AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Concept of Distinctive Distributed Distributed Representations
i know the lood of your work has been really solely focusedn on these and sparse distributed representations. So what do you think about the kind of comparison between vectosn and these m discreet representations that you are aa, well, that's istorict. A, it turns out that, ah, sparse representations have a lot of really desirable and interesting properties that you don't get with dense representations. And we also see that en an in real norans, that they're not very high fidelity. They don't carry individual spiking rates or very crude,. Ither many instances where even the single, the first spike, is actuly the most important thing, recurring information