Earlier quoted context omitted.
Yes seems political to snub him, but then ACM is an American association.
Dr. LeCun is a French native, for what it's worth
That's not true with Schmidhuber.
51–60 of 159 posts
I would love to hear a long form podcast with all three (and a CS knowledgeable interviewer)
I think Schmidhuber should be up there. LSTMs are everywhere, not just NLP. The latest Starcraft 2 bot from Deepmind uses LSTMs extensively in its architecture.
Schmidhuber didn't invent LSTM Just by himself. Original papaer was published by Sepp Hochreiter and Schmidhuber.
Earlier quoted context omitted.
Various researchers, e.g. Werbos, Linnainmaa, Bryson and Yu-Chi Ho have been doing backprop in neural networks before Hinton et al. Hinton was merely a popularizer of the idea.
Wright brothers were most likely not the first to achieve heavier-than-air powered flight. But they made the first controlled, sustained flight. Controlled flight was the real breakthrough in aviation. It's the same with Hinton et. all. They were among many other pioneers, but what really sets them apart is that they made it all work. They also analyzed why it works.
I would love to hear a long form podcast with all three (and a CS knowledgeable interviewer)
This is the closest I could find. https://www.thetalkingmachines.com/episodes/history-machine-...
Text, language, human chat
Image recognition from blurry, multiple views, multiple lighting conditions photos
formal patterns with large numbers of variations
These are not at all the same, yet the praise seems to want to declare "the best" and "beating competitors" .. why is something so multi-faceted, reduced to the logic of a sports event ?