Back
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.
@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} }