无限宽神经网络的无限集成信息
Information in Infinite Ensembles of Infinitely-Wide Neural Networks
摘要:
在这一初步工作中,我们研究了无限宽神经网络的无限集成的推广性质。令人惊讶的是,这个模型家族允许对许多信息论量进行易于处理的计算。我们报告的分析和实证调查,在寻找与泛化相关的信号。
英文摘要:
In this preliminary work, we study the generalization properties of infinite ensembles of infinitely-wide neural networks. Amazingly, this model family admits tractable calculations for many information-theoretic quantities. We report analytical and empirical investigations in the search for signals that correlate with generalization.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。