Fuzzy Logic Systems Institute, Iizuka, Fukuoka, Japan.
Neural Netw. 2011 Sep;24(7):767-78. doi: 10.1016/j.neunet.2011.03.017. Epub 2011 Mar 23.
The neocognitron is a hierarchical multi-layered neural network capable of robust visual pattern recognition. It has been demonstrated that recent versions of the neocognitron exhibit excellent performance for recognizing handwritten digits. When characters are written on a noisy background, however, recognition rate was not always satisfactory. To find out the causes of vulnerability to noise, this paper analyzes the behavior of feature-extracting S-cells. It then proposes the use of subtractive inhibition to S-cells from V-cells, which calculate the average of input signals to the S-cells with a root-mean-square. Together with this, several modifications have also been applied to the neocognitron. Computer simulation shows that the new neocognitron is much more robust against background noise than the conventional ones.
神经认知机是一种分层的多层神经网络，能够实现强大的视觉模式识别。已经证明，最近版本的神经认知机在手写数字识别方面表现出色。然而，当字符写在嘈杂的背景上时，识别率并不总是令人满意。为了找出对噪声敏感的原因，本文分析了提取特征的 S 细胞的行为。然后提出了从 V 细胞到 S 细胞的减法抑制，V 细胞计算输入到 S 细胞的信号的均方根值。此外，还对神经认知机进行了一些修改。计算机模拟表明，新的神经认知机比传统的神经认知机对背景噪声具有更强的鲁棒性。
