Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)KA
Posts
1
Comments
939
Joined
2 yr. ago

  • Honestly, as someone looking to buy a house right now, I'd be fine with the market crashing afterward.

    Of course, there would be unfortunate side-effects along with such a crash, but I'll gladly take a hit if it means affordable housing for Canadians.

  • A neural network is an array of layered nodes, where each node contains some kind of activation function, and each connection represents some weight multiplier. Importantly, once the model is trained, it's stateless, meaning we don't need to store any extra data to use it - just inputs and outputs.

    If we could take some sort of material, like a glass, and modify it so that if you shone a light through one end, the light would bounce in such a way as to emulate these functions and weights, you could create an extremely cheap, compact, fast, and power efficient neural network. In theory, at least.

  • Honestly I've wondered this about shining a laser through some kind of laser-etched glass. Only problem is, I have no idea how to represent something like an activation function using only reflection and such.