Corpus ID: 204971791

Event-based computation: unsupervised elementary motion decomposition

@inproceedings{Bogdan2019EventbasedCU,
  title={Event-based computation: unsupervised elementary motion decomposition},
  author={Petruţ A. Bogdan and Garibaldi Pineda Garcia and Simon Davidson and Michael Hopkins and R. James and S. Furber},
  year={2019}
}
Fast, localised motion detection is crucial for an efficient attention mechanism. We show that modelling a network capable of such motion detection can be performed using spiking neural networks simulated on many-core neuromorphic hard-ware. Moreover, highly sensitive neurons arise from the presented network architecture through unsupervised self-organisation. We use a synaptic rewiring rule which has been shown to enable the formation and refinement of neural topographic maps. Our extension… Expand
Soft-Grasping With an Anthropomorphic Robotic Hand Using Spiking Neurons

References

SHOWING 1-10 OF 11 REFERENCES
Spiking neural networks for computer vision
Structural Plasticity on the SpiNNaker Many-Core Neuromorphic System
Activity dependent structural plasticity in neuromorphic systems
Loihi: A Neuromorphic Manycore Processor with On-Chip Learning
An accelerated analog neuromorphic hardware system emulating NMDA- and calcium-based non-linear dendrites
pyDVS: An extensible, real-time Dynamic Vision Sensor emulator using off-the-shelf hardware
PyNN: A Common Interface for Neuronal Network Simulators
sPyNNaker: A Software Package for Running PyNN Simulations on SpiNNaker
Robust quantification of orientation selectivity and direction selectivity
...
1
2
...