Sublime
An inspiration engine for ideas
Artificial auto-associative memories fail to recognize patterns if they are moved, rotated, rescaled, or transformed in any of a thousand other ways, whereas our brains handle these variations with ease.
Sandra Blakeslee • On Intelligence
Build Your Career
Tony Fadell • Build: An Unorthodox Guide to Making Things Worth Making
2024 physics laureate Geoffrey Hinton used a network developed by his co-laureate John Hopfield as the foundation for a new network: the Boltzmann machine. This can learn to recognise characteristic elements in a given type of data.
The Boltzmann machine can be used to classify images or create new examples of the type of pattern on which it was t... See more
Aleks Pausak
@apausak
Andrew Pajela
@andrewpajela
Goodfire | Interpretability for deploying safe and reliable generative AI models
goodfire.aiThe next clever idea is to stack sparse autoencoders on top of each other
Pedro Domingos • The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World
Filip Sjölander
@vresig