Comparison Between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing

Comparison Between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing

Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can...

Full description

Bibliographic Details
Main Authors: Clément eFarabet, Rafael ePaz, Jose ePerez-Carrasco, Carlos eZamarreño, Alejandro eLinares-Barranco, Yann eLeCun, Eugenio eCulurciello, Teresa eSerrano-Gotarredona, Bernabe eLinares-Barranco
Format: Article
Language:English
Published: Frontiers Media S.A. 2012-04-01
Series:Frontiers in Neuroscience
Subjects:
FPGA
Address-Event-Representation (AER)
Convolutional Neural Network (ConvNet)
Frame-free vision
Image Convolutions
Spike-based Convolutions
Online Access:http://journal.frontiersin.org/Journal/10.3389/fnins.2012.00032/full

Internet

http://journal.frontiersin.org/Journal/10.3389/fnins.2012.00032/full

Similar Items