arXiv 2009.021852020-09-04cs.AIcs.CV

朴素的人工智能

Naive Artificial Intelligence

The Edmond and Lily Safra Center for Brain Sciences（埃德蒙与莉莉·萨夫拉脑科学中心）；The Hebrew University, Jerusalem（耶路撒冷希伯来大学）；Department of Cognitive Sciences（认知科学系）；The Federmann Center for the Study of Rationality（费德曼理性研究中心）；The Alexander Silberman Institute of Life Sciences（亚历山大·西尔伯曼生命科学研究所）

Tomer Barak, Yehonatan Avidan, Yonatan Loewenstein

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

在认知科学中，通常区分晶体智力（crystal intelligence）和流体智力（fluid intelligence），晶体智力是指利用通过过去的学习或经验获得的知识的能力，流体智力是指在不依赖于先前知识的情况下解决新问题的能力。利用这两种智能之间的认知差异，经过广泛训练的深度网络可以下国际象棋或围棋，表现出晶体智能而不是流体智能。在人类中，流体智力通常使用智力测试进行研究和量化。之前的研究表明，深度网络可以解决某些形式的智力测试，但必须经过广泛的训练。在这里，我们提出了一个计算模型，解决了没有任何事先培训的智力测试。这种能力基于连续归纳推理，并由深度无监督潜在预测网络实现。我们的工作展示了深层网络的潜在流体智能。最后，我们提出，我们的方法背后的计算原理可以用来模拟流体智能的认知科学。

英文摘要：

In the cognitive sciences, it is common to distinguish between crystal intelligence, the ability to utilize knowledge acquired through past learning or experience and fluid intelligence, the ability to solve novel problems without relying on prior knowledge. Using this cognitive distinction between the two types of intelligence, extensively-trained deep networks that can play chess or Go exhibit crystal but not fluid intelligence. In humans, fluid intelligence is typically studied and quantified using intelligence tests. Previous studies have shown that deep networks can solve some forms of intelligence tests, but only after extensive training. Here we present a computational model that solves intelligence tests without any prior training. This ability is based on continual inductive reasoning, and is implemented by deep unsupervised latent-prediction networks. Our work demonstrates the potential fluid intelligence of deep networks. Finally, we propose that the computational principles underlying our approach can be used to model fluid intelligence in the cognitive sciences.

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。

摘要：

英文摘要：

相关论文