Ah, I and others use ‘learn’ and ‘forget’ loosely, not implying states of consciousness. Rather, ‘learn’ means only that the neural network moves from a random distribution of outcomes toward a distribution which is closer to what we have declared are correct answers. The machine isn’t thinking — just moving a distribution of responses. Similarly, ‘forgetting’ means only that the neural network moves away from a distribution which is regarded as correct, after having already moved toward it. I am not implying any sentience or will; these are simply the terms that have come to be used, considering that reiterating their precise meaning is cumbersome. You would need to convince the machine intelligence community at large that ‘learn’ and ‘forget’ are terms which should not be used — until then, I will continue to use them, with the above, commonly apprehended meaning.

Written by

Easily distracted mathematician

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store