Authors:
Dušan Medera
1
and
Štefan Babinec
2
Affiliations:
1
Technical University of Košice, Slovak Republic
;
2
Slovak University of Technology, Slovak Republic
Keyword(s):
Convolutional neural networks, Incremental learning, Handwritten numbers classification.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Computational Neuroscience
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Image Processing
;
Informatics in Control, Automation and Robotics
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Robotics and Automation
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Supervised and Unsupervised Learning
;
Theory and Methods
Abstract:
Convolutional neural networks provide robust feature extraction with ability to learn complex, highdimensional non-linear mappings from collection of examples. To accommodate new, previously unseen data, without the need of retraining the whole network architecture we introduce an algorithm for incremental learning. This algorithm was inspired by AdaBoost algorithm. It utilizes ensemble of modified convolutional neural networks as classifiers by generating multiple hypotheses. Furthermore, with this algorithm we can work with the confidence score of classification, which can play crucial importance in specific real world tasks. This approach was tested on handwritten numbers classification. The classification error achieved by this approach was highly comparable with non-incremental learning.