Title :
Composing Music with BPTT and LSTM Networks: Comparing Learning and Generalization Aspects
Author :
Correa, Debora C. ; Saito, Josê H. ; Abib, Sandra
Author_Institution :
Abib Univ. Fed. de Sao Carlos, Sao Paolo
Abstract :
Many researchers have used neural networks on music composition. The architecture of the network and the representation of the training data have influence on the results. We propose to compare BPTT and LSTM networks in musical composition task with two different pitch representations. We present the learning algorithms of both networks and the results obtained in the composition of new melodies.
Keywords :
learning (artificial intelligence); music; neural nets; BPTT networks; LSTM networks; learning algorithm; music composition; neural networks; pitch representation; Artificial neural networks; Biological neural networks; Computer networks; Conferences; Data mining; Frequency; Image converters; Neurons; Pattern analysis; Training data; Learning Algorithms; Music Composition; Neural Networks;
Conference_Titel :
Computational Science and Engineering Workshops, 2008. CSEWORKSHOPS '08. 11th IEEE International Conference on
Conference_Location :
San Paulo
Print_ISBN :
978-0-7695-3257-8
DOI :
10.1109/CSEW.2008.69
