Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity
Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity
复制标题
DOI：
10.1016/j.neunet.2012.02.022
复制
发表时间：
2012-08-01
期刊：
影响因子：
7.8
通讯作者：
Gamrat, Christian
中科院分区：
文献类型：
--
作者：
Bichler, Olivier;Querlioz, Damien;Gamrat, Christian
一种生物启发的方法来学习时间相关的模式，从尖峰硅视网膜。响应于像素级的照明的相对变化从视网膜生成尖峰，并将其传输到前馈尖峰神经网络。在完全无监督的方案中，神经元对具有相关激活时间的像素模式变得敏感。这是使用一种特殊形式的尖峰定时依赖可塑性来实现的，该可塑性抑制最近没有对突触后尖峰激活做出贡献的突触，而不管它们的激活时间。竞争性学习是通过侧抑制来实现的。当使用真实数据进行测试时，该系统能够在仅10分钟的交通学习后提取复杂和重叠的时间相关特征，例如高速公路上的汽车轨迹。使用第二层仍然可以以98%的检测率学习完整的轨迹，并且仍然具有无监督学习，并且该系统可以用作汽车计数器。所提出的神经网络是非常强大的噪声，它可以容忍高度的突触和神经元的变异性，对性能的影响很小。这样的结果表明，一个简单的生物启发的无监督学习方案是能够产生选择性的基础上相对较少的感官经验复杂的有意义的事件。(C)2012爱思唯尔有限公司保留所有权利。
A biologically inspired approach to learning temporally correlated patterns from a spiking silicon retina is presented. Spikes are generated from the retina in response to relative changes in illumination at the pixel level and transmitted to a feed-forward spiking neural network. Neurons become sensitive to patterns of pixels with correlated activation times, in a fully unsupervised scheme. This is achieved using a special form of Spike-Timing-Dependent Plasticity which depresses synapses that did not recently contribute to the post-synaptic spike activation, regardless of their activation time. Competitive learning is implemented with lateral inhibition. When tested with real-life data, the system is able to extract complex and overlapping temporally correlated features such as car trajectories on a freeway, after only 10 min of traffic learning. Complete trajectories can be learned with a 98% detection rate using a second layer, still with unsupervised learning, and the system may be used as a car counter. The proposed neural network is extremely robust to noise and it can tolerate a high degree of synaptic and neuronal variability with little impact on performance. Such results show that a simple biologically inspired unsupervised learning scheme is capable of generating selectivity to complex meaningful events on the basis of relatively little sensory experience. (C) 2012 Elsevier Ltd. All rights reserved.