Ten thousand times faster: Classifying multidimensional data on a spiking neuromorphic hardware system.
-
1
Freie Universität Berlin, Germany
-
2
Bernstein Center for Computational Neuroscience Berlin, Germany
-
3
Heidelberg University, Kirchhoff Institute for Physics, Germany
Discrimination of sensory inputs is a computational task that biological neuronal systems perform very efficiently. Assessing the principles in those systems is a promising approach to develop technical solutions for many problems, such as data classification. A particular problem here is to train a classifier in a supervised fashion to discriminate classes in multidimensional data. We implemented a network of spiking neurons that solves this task using a neuromorphic hardware system, that is, analog neuronal circuits on a silicon substrate. This system enables us to do high-performance computation in a biologically inspired way, with spiking neurons as computational units. In this contribution, we illustrate solutions to technical challenges that occur when implementing a classifier on neuromorphic hardware.
The network topology of the insect olfactory system provides a well suited template for a neuronal architecture processing multidimensional data. In our classifier network, the value of each dimension of a data vector determines the rate of a stochastically generated spike train. The spike trains are fed into non-overlapping populations of neurons. Those populations project onto an association layer with winner-take-all properties representing the output of the classifier. During classifier training, the weights in this projection are adjusted according to a firing-rate based learning rule.
The values in multidimensional data sets are typically real numbers, but neuronal firing rates are restricted to values between zero and some maximal value. Hence, the data must be transformed into a positive, bounded representation. We achieved this by representing each data point as a vector of distances to a number of points in data space (“virtual receptors” [1]). The representation by virtual receptors inevitably introduces correlation between input dimensions. We reduced this correlation using lateral inhibition in the first neuronal layer, leading to a significant increase in classifier performance. We found that decorrelation was most efficient when we scaled the inhibitory weights according to the correlation between the connected populations.
We ran our classifier network on a neuromorphic hardware system that runs at ten thousand times the speed of biological neurons, thus suited for high performance computing [2]. However, the considerable variance of rate-response sensitivity across hardware neurons decreased classification performance. We therefore developed a calibration routine to counteract the neuronal variance.
Acknowledgements
Funding was received through BMBF grants 01GQ1001D (within Bernstein Center for Computational Neuroscience Berlin) to MS and MN, and 01GQ0941 (within Bernstein Focus Neuronal Basis of Learning) to MN and DFG grant SCHM2472/1-1 (wihtin SPP1302: Integrative analysis of olfaction) to MS.
References
[1] Schmuker, M. and Schneider, G. (2007). Processing and classification of chemical data inspired by insect olfaction. Proc. Natl. Acad. Sci. U S A 104, 20285-20289.
[2] Brüderle, D., Bill, J., Kaplan, B., Kremkow, J., Meier, K., Müller, E. and Schemmel, J. (2010). Simulator-like exploration of cortical network architectures with a mixed-signal VLSi system. In Proc. of IEEE Intern. Symp. on Circuits and Systems (ISCAS), 2784–8787.
Keywords:
data analysis and machine learning,
multilayer perceptron,
neuromorphic hardware system,
olfactory system,
Spiking Neuronal Network
Conference:
BC11 : Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting 2011, Freiburg, Germany, 4 Oct - 6 Oct, 2011.
Presentation Type:
Poster
Topic:
data analysis and machine learning (please use "data analysis and machine learning" as keyword)
Citation:
Schmuker
M,
Brüderle
D,
Schrader
S and
Nawrot
MP
(2011). Ten thousand times faster: Classifying multidimensional data on a spiking neuromorphic hardware system..
Front. Comput. Neurosci.
Conference Abstract:
BC11 : Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting 2011.
doi: 10.3389/conf.fncom.2011.53.00109
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
23 Aug 2011;
Published Online:
04 Oct 2011.
*
Correspondence:
Dr. Michael Schmuker, Freie Universität Berlin, Berlin, 14195, Germany, m.schmuker@biomachinelearning.net