Mayr C, Heittmann A, Schüffny R
IEEE Trans Neural Netw. 2007 May;18(3):955-9. doi: 10.1109/TNN.2007.891687.
In this letter, we present an implementation of a neural microcircuit for image processing employing Hebbian-adaptive learning. The neuronal circuit utilizes only excitatory synapses to correlate action potentials, extracting the uncorrelated ones, which contain significant image information. This circuit is capable of approximating Gabor-like image filtering and other image processing functions.
在这封信中，我们展示了一种采用赫布型自适应学习的用于图像处理的神经微电路的实现。该神经元电路仅利用兴奋性突触来关联动作电位，提取出其中不相关的动作电位，而这些不相关的动作电位包含重要的图像信息。此电路能够近似类伽柏图像滤波及其他图像处理功能。
