guest ::
| Home > Publications database > Path classification by stochastic linear recurrent neural networks |
| Home > Publications database > Path classification by stochastic linear recurrent neural networks |
| Journal Article | FZJ-2022-01251 |
; ; ;
2022
London . BioMed Central
This record in other databases: 
Please use a persistent id in citations: http://hdl.handle.net/2128/30882 doi:10.1186/s13662-022-03686-9
Abstract: We investigate the functioning of a classifying biological neural network from the perspective of statistical learning theory, modelled, in a simplified setting, as a continuous-time stochastic recurrent neural network (RNN) with the identity activation function. In the purely stochastic (robust) regime, we give a generalisation error bound that holds with high probability, thus showing that the empirical risk minimiser is the best-in-class hypothesis. We show that RNNs retain a partial signature of the paths they are fed as the unique information exploited for training and classification tasks. We argue that these RNNs are easy to train and robust and support these observations with numerical experiments on both synthetic and real data. We also show a trade-off phenomenon between accuracy and robustness.
; 
; 
; 
; Clarivate Analytics Master Journal List ; Current Contents - Physical, Chemical and Earth Sciences ; DOAJ Seal ; Ebsco Academic Search ; IF < 5 ; JCR ; SCOPUS ; Web of Science Core Collection
|
The record appears in these collections: |
PDF
Fulltext by OpenAccess repository