Title :
Memorization of melodies by complex-valued recurrent network
Author :
Kinouchi, Makoto ; Hagiwara, Masafumi
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
Memorization of the temporal sequences is very important and interesting problem. One of the examples is memorization of melodies. When we memorize melodies, we can recall it from a part. The function can be considered as an associative memory of the temporal sequences. From a technical point of view, it can be considered that the rest of the melody can be determined by some leading some notes. In this paper, we apply the complex-valued recurrent network, which has much superior ability to deal with temporal sequences than the conventional real-valued networks, to memorization of melodies. It is shown in computer simulations that the network can memorize some melodies and recall them correctly from any part
Keywords :
content-addressable storage; music; recurrent neural nets; associative memory; complex-valued recurrent network; leading notes; melody memorization; neural network; temporal sequences; Associative memory; Biological neural networks; Computer simulation; Motion pictures; Neurofeedback; Neurons; Nonhomogeneous media; Process control; Spatial databases; Speech;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549090