Carpenter G A, Ross W D
Center for Adaptive Syst., Boston Univ., MA.
IEEE Trans Neural Netw. 1995;6(4):805-18. doi: 10.1109/72.392245.
A new neural network architecture is introduced for the recognition of pattern classes after supervised and unsupervised learning. Applications include spatio-temporal image understanding and prediction and 3D object recognition from a series of ambiguous 2D views. The architecture, called ART-EMAP, achieves a synthesis of adaptive resonance theory (ART) and spatial and temporal evidence integration for dynamic predictive mapping (EMAP). ART-EMAP extends the capabilities of fuzzy ARTMAP in four incremental stages. Stage 1 introduces distributed pattern representation at a view category field. Stage 2 adds a decision criterion to the mapping between view and object categories, delaying identification of ambiguous objects when faced with a low confidence prediction. Stage 3 augments the system with a field where evidence accumulates in medium-term memory. Stage 4 adds an unsupervised learning process to fine-tune performance after the limited initial period of supervised network training. Each ART-EMAP stage is illustrated with a benchmark simulation example, using both noisy and noise-free data.
本文介绍了一种新的神经网络架构，用于在监督学习和无监督学习后识别模式类别。其应用包括时空图像理解与预测，以及从一系列模糊的二维视图中进行三维物体识别。这种名为ART-EMAP的架构实现了自适应共振理论（ART）与用于动态预测映射的时空证据整合（EMAP）的综合。ART-EMAP通过四个增量阶段扩展了模糊ARTMAP的功能。第一阶段在视图类别字段引入分布式模式表示。第二阶段在视图与对象类别之间的映射中添加决策标准，当面对低置信度预测时延迟对模糊对象的识别。第三阶段通过一个在中期记忆中积累证据的字段增强系统。第四阶段在监督网络有限的初始训练期后添加无监督学习过程以微调性能。每个ART-EMAP阶段都通过一个基准模拟示例进行说明，同时使用了有噪声和无噪声的数据。
