研究人员开发了一个新模型来理解神经网络中的涌现现象，即泛化延迟的现象。该模型使用模运算任务上的全纯单项式激活函数，证明了可表性是关键。当网络的表达函数类崩溃为代数簇时，任务要么立即解决，要么无法拟合，从而消除了典型的涌现状态。研究在 585 次运行中显示出 99.8% 的准确率预测这些结果，为容量-涌现关系提供了新视角。 AI
影响 为理解神经网络中的泛化提供了理论框架，可能为未来的模型设计提供信息。
排序理由 该集群包含一篇详细介绍机器学习新模型和理论发现的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Neural networks trained on modular arithmetic exhibit grokking, a delayed transition from memorisation to generalisation known to depend on model capacity: too little and the network memorises slowly or not at all, too much and it generalises almost immediately. What happens at t…
arXiv:2607.13749v1 Announce Type: cross Abstract: Neural networks trained on modular arithmetic exhibit grokking, a delayed transition from memorisation to generalisation known to depend on model capacity: too little and the network memorises slowly or not at all, too much and it…
Neural networks trained on modular arithmetic exhibit grokking, a delayed transition from memorisation to generalisation known to depend on model capacity: too little and the network memorises slowly or not at all, too much and it generalises almost immediately. What happens at t…