Associative Self-Organizing Map Research Articles

Simulating music with associative self-organizing maps

Abstract We present an architecture able to recognise pitches and to internally simulate likely continuations of partially heard melodies. Our architecture consists of a novel version of the Associative Self-Organizing Map (A-SOM) with generalized ancillary connections. We tested the performance of our architecture with melodies from a publicly available database containing 370 Bach chorale melodies. The results showed that the architecture could learn to represent and perfectly simulate the remaining 20% of three different interrupted melodies when using a context length of 8 centres of activity in the A-SOM. These promising and encouraging results show that our architecture offers something more than what has previously been proposed in the literature. Thanks to the inherent properties of the A-SOM, our architecture does not predict the most likely next pitch only, but rather continues to elicit activity patterns corresponding to the remaining parts of interrupted melodies by internal simulation.

SARASOM: a supervised architecture based on the recurrent associative SOM

We present and evaluate a novel supervised recurrent neural network architecture, the SARASOM, based on the associative self-organizing map. The performance of the SARASOM is evaluated and compared with the Elman network as well as with a hidden Markov model (HMM) in a number of prediction tasks using sequences of letters, including some experiments with a reduced lexicon of 15 words. The results were very encouraging with the SARASOM learning better and performing with better accuracy than both the Elman network and the HMM.