Northcutt Brandon D, Higgins Charles M
Department of Electrical and Computer Engineering, University of Arizona, 1230 E. Speedway Blvd., Tucson, AZ, 85721, USA.
Departments of Neuroscience and Electrical/Computer Eng., University of Arizona, 1040 E. 4th St., Tucson, AZ, 85721, USA.
Biol Cybern. 2017 Apr;111(2):207-227. doi: 10.1007/s00422-017-0716-z. Epub 2017 Mar 16.
We have developed a neural network model capable of performing visual binding inspired by neuronal circuitry in the optic glomeruli of flies: a brain area that lies just downstream of the optic lobes where early visual processing is performed. This visual binding model is able to detect objects in dynamic image sequences and bind together their respective characteristic visual features-such as color, motion, and orientation-by taking advantage of their common temporal fluctuations. Visual binding is represented in the form of an inhibitory weight matrix which learns over time which features originate from a given visual object. In the present work, we show that information represented implicitly in this weight matrix can be used to explicitly count the number of objects present in the visual image, to enumerate their specific visual characteristics, and even to create an enhanced image in which one particular object is emphasized over others, thus implementing a simple form of visual attention. Further, we present a detailed analysis which reveals the function and theoretical limitations of the visual binding network and in this context describe a novel network learning rule which is optimized for visual binding.
我们开发了一种神经网络模型，该模型能够受果蝇视小球神经元回路启发进行视觉捆绑，视小球是位于视叶下游的一个脑区，早期视觉处理在此进行。这种视觉捆绑模型能够在动态图像序列中检测物体，并通过利用它们共同的时间波动将各自的特征视觉特征（如颜色、运动和方向）捆绑在一起。视觉捆绑以抑制性权重矩阵的形式表示，该矩阵会随着时间的推移学习哪些特征源自给定的视觉对象。在本研究中，我们表明，此权重矩阵中隐含表示的信息可用于明确计算视觉图像中存在的物体数量，列举它们的特定视觉特征，甚至创建一个增强图像，其中一个特定物体比其他物体更突出，从而实现一种简单形式的视觉注意力。此外，我们进行了详细分析，揭示了视觉捆绑网络的功能和理论局限性，并在此背景下描述了一种针对视觉捆绑进行优化的新型网络学习规则。
