TY - GEN
T1 - Adaptation and contextualization of deep neural network models
AU - Kollias, Dimitrios
AU - Yu, Miao
AU - Tagaris, Athanasios
AU - Leontidis, Georgios
AU - Stafylopatis, Andreas
AU - Kollias, Stefanos
PY - 2018/2/2
Y1 - 2018/2/2
N2 - The ability of Deep Neural Networks (DNNs) to provide very high accuracy in classification and recognition problems makes them the major tool for developments in such problems. It is, however, known that DNNs are currently used in a 'black box' manner, lacking transparency and interpretability of their decision-making process. Moreover, DNNs should use prior information on data classes, or object categories, so as to provide efficient classification of new data, or objects, without forgetting their previous knowledge. In this paper, we propose a novel class of systems that are able to adapt and contextualize the structure of trained DNNs, providing ways for handling the above-mentioned problems. A hierarchical and distributed system memory is generated and used for this purpose. The main memory is composed of the trained DNN architecture for classification/prediction, i.e., its structure and weights, as well as of an extracted - equivalent - Clustered Representation Set (CRS) generated by the DNN during training at its final - before the output - hidden layer. The latter includes centroids - 'points of attraction' - which link the extracted representation to a specific area in the existing system memory. Drift detection, occurring, for example, in personalized data analysis, can be accomplished by comparing the distances of new data from the centroids, taking into account the intra-cluster distances. Moreover, using the generated CRS, the system is able to contextualize its decision-making process, when new data become available. A new public medical database on Parkinson's disease is used as testbed to illustrate the capabilities of the proposed architecture.
AB - The ability of Deep Neural Networks (DNNs) to provide very high accuracy in classification and recognition problems makes them the major tool for developments in such problems. It is, however, known that DNNs are currently used in a 'black box' manner, lacking transparency and interpretability of their decision-making process. Moreover, DNNs should use prior information on data classes, or object categories, so as to provide efficient classification of new data, or objects, without forgetting their previous knowledge. In this paper, we propose a novel class of systems that are able to adapt and contextualize the structure of trained DNNs, providing ways for handling the above-mentioned problems. A hierarchical and distributed system memory is generated and used for this purpose. The main memory is composed of the trained DNN architecture for classification/prediction, i.e., its structure and weights, as well as of an extracted - equivalent - Clustered Representation Set (CRS) generated by the DNN during training at its final - before the output - hidden layer. The latter includes centroids - 'points of attraction' - which link the extracted representation to a specific area in the existing system memory. Drift detection, occurring, for example, in personalized data analysis, can be accomplished by comparing the distances of new data from the centroids, taking into account the intra-cluster distances. Moreover, using the generated CRS, the system is able to contextualize its decision-making process, when new data become available. A new public medical database on Parkinson's disease is used as testbed to illustrate the capabilities of the proposed architecture.
KW - adaptation
KW - classification
KW - clustered representation sets
KW - contextualization
KW - Deep neural networks
KW - Parkinson's disease
KW - prediction
UR - http://www.scopus.com/inward/record.url?scp=85046115182&partnerID=8YFLogxK
U2 - 10.1109/SSCI.2017.8280975
DO - 10.1109/SSCI.2017.8280975
M3 - Published conference contribution
AN - SCOPUS:85046115182
T3 - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
SP - 1
EP - 8
BT - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017
Y2 - 27 November 2017 through 1 December 2017
ER -