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

Standard

Towards Deep Machine Reasoning : A Prototype-based Deep Neural Network with Decision Tree Inference. / Angelov, Plamen; Soares, Eduardo.

2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. Vol. October Institute of Electrical and Electronics Engineers Inc., 2020. p. 2092-2099 9282812.

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

Harvard

Angelov, P & Soares, E 2020, Towards Deep Machine Reasoning: A Prototype-based Deep Neural Network with Decision Tree Inference. in 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. vol. October, 9282812, Institute of Electrical and Electronics Engineers Inc., pp. 2092-2099, 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020, Toronto, Canada, 11/10/20. https://doi.org/10.1109/SMC42975.2020.9282812

APA

Angelov, P., & Soares, E. (2020). Towards Deep Machine Reasoning: A Prototype-based Deep Neural Network with Decision Tree Inference. In 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 (Vol. October, pp. 2092-2099). [9282812] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC42975.2020.9282812

Vancouver

Angelov P, Soares E. Towards Deep Machine Reasoning: A Prototype-based Deep Neural Network with Decision Tree Inference. In 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. Vol. October. Institute of Electrical and Electronics Engineers Inc. 2020. p. 2092-2099. 9282812 doi: 10.1109/SMC42975.2020.9282812

Author

Angelov, Plamen ; Soares, Eduardo. / Towards Deep Machine Reasoning : A Prototype-based Deep Neural Network with Decision Tree Inference. 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020. Vol. October Institute of Electrical and Electronics Engineers Inc., 2020. pp. 2092-2099

Bibtex

@inproceedings{fc3c8bf6085a4073ac3003a6a11dc83c,
title = "Towards Deep Machine Reasoning: A Prototype-based Deep Neural Network with Decision Tree Inference",
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.",
author = "Plamen Angelov and Eduardo Soares",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 ; Conference date: 11-10-2020 Through 14-10-2020",
year = "2020",
month = oct,
day = "11",
doi = "10.1109/SMC42975.2020.9282812",
language = "English",
volume = "October",
pages = "2092--2099",
booktitle = "2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

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 -