1 ECOMP, Polytechnic School of Pernambuco, University of Pernambuco, Recife, Pernambuco 50720-001, Brazil.
Int J Neural Syst. 2018 Jun;28(5):1750021. doi: 10.1142/S0129065717500216. Epub 2017 Feb 9.
The Pyramidal Neural Networks (PNN) are an example of a successful recently proposed model inspired by the human visual system and deep learning theory. PNNs are applied to computer vision and based on the concept of receptive fields. This paper proposes a variation of PNN, named here as Structured Pyramidal Neural Network (SPNN). SPNN has self-adaptive variable receptive fields, while the original PNNs rely on the same size for the fields of all neurons, which limits the model since it is not possible to put more computing resources in a particular region of the image. Another limitation of the original approach is the need to define values for a reasonable number of parameters, which can turn difficult the application of PNNs in contexts in which the user does not have experience. On the other hand, SPNN has a fewer number of parameters. Its structure is determined using a novel method with Delaunay Triangulation and k-means clustering. SPNN achieved better results than PNNs and similar performance when compared to Convolutional Neural Network (CNN) and Support Vector Machine (SVM), but using lower memory capacity and processing time.
金字塔神经网络 (PNN) 是最近受人类视觉系统和深度学习理论启发而成功提出的模型的一个例子。PNNs 应用于计算机视觉，并基于感受野的概念。本文提出了 PNN 的一种变体，称为结构化金字塔神经网络 (SPNN)。SPNN 具有自适应可变感受野，而原始 PNNs 依赖于所有神经元的相同大小的字段，这限制了模型，因为不可能在图像的特定区域中投入更多的计算资源。原始方法的另一个限制是需要为合理数量的参数定义值，这使得 PNNs 在用户没有经验的情况下难以应用。另一方面，SPNN 的参数数量较少。其结构使用带有 Delaunay 三角剖分和 k-均值聚类的新方法确定。SPNN 的结果优于 PNNs，并且与卷积神经网络 (CNN) 和支持向量机 (SVM) 相比具有相似的性能，但使用的内存容量和处理时间较低。
