Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers

TL;DR

This paper demonstrates that recurrent neural networks combined with conceptors enable rapid learning with minimal data, achieving high accuracy in speech recognition and car maneuver detection, surpassing existing methods.

Contribution

The study introduces a novel approach combining RNNs and conceptors for fast, data-efficient learning in speech and driving applications, with application-specific optimizations.

Findings

High accuracy with few training examples

Improved speech recognition using mel frequency cepstral coefficients

Effective car maneuver detection without polynomial interpolation

Abstract

Recurrent neural networks are a powerful means in diverse applications. We show that, together with so-called conceptors, they also allow fast learning, in contrast to other deep learning methods. In addition, a relatively small number of examples suffices to train neural networks with high accuracy. We demonstrate this with two applications, namely speech recognition and detecting car driving maneuvers. We improve the state of the art by application-specific preparation techniques: For speech recognition, we use mel frequency cepstral coefficients leading to a compact representation of the frequency spectra, and detecting car driving maneuvers can be done without the commonly used polynomial interpolation, as our evaluation suggests.