Back to Search
Start Over
Tailored ensembles of neural networks optimize sensitivity to stimulus statistics
- Source :
- Physical Review Research
- Publication Year :
- 2020
-
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.<br />6 pages plus supplemental material
- Subjects :
- Computational Neuroscience
Neurons, networks, dynamical systems
Artificial neural network
Quantitative Biology::Neurons and Cognition
Dynamic range
Computer science
business.industry
Artificial networks
Reservoir computing
FOS: Physical sciences
Pattern recognition
Disordered Systems and Neural Networks (cond-mat.dis-nn)
Stimulus (physiology)
Condensed Matter - Disordered Systems and Neural Networks
FOS: Biological sciences
Quantitative Biology - Neurons and Cognition
Neurons and Cognition (q-bio.NC)
Artificial intelligence
business
Biological network
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Physical Review Research
- Accession number :
- edsair.doi.dedup.....5a8bfd0525671e151cf0be336c6519de