Learning exact enumeration and approximate estimation in deep neural network models
Learning exact enumeration and approximate estimation in deep neural network models
复制标题
DOI：
10.1016/j.cognition.2021.104815
复制
发表时间：
2021-06-26
期刊：
影响因子：
3.4
通讯作者：
Solstad, Trygve
中科院分区：
文献类型：
--
作者：
Creatore, Celestino;Sabathiel, Silvester;Solstad, Trygve
用于近似数辨别的系统已经被证明出现在至少两种类型的分层神经网络模型中-生成深度信念网络（DBN）和分层卷积神经网络（HCNN），其被训练用于对自然对象进行分类。在这里，我们研究相同的两个网络架构是否可以学习识别精确的数值。性能上的明显差异可以追溯到每个网络最后一个隐藏层中出现的单位响应的特异性。在DBN中，单调的“求和单元”层的出现足以产生与近似数系统的行为签名一致的分类行为。在HCNN中，一层独特地调整到特定数字之间的过渡的单元有效地编码了一个类似温度计的“数字代码”，确保了近乎完美的分类准确性。结果支持的概念，并行模式识别机制可能会引起精确和近似的数字概念，这两者都可能有助于学习的符号数字和算术。
A system for approximate number discrimination has been shown to arise in at least two types of hierarchical neural network models-a generative Deep Belief Network (DBN) and a Hierarchical Convolutional Neural Network (HCNN) trained to classify natural objects. Here, we investigate whether the same two network architectures can learn to recognise exact numerosity. A clear difference in performance could be traced to the specificity of the unit responses that emerged in the last hidden layer of each network. In the DBN, the emergence of a layer of monotonic 'summation units' was sufficient to produce classification behaviour consistent with the behavioural signature of the approximate number system. In the HCNN, a layer of units uniquely tuned to the transition between particular numerosities effectively encoded a thermometer-like 'numerosity code' that ensured near-perfect classification accuracy. The results support the notion that parallel pattern-recognition mechanisms may give rise to exact and approximate number concepts, both of which may contribute to the learning of symbolic numbers and arithmetic.