Spike timing-based unsupervised learning of orientation, disparity, and motion representations in a spiking neural network

• Published in: IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops pp. 1377 - 1386
• Main Authors: Barbier, Thomas, Teuliere, Celine, Triesch, Jochen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2021
• Subjects: Conferences; Detectors; Neuromorphics; Neurons; Robot sensing systems; Vision sensors; Visualization

Neuromorphic vision sensors present unique advantages over their frame based counterparts. However, unsupervised learning of efficient visual representations from their asynchronous output is still a challenge, requiring a re-thinking of traditional image and video processing methods. Here we presen...