Authors:
Charles Kent
1
;
Leila Bagheriye
2
and
Johan Kwisthout
2
Affiliations:
1
School of Artificial Intelligence, Radboud Universiteit, Houtlaan 4, Nijmegen, Netherlands
;
2
Donders Institute for Brain, Cognition & Behaviour, Radboud Universiteit, Houtlaan 4, Nijmegen, Netherlands
Keyword(s):
Cancer Diagnosis, Multi-Omics, Population Decoding, Spiking Neural Networks, Winner-Take-All, Hierarchical Bayesian Network, Self-Organising Maps.
Abstract:
Recent strides in the field of neural computation has seen the adoption of Winner-Take-All (WTA) circuits to facilitate the unification of hierarchical Bayesian inference and spiking neural networks as a neurobiologically plausible model of information processing. Current research commonly validates the performance of these networks via classification tasks, particularly of the MNIST dataset. However, researchers have not yet reached consensus about how best to translate the stochastic responses from these networks into discrete decisions, a process known as population decoding. Despite being an often underexamined part of SNNs, in this work we show that population decoding has a significant impact on the classification performance of WTA networks. For this purpose, we apply a WTA network to the problem of cancer subtype diagnosis from multi-omic data, using datasets from The Cancer Genome Atlas (TCGA). In doing so we utilise a novel implementation of gene similarity networks, a feat
ure encoding technique based on Kohoen’s self-organising map algorithm. We further show that the impact of selecting certain population decoding methods is amplified when facing imbalanced datasets.
(More)