Abstract | ||
---|---|---|
We present a fully event-driven vision and processing system for selective attention and tracking implemented on Intel's neuromorphic research chip, Loihi, directly interfaced with an event-based Dynamic Vision Sensor, DAVIS. The attention mechanism is realized as a recurrent spiking neural network (SNN) that forms sustained activation-bump attractors. The network dynamics support object tracking when distractors are present and when the object slows down or stops. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/AICAS48895.2020.9073789 | 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) |
Keywords | DocType | ISBN |
recurrent spiking neural network,network dynamics,neuromorphic hardware,event-driven vision processing system,Intel neuromorphic research chip,event-based dynamic vision sensor,event-based attention tracking,SNN,activation-bump attractors,object tracking | Conference | 978-1-7281-4923-3 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alpha Renner | 1 | 0 | 2.70 |
Matthew Evanusa | 2 | 0 | 0.68 |
Orchard, G. | 3 | 24 | 3.77 |
Yulia Sandamirskaya | 4 | 95 | 20.93 |