Interpreting Multilayer Perceptrons Using 3-Valued Activation Function

Multilayer perceptrons (MLPs) have been successfully applied to solving many problems, but in most cases, they are used as black boxes which are not interpretable. That is, even if an MLP can provide correct answers, we cannot understand the reasons why it makes these decisions. In this study, we tr...

Full description

Saved in:
Bibliographic Details
Published in2017 3rd IEEE International Conference on Cybernetics (CYBCONF) pp. 1 - 6
Main Authors Furukawa, Tomoya, Qiangfu Zhao
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2017
Subjects
Cancer
Decision trees
Ionosphere
Iris
Iris recognition
Neurons
Training
Online AccessGet full text

Cover

More Information
Summary:Multilayer perceptrons (MLPs) have been successfully applied to solving many problems, but in most cases, they are used as black boxes which are not interpretable. That is, even if an MLP can provide correct answers, we cannot understand the reasons why it makes these decisions. In this study, we try to interpret a single hidden layer MLP by discretizing the hidden neuron outputs into 3 values (e.g. -1, 0, and 1). The 3 values correspond to false, unknown, and true, respectively. The basic process is (1) train an MLP first, (2) discretize the hidden neurons, (3) retrain the output layer of the MLP, (4) add more hidden neurons if needed, and (5) induce a decision tree based on the hidden neuron outputs. Experiments on several public datasets show that the proposed method is feasible for acquiring interpretable knowledge.
DOI:10.1109/CYBConf.2017.7985786