[peterfirefly]

> It just wouldn't have worked any earlier than when the results started coming out.

It most certainly would. Not in the 50's, of course, but in the 60's and 70's.

http://www.roylongbottom.org.uk/whetstone.htm

Look at the MFLOPS columns.

It seems to me that we had to wait until decent memory sizes and decent fp performance was a lot cheaper and therefore much more accessible => much easier to do experiments without having to justify them to higher-ups => somebody figured out 1) how to do backpropagation on neural nets and 2) that it was useful.

In other words, it wasn't obvious at all. It required experimentation.

It would have been practically useful from the 60's (for small neural nets and high-value problems) and 70's (not so small neural nets or lower-value problems) if somebody had figured out how to do it and that it was a useful thing to do.