Ñaari Wàccig Fenomen Quiz

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Fan la njuumti test bi di gëna bari ci courbe descendant double bi?
   • Ci buntu interpolation bi model bi di méngoo ak bépp done buñ tàggat
   • Bi ñuy tàmbali tàggat yaram ak ay paramet yu néew
   • Ginaaw ay miliyaar ciy parametre
   • Jumtukaayu test du musa yéeg; Dafay daanu ci anam wu monoton
2. Lan mooy xew ci njuumti test bi model bi di gëna bari ay parametre?
   • Dafay yokk ba fàww ndax overfitting
   • Mën na wàññeekuwaat, lu bari ci suufu li gëna ndaw
   • Dafay des ndànk
   • Dafay nekk lu bari te kenn mënu la wax
3. In which setting does the cited implicit-bias analysis characterize a minimum-norm solution?
   • Any neural network trained with gradient descent
   • Any model that reaches zero training error
   • A single-hidden-layer linear network under stated gradient-flow and initialization assumptions
   • A model trained without an optimization objective
4. 'Epoch-wise' ñaari wàcciku dafay wax ci efekt bi feeñ ci fonction lan?
   • Limu GPU yiñ jëfandikoo
   • Jamonoy jàngat bi kese
   • Dayo ensemble test bi
   • Jamonoy tàggat yaram (limu jamono yi)
5. Ban xalaat bu yàgg la double descendant di xeex?
   • kompromis bi am formu U
   • Tasaaro ci ginaaw
   • Wàcci degrade stokastik
   • Regle de chaîne
6. Kan moo jàppale siiwal ak formalise courbe double descent ci 2019?
   • newton ak leibniz
   • Belkin, Hsu, Ma, ak Mandal
   • Turing ak Eglis
   • Concurrent yu Kaggle yu kenn xamul turam kese
7. Which model families did OpenAI report studying in its deep double-descent experiments?
   • Only decision trees and linear regression
   • Only recurrent speech recognizers
   • Convolutional neural networks, ResNets, and transformers
   • Only graphical game generators
8. Besides model size and training duration, which axis can also show double-descent behavior?
   • Font size in a report
   • The number of words in a product name
   • The screen resolution of a monitor
   • Training dataset size