BriefGPT.xyz
Nov, 2022
利用幂律缩放应对人工智能面临的关键挑战
Power-law Scaling to Assist with Key Challenges in Artificial Intelligence
HTML
PDF
Yuval Meir, Shira Sardi, Shiri Hodassman, Karin Kisos, Itamar Ben-Noam...
TL;DR
使用幂律缩放在深度学习中有助于处理当前人工智能应用中的关键挑战，可用于测量训练复杂性和机器学习任务算法的量化层次，并建立数据集大小估计的基准以实现期望的测试准确性。
Abstract
power-law scaling
, a central concept in
critical phenomena
, is found to be useful in
deep learning
, where optimized
→