Authors:
Julius Voigt
1
;
Sascha Saralajew
2
;
Marika Kaden
1
;
Katrin Bohnsack
1
;
3
;
Lynn Reuss
1
and
Thomas Villmann
1
Affiliations:
1
Saxon Institute for Computational Intelligence and Machine Learning, University of Applied Sciences Mittweida, Mittweida, Germany
;
2
NEC Laboratories Europe GmbH, Heidelberg, Germany
;
3
Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, The Netherlands
Keyword(s):
Classification Learning, Biologically-Informed Neural Networks, Pathway Knowledge Integration, Shallow Neural Networks, Interpretable Models.
Abstract:
We propose a biologically-informed shallow neural network as an alternative to the common knowledge-integrating deep neural network architecture used in bio-medical classification learning. In particular, we focus on the Generalized Matrix Learning Vector Quantization (GMLVQ) model as a robust and interpretable shallow neural classifier based on class-dependent prototype learning and accompanying matrix adaptation for suitable data mapping. To incorporate the biological knowledge, we adjust the matrix structure in GMLVQ according to the pathway knowledge for the given problem. During model training both the mapping matrix and the class prototypes are optimized. Since GMLVQ is fully interpretable by design, the interpretation of the model is straightforward, taking explicit account of pathway knowledge. Furthermore, the robustness of the model is guaranteed by the implicit separation margin optimization realized by means of the stochastic gradient descent learning. We demonstrate the
performance and the interpretability of the shallow network by reconsideration of a cancer research dataset, which was already investigated using a biologically-informed deep neural network.
(More)