Home > Research > Publications & Outputs > Towards Deep Machine Reasoning

Text available via DOI:

View graph of relations

Towards Deep Machine Reasoning: A Prototype-based Deep Neural Network with Decision Tree Inference

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published
Publication date11/10/2020
Host publication2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2092-2099
Number of pages8
VolumeOctober
ISBN (Electronic)9781728185262
<mark>Original language</mark>English
Event2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 - Toronto, Canada
Duration: 11/10/202014/10/2020

Conference

Conference2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Country/TerritoryCanada
CityToronto
Period11/10/2014/10/20

Conference

Conference2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
Country/TerritoryCanada
CityToronto
Period11/10/2014/10/20

Abstract

In this paper we introduce the DMR - a prototype-based method and network architecture for deep learning which is using a decision tree (DT)- based inference and synthetic data to balance the classes. It builds upon the recently introduced xDNN method addressing more complex multi-class problems, specifically when classes are highly imbalanced. DMR moves away from a direct decision based on all classes towards a layered DT of pair-wise class comparisons. In addition, it forces the prototypes to be balanced between classes regardless of possible class imbalances of the training data. It has two novel mechanisms, namely i) using a DT to determine the winning class label, and ii) balancing the classes by synthesizing data around the prototypes determined from the available training data. As a result, we improved significantly the performance of the resulting fully explainable DNN as evidenced on the well know benchmark problem Caltech-101. Furthermore, we also achieved high results in terms of accuracy for the well known Caltech-256 dataset, as well as surpassed the results of other approaches on Faces-1999 problem. In summary, we propose a new approach specifically advantageous for imbalanced multi-class problems on well known hard benchmark datasets. Moreover, DMR offers full explainability, does not require GPUs and can continue to learn from new data by adding new prototypes preserving the previous ones but not requiring full retraining.

Bibliographic note

Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.