Musical Instrument Classification using Democratic Liquid State Machines

The Liquid State Machine (LSM) is a relatively new recurrent neural network architecture, in which a static recurrent spiking neural network referred to as a ‘liquid’ and a trainable read-out network are combined to tackle time-series data. In this paper we describe the Democratic Liquid State Machine (DLSM) that uses an ensemble of single LSMs. We investigated the feasibility of the two LSM architectures as a complex spectrum analyzer over a broad frequency range using a musical instrument classification task in which bass guitar and flute had to be recognized by timbre. The experiments showed that single LSMs correctly classified 96% of all test samples, whereas the DLSMs classified 99% of all test samples correctly, improving overall performance to near perfection.

[1]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[2]  S. Hochreiter.  Recurrent Neural Net Learning and Vanishing , 1998 .

[3]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[4]  Yoav Freund,et al.  Boosting the margin: A new explanation for the effectiveness of voting methods , 1997, ICML.

[5]  Jilles Vreeken,et al.  Dynamic neural networks, comparing spiking circuits and LSTM , 2003 .

[6]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[7]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[8]  Jilles Vreeken,et al.  On real-world temporal pattern recognition using Liquid State Machines , 2003 .

[9]  Jürgen Schmidhuber,et al.  A robot that reinforcement-learns to identify and memorize important previous observations , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[10]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[11]  Alex Waibel,et al.  Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[12]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[13]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[14]  Gaël Richard,et al.  Musical instrument recognition based on class pairwise feature selection , 2004, ISMIR.

[15]  Michael I. Jordan,et al.  Hierarchies of Adaptive Experts , 1991, NIPS.

[16]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[17]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[18]  Leon O. Chua,et al.  Fading memory and the problem of approximating nonlinear operators with volterra series , 1985 .

[19]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.