Comment by vasco
1 day ago
So it's not the situation they described at all, you didn't waste time during the PhD having to scramble to change topics as it happened after you were done.
1 day ago
So it's not the situation they described at all, you didn't waste time during the PhD having to scramble to change topics as it happened after you were done.
That, and also it's just a completely different approach which might later on turn out to be useful. People should remember that artificial neural networks were developed decades before they were useful. People were doing all kinds of other approaches to ML like support vector machines before advances in hardware made deep neural nets feasible and therefore interesting again. ANNs were never obsoleted by SVMs.
Actually, I'm pretty sure SVMs were obsoleted with ANNs (not just in terms of UFFs).