arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.04225cs.LGstat.ML
收藏

测量神经网络中的抽象推理

Measuring abstract reasoning in neural networks

DeepMind(深度思维)

David G. T. Barrett, Felix Hill, Adam Santoro, Ari S. Morcos, Timothy Lillicrap

摘要:

神经网络是否能够学习抽象推理,或者它们是否仅仅依赖于表面的统计数据,这是最近争论的一个话题。在这里,我们提出了一个数据集和挑战,旨在探索抽象推理,灵感来自一个著名的人类智商测试。为了在这一挑战中取得成功,模型必须应对各种泛化“制度”,其中训练和测试数据以明确定义的方式不同。我们发现,像ResNets这样的流行模型表现不佳,即使训练集和测试集只有最小的差异,我们提出了一种新的架构,其结构旨在鼓励推理,这一点要好得多。当我们改变测试问题和训练数据不同的方式时,我们发现我们的模型在某些形式的概括方面非常精通,但在其他方面却非常薄弱。我们进一步表明,该模型的概括能力显着提高,如果它被训练来预测其答案的符号解释。总之,我们介绍和探索的方法来衡量和诱导更强的抽象推理的神经网络。我们免费提供的数据集应该会推动这方面的进一步进展。

英文摘要:

Whether neural networks can learn abstract reasoning or whether they merely rely on superficial statistics is a topic of recent debate. Here, we propose a dataset and challenge designed to probe abstract reasoning, inspired by a well-known human IQ test. To succeed at this challenge, models must cope with various generalisation `regimes' in which the training and test data differ in clearly-defined ways. We show that popular models such as ResNets perform poorly, even when the training and test sets differ only minimally, and we present a novel architecture, with a structure designed to encourage reasoning, that does significantly better. When we vary the way in which the test questions and training data differ, we find that our model is notably proficient at certain forms of generalisation, but notably weak at others. We further show that the model's ability to generalise improves markedly if it is trained to predict symbolic explanations for its answers. Altogether, we introduce and explore ways to both measure and induce stronger abstract reasoning in neural networks. Our freely-available dataset should motivate further progress in this direction.

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。

↑