Comment by woko
13 hours ago
I have checked LeCun's #3 most cited article (20k citations) [1]. Among the 15 references in this article, one is for the most cited article by Fukushima (11k citations) [2].
Also, LeCun mentioned [3] "a chat with Kunihiko Fukushima in 1991", which states that "Fukushima started to work on a backprop version of the Neocognitron in 1989 or so but saw our 1989 paper in Neural Computation and gave up."
[1] LeCun et al., "Backpropagation applied to handwritten zip code recognition", 1989
[2] Fukushima et al., "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position", 1980
I like how tweets are now our source for giving credit to people after taking the Turing Award for CNNs.
CNNs were a pretty simple idea even at the time. People were using convolutions for years already in classical image processing. It's a small step to put those computations into weights. Especially if you leave out the FFT step which neural nets don't even use.
Low hanging fruit successfully plucked, I guess.
I sometimes find myself thinking this too then challenge myself to find a low hanging fruit in an area I’m somewhat familiar with and draw a blank (usually).
Low hanging fruit is somewhat the opposite of sour grapes - I don’t want these grapes because they were probably sour versus so what if he got those sweet grapes - they were hanging low!
Maybe connecting “low hanging fruit” to “sour grapes” is “low hanging fruit” to some but it took a serious mental leap for me.