Google DeepMind 是一家英国的人工智能公司。公司创建于 2010 年,最初名称是 DeepMind 科技,在 2014 年被谷歌收购。

VIP内容

高度超参数化的神经网络可以显示出令人好奇的强大的泛化性能——为了更好地理解这一现象,最近积累了大量的理论和实证研究。与之前的工作相比,通常认为性能是模型大小的函数,在本文中,我们实证地研究了训练集的大小在多个数量级上变化时的泛化性能。这些系统的实验导致了一些有趣的和潜在的非常有用的观察;也许最值得注意的是,对较小子集的数据的训练可以导致更可靠的模型选择决策,同时享受较小的计算开销。我们的实验进一步允许我们估计现代神经网络结构下公共数据集的最小描述长度,从而为基于Ocams -razor的原则模型选择铺平了道路。

https://deepmind.com/research/publications/Small-Data-Big-Decisions-Model-Selection-in-the-Small-Data-Regime

成为VIP会员查看完整内容
0
21

最新论文

In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new environment, we assume no prior knowledge of those changes yet still obtain significant improvements. Empirical evaluations are performed on diverse environments from DeepMind Control suite and ViZDoom. Our method improves generalization in 25 out of 30 environments across various tasks, and outperforms domain randomization on a majority of environments.

0
0
下载
预览
Top