Zhang B, Fu M, Yan H, Jabri M A
Department of Electrical and Computer Engineering, University of Newcastle, NSW 2308, Australia.
IEEE Trans Neural Netw. 1999;10(4):939-45. doi: 10.1109/72.774267.
The adaptive-subspace self-organizing map (ASSOM) proposed by Kohonen is a recent development in self-organizing map (SOM) computation. In this paper, we propose a method to realize ASSOM using a neural learning algorithm in nonlinear autoencoder networks. Our method has the advantage of numerical stability. We have applied our ASSOM model to build a modular classification system for handwritten digit recognition. Ten ASSOM modules are used to capture different features in the ten classes of digits. When a test digit is presented to all the modules, each module provides a reconstructed pattern and the system outputs a class label by comparing the ten reconstruction errors. Our experiments show promising results. For relatively small size modules, the classification accuracy reaches 99.3% on the training set and over 97% on the testing set.
科霍宁提出的自适应子空间自组织映射（ASSOM）是自组织映射（SOM）计算中的一项最新进展。在本文中，我们提出了一种在非线性自动编码器网络中使用神经学习算法来实现ASSOM的方法。我们的方法具有数值稳定性的优点。我们已将我们的ASSOM模型应用于构建用于手写数字识别的模块化分类系统。十个ASSOM模块用于捕捉十类数字中的不同特征。当将一个测试数字呈现给所有模块时，每个模块都会提供一个重构模式，并且系统通过比较十个重构误差来输出一个类别标签。我们的实验显示出了有前景的结果。对于相对较小尺寸的模块，在训练集上分类准确率达到99.3%，在测试集上超过97%。
