Paper Info
Title
Efficient implementation of STDP rules on SpiNNaker neuromorphic hardware
Abstract
Recent development of neuromorphic hardware offers great potential to speed up simulations of neural networks. SpiNNaker is a neuromorphic hardware and software system designed to be scalable and flexible enough to implement a variety of different types of simulations of neural systems, including spiking simulations with plasticity and learning. Spike-timing dependent plasticity (STDP) rules are the most common form of learning used in spiking networks. However, to date very few such rules have been implemented on SpiNNaker, in part because implementations must be designed to fit the specialized nature of the hardware. Here we explain how general STDP rules can be efficiently implemented in the SpiNNaker system. We give two examples of applications of the implemented rule: learning of a temporal sequence, and balancing inhibition and excitation of a neural network. Comparing the results from the SpiNNaker system to a conventional double-precision simulation, we find that the network behavior is comparable, and the final weights differ by less than 3% between the two simulations, while the SpiNNaker simulation runs much faster, since it runs in real time, independent of network size.
Year
DOI
Venue
2014
10.1109/IJCNN.2014.6889876
Neural Networks
Keywords
Field
DocType
learning (artificial intelligence),neural nets,STDP rules,SpiNNaker neuromorphic hardware,inhibition balancing,network behavior,neural network excitation,neuromorphic hardware system,neuromorphic software system,spike-timing dependent plasticity rules,spiking neural networks,temporal sequence learning
Neuromorphic hardware,Computer science,SpiNNaker,Neuromorphic engineering,Software system,Implementation,Artificial intelligence,Artificial neural network,Machine learning,Scalability,Speedup
Conference
ISSN
Citations 
PageRank 
2161-4393
7
0.61
References 
Authors
11
2
Name
Order
Citations
PageRank
Peter U. Diehl12339.75
Matthew Cook228818.19