Learning audio and image representations with bio-inspired trainable feature extractors

TL;DR

This paper introduces bio-inspired trainable feature extractors for audio and image data that can learn representations from single prototypes, reducing reliance on large labeled datasets and demonstrating effectiveness on benchmark datasets.

Contribution

The paper presents novel bio-inspired feature extractors capable of learning from single prototype samples, offering an alternative to deep learning methods requiring extensive labeled data.

Findings

Effective on benchmark datasets for audio and image processing

Can learn from single prototype samples

Demonstrates competitive performance compared to traditional methods

Abstract

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.