Article 2020

Tailored ensembles of neural networks optimize sensitivity to stimulus statistics

The dynamic range of stimulus processing in living organisms is much larger than a single neural network can explain. For a generic, tunable spiking network we derive that while the dynamic range is maximal at criticality, the interval of discriminable intensities is very similar for any network tuning due to coalescence. Compensating coalescence enables adaptation of discriminable intervals. Thus, we can tailor an ensemble of networks optimized to the distribution of stimulus intensities, e.g., extending the dynamic range arbitrarily. We discuss potential applications in machine learning.

Author(s): Zierenberg, J and Wilting, J and Priesemann, V and Levina, A
Journal: {Physical Review Research}
Volume: 2
Pages: 1--9
Year: 2020
Publisher: American Physical Society (APS)
Project(s):
Bibtex Type: Article (article)
DOI: 10.1103/PhysRevResearch.2.013115
Address: College Park, Maryland, United States
Electronic Archiving: grant_archive

BibTex

@article{item_3165076,
  title = {{Tailored ensembles of neural networks optimize sensitivity to stimulus statistics}},
  journal = {{Physical Review Research}},
  abstract = {The dynamic range of stimulus processing in living organisms is much larger than a single neural network can explain. For a generic, tunable spiking network we derive that while the dynamic range is maximal at criticality, the interval of discriminable intensities is very similar for any network tuning due to coalescence. Compensating coalescence enables adaptation of discriminable intervals. Thus, we can tailor an ensemble of networks optimized to the distribution of stimulus intensities, e.g., extending the dynamic range arbitrarily. We discuss potential applications in machine learning.},
  volume = {2},
  pages = {1--9},
  publisher = {American Physical Society (APS)},
  address = {College Park, Maryland, United States},
  year = {2020},
  slug = {item_3165076},
  author = {Zierenberg, J and Wilting, J and Priesemann, V and Levina, A}
}