Simplicable Guide

3 Examples of Deep Learning

John Spacey, May 03, 2017

Deep learning is a general approach to artificial intelligence that involves AI that acts as an input to other AI. Such architectures can be quite complex with a large number of machine learners giving their opinion to other machine learners. The following are illustrative examples.

Speech Recognition

An AI learns to tell the difference between languages. It decides a person is speaking English and invokes an AI that is learning to tell the difference between different regional accents of English. The AI decides the person is speaking Cardiff English and invokes an AI that is learning to speak Cardiff English. In this way, each conversation can be interpreted by a highly specialized AI that has learned their dialect.

Self-Driving Car

The street in front of a moving vehicle is interpreted by a large number of specialized AI. For example, one learner is only training to recognize pedestrians, another is learning to recognize street signs. There might be hundreds of such specialized visual recognition AI that all feed their opinions into an AI that interprets driving events. In theory, a single car could use the opinions of thousands or even millions of individual AI as it navigates a street.

Robotics

A housekeeping robot might use the opinions of a large number of AI in order to complete everyday tasks. For example, the robot might have a few AI devoted to dog psychology that help it deal with the household pet over the course of its day.

Overview: Deep Learning
Type	Artificial Intelligence
Definition	An artificial intelligence that contains many specialized artificial intelligences that act together in a coordinated way.
Notes	The examples above are somewhat simplified. For example, a self driving car might have several levels of learning just to recognize street signs. At each level, you could potentially have a large number of AI with results decided by a committee machine.
Related Concepts	Artificial Intelligence Machine Learning Affective Computing Blockhead Recursive Self-Improvement Swarm Intelligence Superintelligence Committee Machine