| Jahr | 2017 |
| Autor(en) | Syed Ahmed Aamir* , Paul Müller*, Laura Kriener, Gerd Kiene, Johannes Schemmel and Karlheinz Meier |
| Titel | From LIF to AdEx Neuron Models: Accelerated Analog 65 nm CMOS Implementation |
| KIP-Nummer | HD-KIP 17-61 |
| KIP-Gruppe(n) | F9 |
| Dokumentart | Paper |
| Keywords (angezeigt) | Analog integrated circuits, Neuromorphic, Leaky Integrate-and-Fire, 65 nm CMOS, Spiking, Neuron, Adaptation, Exponential, LIF, AdEx |
| Quelle | Accepted at 2017 IEEE Biomedical Circuits and Systems Conference (BioCAS) |
| doi | 10.1109/BIOCAS.2017.8325167 |
| Abstract (en) | Here we present analog circuits emulating an Adaptive Exponential I&F (AdEx) neuron model developed for our second generation 65-nm CMOS neuromorphic hardware. Designed for an existing accelerated Leaky Integrate and Fire (LIF) circuit, the modular circuit architecture allows us to switch between LIF and AdEx neuron models and further to multiple-compartments. We describe our circuit implementation and the simulation results for adaptation and exponential sub-circuits. The neuron circuit specifications are compared with a targeted set of computational models. We show how addition of analog AdEx circuits let us qualitatively reproduce spike patterns known from cortical neurons. |
| bibtex | @inproceedings{aamir17dls3neuron,
author = {S. A. Aamir and P. Müller and L. Kriener and G. Kiene and J. Schemmel and K. Meier},
title = {From LIF to AdEx Neuron Models: Accelerated Analog 65 nm CMOS Implementation},
booktitle = {IEEE Biomedical Circuits and Systems Conference (BioCAS)},
year = {2017},
volume = {},
pages = {1-4},
month = {October},
publisher = {IEEE}
} |
| URL |
