论文标题
CNN体系结构中FRPN的嵌入
Embedding of FRPN in CNN architecture
论文作者
论文摘要
本文将媒介输入的完全递归感知器网络（FRPN）模型扩展到包括深卷积神经网络（CNN），该模型可以接受多维输入。 FRPN由递归层组成，鉴于固定输入，它迭代地计算了平衡状态。通过这种迭代机制实现的展开允许模拟具有任何数量层的深神经网络。将FRPN扩展到CNN会导致建筑，我们称之为卷积FRPN（C-FRPN），其中卷积层是递归的。该方法在几个图像分类基准上进行评估。结果表明，C-FRPN始终优于具有相同数量参数的标准CNN。对于小型网络而言，性能的差距特别较大，表明C-FRPN是一种非常强大的体系结构，因为与Deep CNN相比，它允许以更少的参数获得等效性能。
This paper extends the fully recursive perceptron network (FRPN) model for vectorial inputs to include deep convolutional neural networks (CNNs) which can accept multi-dimensional inputs. A FRPN consists of a recursive layer, which, given a fixed input, iteratively computes an equilibrium state. The unfolding realized with this kind of iterative mechanism allows to simulate a deep neural network with any number of layers. The extension of the FRPN to CNN results in an architecture, which we call convolutional-FRPN (C-FRPN), where the convolutional layers are recursive. The method is evaluated on several image classification benchmarks. It is shown that the C-FRPN consistently outperforms standard CNNs having the same number of parameters. The gap in performance is particularly large for small networks, showing that the C-FRPN is a very powerful architecture, since it allows to obtain equivalent performance with fewer parameters when compared with deep CNNs.
