U tweetove putem weba ili aplikacija drugih proizvođača možete dodati podatke o lokaciji, kao što su grad ili točna lokacija. Povijest lokacija tweetova uvijek možete izbrisati. Saznajte više
What's Hidden in a Randomly Weighted Neural Network?
“Hidden in a randomly weighted Wide ResNet-50 we show that there is a subnetwork (with random weights) that is smaller than, but matches the performance of a ResNet-34 trained on ImageNet.” 
https://arxiv.org/abs/1911.13299 https://twitter.com/Mitchnw/status/1201575787100561408 …
I hope to see more work into HyperNEAT-style genetic encoding for compressing large networks into a subnetwork enforcing regular structural patterns. An artificial “genetic bottleneck” should bring us closer to innate structures observed in animals:https://twitter.com/TonyZador/status/1164362711620362240 …
"Every block of stone has a statue inside it and it is the task of the sculptor to discover it." -- Michelangelo
@tyrell_turing @KordingLab Where does their alg. for judicious pruning of randomly weighted network stand on the credit assignment efficiency spectrum? Better than node pert.? "Not only do these 'untrained subnetworks' exist, but we provide an algorithm to effectively find them."
Pretty cool idea l. Wondering how close is it to self similarly and something like fractal symmetry
I think that this is simply that if you add enough random initialized units to the network you will find the ones that solve the problem eventually
I suggest a name: matrioshka nets
Isn't finding a subnetwork with a given performance equivalent to train a network? The number of possible subnetworks is colossal, it shouldn't be surprising that some of them have good performance on any task.
Variation of the Infinite monkey problem? :) https://en.wikipedia.org/wiki/Infinite_monkey_theorem …
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
香港人 
⠀
