Deep rule-based classifier with human-level performance and characteristics

Plamen Parvanov Angelov, Xiaowei Gu

Research output: Contribution to journalArticlepeer-review

51 Citations (SciVal)
39 Downloads (Pure)


In this paper, a new type of multilayer rule-based classifier is proposed and applied to image classification problems. The proposed approach is entirely data-driven and fully automatic. It is generic and can be applied to various classification and prediction problems, but in this paper we focus on image processing, in particular. The core of the classifier is a fully interpretable, understandable, self-organized set of IF…THEN… fuzzy rules based on the prototypes autonomously identified by using a one-pass type training process. The classifier can self-evolve and be updated continuously without a full retraining. Due to the prototype-based nature, it is non-parametric; its training process is non-iterative, highly parallelizable and computationally efficient. At the same time, the proposed approach is able to achieve very high classification accuracy on various benchmark datasets surpassing most of the published methods, be comparable with the human abilities. In addition, it can start classification from the first image of each class in the same way as humans do, which makes the proposed classifier suitable for real-time applications. Numerical examples of benchmark image processing demonstrate the merits of the proposed approach.
Original languageEnglish
Pages (from-to)196-213
Number of pages18
JournalInformation Sciences
Early online date21 Jun 2018
Publication statusPublished - 01 Oct 2018
Externally publishedYes


  • Deep learning
  • Fuzzy rule based classifiers
  • Non-iterative
  • Non-parametric
  • Self-evolving structure


Dive into the research topics of 'Deep rule-based classifier with human-level performance and characteristics'. Together they form a unique fingerprint.

Cite this