Question

The Lottery Ticket Hypothesis attempts to explain these constructs’ efficiency despite their low VC dimension. Proving that a sequence of these constructs converges to any arbitrary function is the goal of several Universal Approximation Theorems. One type of these constructs passes a 2D “mask” over values to compute an activation map. The LSTM (10[1])was created to alleviate a problem with these constructs where a value “vanishes” (10[1])due to repeatedly applying the chain rule. (-5[1])Images can be processed using the “convolutional” type (10[1])of these constructs. The weights of these constructs (10[2])are typically updated using backpropagation, (10[1])which was popularized by 2024 Nobel Laureate Geoffrey Hinton. For 10 points, “deep learning” uses what biologically-inspired computational (10[2])constructs? ■END■

ANSWER: artificial neural networks [or deep neural networks or ANNs or DNNs; accept specific types of neural networks such as convolutional neural networks or recurrent neural networks or CNNs or RNNs; accept “The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks”; prompt on classifiers or learners or machine learning models or large language models or LLMs; prompt on artificial neurons; reject “biological neural networks”]
<Other Science>
= Average correct buzz position

Back to tossups

Buzzes

PlayerTeamOpponentBuzz PositionValue
Cole WelchGeorgia Tech EEmory A5210
Michael ZhouGeorgia Tech AGeorgia Tech C6510
Charlie WeaverClemson AGeorgia Tech D72-5
Malachi LedfordTusculum ATennesse B8010
Will McCurleyAuburn AEmory B8810
Parker McCoigTennesse AAlabama A8810
Bharath RamGeorgia Tech DClemson A9310
Clark QuenzlerGeorgia Tech FAuburn C11110
TurjyaGeorgia AAuburn B11110