Video Time Encoding Machines


This package provides Python/PyCUDA code for encoding and decoding natural and synthetic visual scenes (videos) with Time Encoding Machines consisting of Gabor or center surround receptive fields followed by Integrate-and-Fire neurons [1], [2]. The decoder supports both the pseudoinverse algorithm, described in [1], [2] and the recurrent neural networks method, described in [3].

Downloads

  • VTEM 0.1.1 [ code | docs ] (June 7, 2013)

Documentation

The latest source code and documentation written by Nikul H. Ukani and Yiyin Zhou can be obtained from the vtem GitHub repository.

  1. Video Time Encoding Machines ,

    Aurel A. Lazar and Eftychios A. Pnevmatikakis , IEEE Transactions on Neural Networks , Volume 22 , Number 3 , pp. 461-473 , March 2011

  2. Encoding Natural Scenes with Neural Circuits with Random Thresholds ,

    Aurel A. Lazar, Eftychios A. Pnevmatikakis and Yiyin Zhou , Vision Research , Volume 50 , Number 22 , pp. 2200-2212 , October 2010 , Special Issue on Mathematical Models of Visual Coding

  3. Massively Parallel Neural Encoding and Decoding of Visual Stimuli ,

    Aurel A. Lazar and Yiyin Zhou , Neural Networks , Volume 32 , pp. 303-312 , August 2012 , Special Issue: IJCNN 2011