Learning in Silicon: Timing Is Everything
Abstract
We describe a neuromorphic chip that uses binary synapses with spike timing-dependent plasticity (STDP) to learn stimulated patterns of activ- ity and to compensate for variability in excitability. Specifically, STDP preferentially potentiates (turns on) synapses that project from excitable neurons, which spike early, to lethargic neurons, which spike late. The additional excitatory synaptic current makes lethargic neurons spike ear- lier, thereby causing neurons that belong to the same pattern to spike in synchrony. Once learned, an entire pattern can be recalled by stimulating a subset.
Cite
Text
Arthur and Boahen. "Learning in Silicon: Timing Is Everything." Neural Information Processing Systems, 2005.Markdown
[Arthur and Boahen. "Learning in Silicon: Timing Is Everything." Neural Information Processing Systems, 2005.](https://mlanthology.org/neurips/2005/arthur2005neurips-learning/)BibTeX
@inproceedings{arthur2005neurips-learning,
title = {{Learning in Silicon: Timing Is Everything}},
author = {Arthur, John V. and Boahen, Kwabena},
booktitle = {Neural Information Processing Systems},
year = {2005},
pages = {75-82},
url = {https://mlanthology.org/neurips/2005/arthur2005neurips-learning/}
}