A Novel Approach for Effective Learning in Low Resourced Scenarios
This addresses the challenge of applying state-of-the-art machine learning in data-scarce settings, though it appears incremental as it builds on existing discriminative methods.
The paper tackles the problem of deep learning's ineffectiveness with low data by proposing a simultaneous two sample learning (s2sL) framework, which improves classification performance in low-resource and imbalanced scenarios, as demonstrated in speech/music discrimination and emotion classification experiments.
Deep learning based discriminative methods, being the state-of-the-art machine learning techniques, are ill-suited for learning from lower amounts of data. In this paper, we propose a novel framework, called simultaneous two sample learning (s2sL), to effectively learn the class discriminative characteristics, even from very low amount of data. In s2sL, more than one sample (here, two samples) are simultaneously considered to both, train and test the classifier. We demonstrate our approach for speech/music discrimination and emotion classification through experiments. Further, we also show the effectiveness of s2sL approach for classification in low-resource scenario, and for imbalanced data.