TY  - CONF
AU  - He, Xu
AU  - Liu, Tianlin
AU  - Hadaeghi, Fatemeh
AU  - Jaeger, Herbert
TI  - Reservoir Transfer on Analog Neuromorphic Hardware
M1  - FZJ-2020-00876
PY  - 2019
N1  - Tianlin Liu was supported by  the FZJ through the project SMARTSTART Computational Neuroscience, DB001423.
AB  - Analog, unclocked, spiking neuromorphic microchips open new perspectives for implantable or wearable biosensors and biocontrollers, due to their low energy consumption and heat dissipation. However, the challenges from a computational point of view are formidable. Here we outline our solutions to realize the reservoir computing paradigm on such hardware and address the combined problems of low bit resolution, device mismatch, approximate neuron models, and timescale mismatch. The main contribution is a computational scheme, called Reservoir Transfer, which enables us to transfer the dynamical properties of a well-performing neural network which has been optimized on a digital computer, onto neuromorphic hardware that displays the abovementioned problematic properties. Here we present a case study of implementing an ECG heartbeat abnormality detector to showcase the proposed method.
T2  - 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER)
CY  - 20 Mar 2019 - 23 Mar 2019, San Francisco (CA)
Y2  - 20 Mar 2019 - 23 Mar 2019
M2  - San Francisco, CA
LB  - PUB:(DE-HGF)1
UR  - <Go to ISI:>//WOS:000469933200299
DO  - DOI:10.1109/NER.2019.8716891
UR  - https://juser.fz-juelich.de/record/873633
ER  -