TY  - JOUR
A1  - Bird, Alex D.
A1  - Jedlička, Peter
A1  - Cuntz, Hermann
T1  - Dendritic normalisation improves learning in sparsely connected artificial neural networks
T2  - PLOS Computational Biology
N2  - Artificial neural networks, taking inspiration from biological neurons, have become an invaluable tool for machine learning applications. Recent studies have developed techniques to effectively tune the connectivity of sparsely-connected artificial neural networks, which have the potential to be more computationally efficient than their fully-connected counterparts and more closely resemble the architectures of biological systems. We here present a normalisation, based on the biophysical behaviour of neuronal dendrites receiving distributed synaptic inputs, that divides the weight of an artificial neuron’s afferent contacts by their number. We apply this dendritic normalisation to various sparsely-connected feedforward network architectures, as well as simple recurrent and self-organised networks with spatially extended units. The learning performance is significantly increased, providing an improvement over other widely-used normalisations in sparse networks. The results are two-fold, being both a practical advance in machine learning and an insight into how the structure of neuronal dendritic arbours may contribute to computation.
Y1  - 2021
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/73396
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-733961
SN  - 1553-7358
VL  - 17
IS  - 8, e1009202
SP  - 1
EP  - 24
PB  - Public Library of Science
CY  - San Francisco, Calif.
ER  -