Musical composer identification through probabilistic and feedforward neural networks

Authors:
Maximos A. Kaliakatsos-Papakostas;Michael G. Epitropakis;Michael N. Vrahatis
Affiliations:
Computational Intelligence Laboratory (CI Lab), Department of Mathematics, University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, Patras, Greece;Computational Intelligence Laboratory (CI Lab), Department of Mathematics, University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, Patras, Greece;Computational Intelligence Laboratory (CI Lab), Department of Mathematics, University of Patras Artificial Intelligence Research Center (UPAIRC), University of Patras, Patras, Greece
Venue:
EvoCOMNET'10 Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part II
Year:
2010

Citing 11
Cited 2

Probabilistic neural networks

Neural Networks
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Parallel evolutionary training algorithms for “hardware-friendly“ neural networks

Natural Computing: an international journal
Classification of Melodies by Composer with Hidden Markov Models

WEDELMUSIC '01 Proceedings of the First International Conference on WEB Delivering of Music (WEDELMUSIC'01)
Evolutionary training of hardware realizable multilayer perceptrons

Neural Computing and Applications
Algorithms for Chordal Analysis

Computer Music Journal
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)

Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
Tonal Description of Polyphonic Audio for Music Content Processing

INFORMS Journal on Computing
Novel Approaches to Probabilistic Neural Networks Through Bagging and Evolutionary Estimating of Prior Probabilities

Neural Processing Letters
Recognition of Western style musical genres using machine learning techniques

Expert Systems with Applications: An International Journal

Weighted Markov chain model for musical composer identification

EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part II
Feature extraction using pitch class profile information entropy

MCM'11 Proceedings of the Third international conference on Mathematics and computation in music

Quantified Score

Hi-index	0.00

Visualization

Abstract

During the last decade many efforts for music information retrieval have been made utilizing Computational Intelligence methods. Here, we examine the information capacity of the Dodecaphonic Trace Vector for composer classification and identification. To this end, we utilize Probabilistic Neural Networks for the construction of a “similarity matrix” of different composers and analyze the Dodecaphonic Trace Vector's ability to identify a composer through trained Feedforward Neural Networks. The training procedure is based on classical gradient-based methods as well as on the Differential Evolution algorithm. An experimental analysis on the pieces of seven classical composers is presented to gain insight about the most important strengths and weaknesses of the aforementioned approach.