Name
Abstract | ||
|---|---|---|
We introduce the Spiking Multi-Layer Perceptron (SMLP). The SMLP is a spiking version of a conventional Multi-Layer Perceptron with rectified-linear units. Our architecture is event-based, meaning that neurons in the network communicate by sending "events" to downstream neurons, and that the state of each neuron is only updated when it receives an event. We show that the SMLP behaves identically, during both prediction and training, to a conventional deep network of rectified-linear units in the limiting case where we run the spiking network for a long time. We apply this architecture to a conventional classification problem (MNIST) and achieve performance very close to that of a conventional MLP with the same architecture. Our network is a natural architecture for learning based on streaming event-based data, and has potential applications in robotic systems systems, which require low power and low response latency. |
Year | Venue | DocType |
|---|---|---|
2016 | CoRR | Journal |
Volume | Citations | PageRank |
abs/1602.08323 | 13 | 0.73 |
References | Authors | |
4 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Peter O'Connor | 1 | 137 | 17.28 |
| Max Welling | 2 | 4875 | 550.34 |