Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Towards Deep Machine Reasoning
T2 - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
AU - Angelov, Plamen
AU - Soares, Eduardo
N1 - Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/10/11
Y1 - 2020/10/11
N2 - 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.
AB - 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.
U2 - 10.1109/SMC42975.2020.9282812
DO - 10.1109/SMC42975.2020.9282812
M3 - Conference contribution/Paper
AN - SCOPUS:85098848408
VL - October
SP - 2092
EP - 2099
BT - 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 October 2020 through 14 October 2020
ER -