Learning audio and image representations with bio-inspired trainable feature extractors
This addresses the need for representation learning with limited labeled data, though it appears incremental as it builds on existing bio-inspired and feature extraction concepts.
The paper tackles the problem of learning data representations from single prototype samples by proposing novel trainable feature extractors, demonstrating their effectiveness on audio and image benchmark datasets.
Recent advancements in pattern recognition and signal processing concern the automatic learning of data representations from labeled training samples. Typical approaches are based on deep learning and convolutional neural networks, which require large amount of labeled training samples. In this work, we propose novel feature extractors that can be used to learn the representation of single prototype samples in an automatic configuration process. We employ the proposed feature extractors in applications of audio and image processing, and show their effectiveness on benchmark data sets.