arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.06374cs.LGq-bio.NCstat.ML
收藏

理解神经网络意味着什么?

What does it mean to understand a neural network?

Timothy P. Lillicrap, Konrad P. Kording

摘要:

我们可以定义一个神经网络,它可以在不到100行的代码中学会识别物体。然而,经过训练后,它的特点是拥有数百万个权重,其中包含有关视觉场景中许多对象类型的知识。这样的网络在代码方面比结果属性(如调优或连接)更容易理解。以此类推,我们推测,大脑的发育和学习规则可能比它们的结果属性更容易理解。这个类比表明,神经科学将受益于对学习和发展的关注。

英文摘要:

We can define a neural network that can learn to recognize objects in less than 100 lines of code. However, after training, it is characterized by millions of weights that contain the knowledge about many object types across visual scenes. Such networks are thus dramatically easier to understand in terms of the code that makes them than the resulting properties, such as tuning or connections. In analogy, we conjecture that rules for development and learning in brains may be far easier to understand than their resulting properties. The analogy suggests that neuroscience would benefit from a focus on learning and development.

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。

↑