Voit lisätä twiitteihisi sijainnin, esimerkiksi kaupungin tai tarkemman paikan, verkosta ja kolmannen osapuolen sovellusten kautta. Halutessasi voit poistaa twiittisi sijaintihistorian myöhemmin. Lue lisää
So you don’t think something exists until it’s been shown to work. More accurate would be to give everyone credit for their part instead of just saying backprop was invented in 1985 (and even then by multiple separate people at once).
And to Rao’s point, there was really nothing preventing Fukushima from applying backprop (by whatever name) to the Neocognitron. Which would have saved us quite a few years!
Other than his supposed interest in biological plausibility? (..or that he wouldn't really have seen much of a difference at that time with his level of compute/data support anyway?)
He probably didn't know about it, but then again he wasn't looking because from a biological point of view convnets and backprop are a very odd combination.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.
