Voting with random classifiers (VORACE): theoretical and experimental analysis

Abstract

In many machine learning scenarios, looking for the best classifier that fits a particular dataset can be very costly in terms of time and resources. Moreover, it can require deep knowledge of the specific domain. We propose a new technique which does not require profound expertise in the domain and avoids the commonly used strategy of hyper-parameter tuning and model selection. Our method is an innovative ensemble technique that uses voting rules over a set of randomly-generated classifiers. Given a new input sample, we interpret the output of each classifier as a ranking over the set of possible classes. We then aggregate these output rankings using a voting rule, which treats them as preferences over the classes. We show that our approach obtains good results compared to the state-of-the-art, both providing a theoretical analysis and an empirical evaluation of the approach on several datasets.

Deep Semantic Segmentation in Skin Detection

“…The performance of the ensemble is better than the performance of the single individual classifiers used as baselines. These results support the evidence that different individual classifiers can generalize differently in the training space leading to an improvement in the final performance of the ensemble [24]. This can be achieved by either varying the type of data augmentation or the kind of individual classifiers.…”

Machine learning method for the classification of the state of living organisms’ oscillations

“…Our approach resembles “voting” classification approaches ( Cornelio et al 2021 , or Anton et al 2023 ), where several classifiers are applied, and the predicted class is one predicted by the largest number of the classifiers. In turn, we divide the observation into many smaller chunks and apply the same classifier to each chunk.…”

SenTag: A Web-Based Tool for Semantic Annotation of Textual Documents

“…We presented SenTag a new lightweight web-based tool focused on semantic annotation of textual documents. As future work, we plan to embed into the system artificial intelligence techniques (such as ensemble methods (Cornelio et al 2021)) with the goal of automating some parts of tagging.…”