Error-free Training for MedMNIST Datasets
For biomedical image classification, this work claims error-free training, but the novelty is incremental as it applies an existing concept to new datasets.
The paper introduces Artificial Special Intelligence to train classification models error-free on 18 MedMNIST datasets, achieving perfect training on 15 of them (excluding three with double-labeling issues).
In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be trained error-free, thus acquiring the capability of not making repeated mistakes. The method is applied to 18 MedMNIST biomedical datasets. Except for three datasets, which suffer from the double-labeling problem, all are trained to perfection.