English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper we introduce the DMR -- a prototype-based method and networkarchitecture for deep learning which is using a decision tree (DT)-basedinference and synthetic data to balance the classes. It builds upon therecently introduced xDNN method addressing more complex multi-class problems,specifically when classes are highly imbalanced. DMR moves away from a directdecision based on all classes towards a layered DT of pair-wise classcomparisons. In addition, it forces the prototypes to be balanced betweenclasses regardless of possible class imbalances of the training data. It hastwo novel mechanisms, namely i) using a DT to determine the winning classlabel, and ii) balancing the classes by synthesizing data around the prototypesdetermined from the available training data. As a result, we improvedsignificantly the performance of the resulting fully explainable DNN asevidenced by the best reported result on the well know benchmark problemCaltech-101 surpassing our own recently published "world record". Furthermore,we also achieved another "world record" for another very hard benchmarkproblem, namely Caltech-256 as well as surpassed the results of otherapproaches on Faces-1999 problem. In summary, we propose a new approachspecifically advantageous for imbalanced multi-class problems that achieved twoworld records on well known hard benchmark problems and the best result onanother problem in terms of accuracy. Moreover, DMR offers full explainability,does not require GPUs and can continue to learn from new data by adding newprototypes preserving the previous ones but not requiring full retraining.

Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference