Massively Parallel Neural Encoding and Decoding of Visual Stimuli

Aurel A. Lazar, Yiyin Zhou
Department of Electrical Engineering, Columbia University, New York, NY 10027, USA
Neural Networks, Special Issue: Selected papers from IJCNN11, 2012


   title={Massively Parallel Neural Encoding and Decoding of Visual Stimuli},

   author={Lazar, A.A. and Zhou, Y.},



Download Download (PDF)   View View   Source Source   



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.
No votes yet.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: