11-19 更新 实时
首页/ 深度/ 正文

分形盆地几何与深度学习可预测性、可复现性的极限

深度 来源:Nature Machine Intelligence 2026-11-05 00:00 0 阅读 机器翻译
分形盆地几何与深度学习可预测性、可复现性的极限

Nature Machine Intelligence,在线发表:2026年11月5日;doi:10.1038/s42256-026-01336-3

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(Fractal basin geometry and the limits to predictability and reproducibility in deep learning)

Nature Machine Intelligence, Published online: 05 November 2026; doi:10.1038/s42256-026-01336-3

Deep learning outcomes are hard to predict and reproduce. Ly and Gong propose fractal basin geometry as a mechanism: starting points leading to different outcomes interweave at arbitrarily fine scales, so greater precision yields little improvement.

正文保留英文原文,标题与摘要由机器翻译。

本文由采集器自动同步

原文发布于 Nature Machine Intelligence(Fractal basin geometry and the limits to predictability and reproducibility in deep learning),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗