Abstract
Spiking neural networks are rapidly gaining popularity for their ability to perform efficient computation akin to the way a brain processes information. It has the potential to achieve low cost and high energy efficiency due to the distributed nature of neural computation and the use of low energy spikes for information exchange. A stochastic spiking neural network naturally can be used to realize Bayesian inference. IBM's TrueNorth is a neurosynaptic processor that has more than 1 million digital spiking neurons and 268 million digital synapses with less than 200 mW peak power. In this paper we propose the first work that converts an inference network to a spiking neural network that runs on the TrueNorth processor. Using inference-based sentence construction as a case study, we discuss algorithms that transform an inference network to a spiking neural network, and a spiking neural network to TrueNorth corelet designs. In our experiments, the TrueNorth spiking neural network constructed sentences have a matching accuracy of 88% while consuming an average power of 0.205 mW.
Original language | English (US) |
---|---|
Title of host publication | 2016 International Joint Conference on Neural Networks, IJCNN 2016 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 4286-4293 |
Number of pages | 8 |
Volume | 2016-October |
ISBN (Electronic) | 9781509006199 |
DOIs | |
State | Published - Oct 31 2016 |
Event | 2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada Duration: Jul 24 2016 → Jul 29 2016 |
Other
Other | 2016 International Joint Conference on Neural Networks, IJCNN 2016 |
---|---|
Country | Canada |
City | Vancouver |
Period | 7/24/16 → 7/29/16 |
ASJC Scopus subject areas
- Software
- Artificial Intelligence