| dc.contributor.advisor | Gütig, Robert Dr. | |
| dc.contributor.author | Brune, Rafael | |
| dc.date.accessioned | 2018-11-29T10:23:24Z | |
| dc.date.available | 2018-11-29T10:23:24Z | |
| dc.date.issued | 2018-11-29 | |
| dc.identifier.uri | http://hdl.handle.net/11858/00-1735-0000-002E-E519-5 | |
| dc.identifier.uri | http://dx.doi.org/10.53846/goediss-7151 | |
| dc.language.iso | eng | de |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject.ddc | 571.4 | de |
| dc.title | Margin learning in spiking neural networks | de |
| dc.type | doctoralThesis | de |
| dc.contributor.referee | Geisel, Theo Prof. Dr. | |
| dc.date.examination | 2017-12-15 | |
| dc.description.abstracteng | The ability to learn, generalize and reliably detect features embedded
in continuous sensory input streams is a crucial function of the central
nervous system. Sensory neurons process input from thousands of
synapses and respond to short features embedded in the input spike
stream.
Although supervised synaptic learning rules that allow neurons
to learn and detect spatio-temporal structures in spike patterns have
been developed and studied, it is unclear how neurons can learn to
generalize when only a limited set of training examples embedded
in high-dimensional input patterns are available. Current learning
rules rely on the availability of many training patterns. The neurons
generalization performance to previously unseen feature variations
suffers from overfitting when the number of its synapses is too high
and hence limiting their usefulness when studying neural processing
of high-dimensional spatio-temporal input streams.
We introduce a novel definition of margin for spiking neuron mod-
els and a learning rule that extends the multi-spike tempotron with
methods to increase said margin during training. We discover that
this margin learning ensures high generalization ability even when
only a small set of training patterns are available and the number of
synapses is high. Using features embedded in Poisson patterns we
demonstrate the improvement in performance even under noise. By
successfully applying the introduced margin learning rules to human
speech recognition tasks we show their potential for studying neural
processing of high-dimensional inputs in spiking sensory neurons. | de |
| dc.contributor.coReferee | Gütig, Robert Dr. | |
| dc.subject.eng | supervised learning | de |
| dc.subject.eng | neuron model | de |
| dc.subject.eng | margin learning | de |
| dc.subject.eng | sensory processing | de |
| dc.subject.eng | spiking neuron | de |
| dc.identifier.urn | urn:nbn:de:gbv:7-11858/00-1735-0000-002E-E519-5-3 | |
| dc.affiliation.institute | Göttinger Graduiertenschule für Neurowissenschaften, Biophysik und molekulare Biowissenschaften (GGNB) | de |
| dc.subject.gokfull | Biologie (PPN619462639) | de |
| dc.identifier.ppn | 1041240384 | |