your problem fail: where you want derive insightful or complex relationships from vast data, custom programming is impossible, or on visual or auditory data.
Ask a question, contribute to the conversation, and meet the IBM PowerAI team: