Department of Electrical Engineering, Columbia University, New York, NY 10027, USA.
Neural Netw. 2012 Aug;32:303-12. doi: 10.1016/j.neunet.2012.02.007. Epub 2012 Feb 16.
The massively parallel nature of video Time Encoding Machines (TEMs) calls for scalable, massively parallel decoders that are implemented with neural components. The current generation of decoding algorithms is based on computing the pseudo-inverse of a matrix and does not satisfy these requirements. Here we consider video TEMs with an architecture built using Gabor receptive fields and a population of Integrate-and-Fire neurons. We show how to build a scalable architecture for video Time Decoding Machines using recurrent neural networks. Furthermore, we extend our architecture to handle the reconstruction of visual stimuli encoded with massively parallel video TEMs having neurons with random thresholds. Finally, we discuss in detail our algorithms and demonstrate their scalability and performance on a large scale GPU cluster.
视频时间编码机 (TEM) 的大规模并行性质要求使用神经组件实现可扩展的大规模并行解码器。当前一代的解码算法基于计算矩阵的伪逆，无法满足这些要求。在这里，我们考虑使用 Gabor 感受野和群体积分放电神经元构建的视频 TEM 架构。我们展示了如何使用递归神经网络为视频时间解码机构建可扩展的架构。此外，我们将我们的架构扩展到处理使用具有随机阈值的神经元的大规模并行视频 TEM 编码的视觉刺激的重建。最后，我们详细讨论了我们的算法，并在大型 GPU 集群上展示了它们的可扩展性和性能。
