Miller Vonda H, Jansen Ben H
The Boeing Company, 13100 Space Center Blvd, MC 2-10, Houston, TX, 77059, USA.
Biol Cybern. 2008 Dec;99(6):459-71. doi: 10.1007/s00422-008-0253-x. Epub 2008 Sep 20.
Computer algorithms that match human performance in recognizing written text or spoken conversation remain elusive. The reasons why the human brain far exceeds any existing recognition scheme to date in the ability to generalize and to extract invariant characteristics relevant to category matching are not clear. However, it has been postulated that the dynamic distribution of brain activity (spatiotemporal activation patterns) is the mechanism by which stimuli are encoded and matched to categories. This research focuses on supervised learning using a trajectory based distance metric for category discrimination in an oscillatory neural network model. Classification is accomplished using a trajectory based distance metric. Since the distance metric is differentiable, a supervised learning algorithm based on gradient descent is demonstrated. Classification of spatiotemporal frequency transitions and their relation to a priori assessed categories is shown along with the improved classification results after supervised training. The results indicate that this spatiotemporal representation of stimuli and the associated distance metric is useful for simple pattern recognition tasks and that supervised learning improves classification results.
在识别书面文本或口语对话方面，能与人类表现相匹配的计算机算法仍然难以实现。迄今为止，人类大脑在泛化能力以及提取与类别匹配相关的不变特征方面，远远超过任何现有的识别方案，其原因尚不清楚。然而，据推测，大脑活动的动态分布（时空激活模式）是刺激被编码并与类别进行匹配的机制。本研究聚焦于在振荡神经网络模型中使用基于轨迹的距离度量进行监督学习以进行类别区分。分类是通过基于轨迹的距离度量来完成的。由于距离度量是可微的，展示了一种基于梯度下降的监督学习算法。呈现了时空频率转换的分类及其与先验评估类别之间的关系，以及监督训练后的改进分类结果。结果表明，这种刺激的时空表示以及相关的距离度量对于简单模式识别任务是有用的，并且监督学习能改善分类结果。
