Skip to main content

MICE: Multi-Layer Multi-Model Images Classifier Ensemble

Angelov, Plamen, Gu, Xiaowei (2017) MICE: Multi-Layer Multi-Model Images Classifier Ensemble. In: 2017 3rd IEEE International Conference on Cybernetics (CYBCONF). . pp. 1-8. IEEE ISBN 978-1-5386-2202-5. (doi:10.1109/CYBConf.2017.7985788) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:90130)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
https://doi.org/10.1109/CYBConf.2017.7985788

Abstract

In this paper, a new type of fast deep learning (DL) network for handwriting recognition is proposed. In contrast to the existing DL networks, the proposed approach has a clearly interpretable structure that is entirely data- driven and free from user- or problem-specific assumptions. Firstly, the fundamental image transformation techniques (rotation and scaling) used by other existing DL methods are used to improve the generalization. The commonly used descriptors are then used to extract the global features from the training set and based on them a bank/ensemble of zero order AnYa type fuzzy rule-based (FRB) models is built in parallel through the recently introduced Autonomous Learning Multiple Model (ALMMo) method. The final decision about the winning class label is made by a committee on the basis of the fuzzy mixture of the trained zero order ALMMo models. The training of the proposed MICE system is very efficient and highly parallelizable. It significantly outperforms the best-known methods in terms of time and is on par in terms of precision/accuracy. Critically, it offers a high level of interpretability, transparency of the classification model, full repeatability (unlike the methods that use probabilistic elements) of the results. Moreover, it allows an evolving scenario whereby the data is provided in an incremental, online manner and the system structure evolves in parallel with the classification which opens opportunities for online and real-time applications (on a sample by sample basis). Numerical examples from the well-known handwritten digits recognition problem (MNIST) were used and the results demonstrated the very high repeatable performance after a very short training process exhibiting high level of interpretability, transparency.

Item Type: Conference or workshop item (Paper)
DOI/Identification number: 10.1109/CYBConf.2017.7985788
Uncontrolled keywords: Training; Distortion; Handwriting recognition; Feature extraction; Interpolation; Computer architecture
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Amy Boaler
Date Deposited: 10 Sep 2021 10:42 UTC
Last Modified: 13 Sep 2021 10:47 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/90130 (The current URI for this page, for reference purposes)
  • Depositors only (login required):