Note that they do not call this Hebb’s law for a reason. This whole section on learning is still entirely theoretical. There is evidence (in some cases strong, in others not so much) for much of the theory, but there are many competing theories, with evidence to support them as well. I mention this only to remind the machine learning and artificial neural network people that using the theory of learning described here (the most popular) as the basis for saying you have developed a learning machine is your prerogative, but the theory may be totally wrong or only partially right. Even if a computer could mimic the processes described exactly (it cannot), by no means does that guarantee you have built a learning machine. It is hubris of the highest order to suggest we can build machines that learn when we do not yet even fully understand how human beings (and some non human animals) learn.

Written by

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