Number detectors spontaneously emerge in a deep neural network designed for visual object recognition
Number detectors spontaneously emerge in a deep neural network designed for visual object recognition
复制标题
DOI：
10.1126/sciadv.aav7903
复制
发表时间：
2019-05-01
期刊：
影响因子：
13.6
通讯作者：
Nieder, Andreas
中科院分区：
文献类型：
--
作者：
Nasr, Khaled;Viswanathan, Pooja;Nieder, Andreas
人类和动物都有一种“数感”，这是一种天生的能力，可以直观地评估一组视觉项目的数量和数量。这种能力意味着提取数字的机制与大脑的视觉系统密切相关，而视觉系统主要与视觉对象识别有关。在这里，我们展示了调整到抽象数字的网络单元，因此让人想起实数神经元，自发地出现在一个生物启发的深度神经网络中，这个网络仅仅是在视觉对象识别方面训练的。这些数量调整的单位构成了该网络数字辨别性能的基础，显示了韦伯-费克纳定律所预测的人类和动物数量辨别的所有特征。这些发现解释了基于视觉系统固有机制的数字感觉的自发出现。
Humans and animals have a "number sense," an innate capability to intuitively assess the number of visual items in a set, its numerosity. This capability implies that mechanisms to extract numerosity indwell the brain's visual system, which is primarily concerned with visual object recognition. Here, we show that network units tuned to abstract numerosity, and therefore reminiscent of real number neurons, spontaneously emerge in a biologically inspired deep neural network that was merely trained on visual object recognition. These numerosity-tuned units underlay the network's number discrimination performance that showed all the characteristics of human and animal number discriminations as predicted by the Weber-Fechner law. These findings explain the spontaneous emergence of the number sense based on mechanisms inherent to the visual system.