% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Keup:890946,
      author       = {Keup, Christian and Kühn, Tobias and Dahmen, David and
                      Helias, Moritz},
      title        = {{T}ransient chaotic {SNR} amplification},
      reportid     = {FZJ-2021-01268},
      year         = {2021},
      note         = {The short summary video can be found online at
                      https://vimeo.com/514398744},
      abstract     = {Strongly chaotic non-linear networks strongly separate
                      inputs, but are believed to be useless for classification
                      tasksbecause also irrelevant (noise) differences within any
                      class are exacerbated, leading to bad generalization. We
                      show thisis actually not the case during the initial time
                      period following input presentation: During this time, the
                      representationis dominated by expansion, but not by mixing,
                      and larger differences (between classes) expand faster than
                      smallerdifferences (within classes). Therefore, the
                      representation is disentangled by the dynamics, and when
                      classifying thenetwork state by linear readouts, the
                      signal-to-noise ratio (SNR) actually increases, before it
                      eventually deteriorateswhen mixing begins to dominate. We
                      show that this is a general effect in high-dimensional
                      non-linear chaotic systems,and demonstrate it in spiking,
                      continuous rate, and LSTM networks. The transient SNR
                      amplification is always fast(within 50 ms) for spiking
                      networks, while its timescale in continuous valued networks
                      depends on the distance to theedge of chaos. Moreover, this
                      fast, noise-resilient transient disentanglement of
                      representations is in line with empiricalevidence: the
                      olfactory bulb, for example, rapidly enhances the
                      separability of sensory representations in a singlerecurrent
                      layer, being the initial processing stage of a relatively
                      flat hierarchy.},
      month         = {Feb},
      date          = {2021-02-24},
      organization  = {COSYNE 2021, virtual (NA), 24 Feb 2021
                       - 26 Feb 2021},
      subtyp        = {After Call},
      cin          = {INM-6 / IAS-6 / INM-10},
      cid          = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
                      I:(DE-Juel1)INM-10-20170113},
      pnm          = {5232 - Computational Principles (POF4-523) / neuroIC002 -
                      Recurrence and stochasticity for neuro-inspired computation
                      (EXS-SF-neuroIC002) / MSNN - Theory of multi-scale neuronal
                      networks (HGF-SMHB-2014-2018) / GRK 2416 - GRK 2416:
                      MultiSenses-MultiScales: Neue Ansätze zur Aufklärung
                      neuronaler multisensorischer Integration (368482240) / ERS
                      Prep Fund - Exploratory Research Space: Prep Fund als
                      Anschubfinanzierung zur Schließung strategischer Lücken
                      (EXS-PF)},
      pid          = {G:(DE-HGF)POF4-5232 / G:(DE-82)EXS-SF-neuroIC002 /
                      G:(DE-Juel1)HGF-SMHB-2014-2018 / G:(GEPRIS)368482240 /
                      G:(DE-82)EXS-PF},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/890946},
}