Artificial intelligence (AI) and artificial neural networks (ANN) are two exciting and intertwined fields in computer science. There are, however, several differences between the two that are worth knowing about.
The key difference is that neural networks are a stepping stone in the search for artificial intelligence.
Artificial intelligence is a vast field that has the goal of creating intelligent machines, something that has been achieved many times depending on how you define intelligence. Despite the fact that we have computers that can win at “Jeopardy” and beat chess champions, the goal of AI is generally seen as a quest for general intelligence, or intelligence that can be applied to diverse and unrelated situational problems.
Many of the AIs built up to this point have been built with a purpose, such as running a robot that plays ping pong or dominates at “Jeopardy.” This is the inevitable result when computer scientists sit down and create something to do a specific task – they end up with something that can do that task and not much else.
To get around this problem of task-orientated AIs, computer scientists started playing around with artificial neural networks. Our generally intelligent brains are made up of biological neural networks that make connections based on our perceptions and outside stimulus.
A grossly simplified example is the pain from getting burned. When this happens for the first time, a connection is made in your brain that identifies the sensory information known as fire (flames, smell of smoke, heat) and relates it with pain. This is how you learn, at a very young age, how to avoid getting burned.
Through this same neural network, we can do a lot of general learning like “ice cream tastes good” and even make deductive leaps like “there are always clouds before rain” or “stocks always rally in December.” These leaps are not always correct (there is bad ice cream and there are stocks that drop in December), but they can be corrected through experience, thus allowing adaptive learning.