Frederic Piat
DOCTORAL DISSERTATION
ARTIST: Adaptive Resonance
Theory for the Internalization of the Structure of Tonality (a neural net
listening to music)
ABSTRACT en Francais(.doc)
Take a look at the whole thing, 200 pages (.pdf)
ABSTRACT
After sufficient exposure to music, we naturally
develop a sense of which note sequences are musical and pleasant, even without
being taught anything about music. This is the result of a process of
acculturation that consists of extracting the temporal and tonal regularities
found in the styles of music we hear.
ARTIST, an artificial neural network
based on Grossberg's (1982) Adaptive Resonance Theory, is proposed to model the
acculturation process. The model self-organizes its 2-layer architecture of
neuron-like units through unsupervised learning. Its performance is assessed by
how well it accounts for human data on several tasks, mostly involving
pleasantness ratings of musical sequences.
ARTIST's responses on Krumhansl
and Shepard's (1979) probe-tone technique are virtually identical to humans',
showing that ARTIST successfully extracted the rules of tonality from its
environment. Thus, it distinguishes between tonal vs atonal musical sequences
and can predict their exact degree of tonality or pleasantness. Moreover, as
exposure to music increases, the model's responses to a variation of the
probe-tone task follow the same changes as those of children as they grow up.
ARTIST can further discriminate between several kinds of musical stimuli
within tonal music: its preferences for some musical modes over others resembles
humans'. This resemblance seems limited by the differences between humans' and
ARTIST's musical environment.
The recognition of familiar melodies is also
one of ARTIST's abilities. It is impossible to identify even a very familiar
melody when its notes are interleaved with distractor notes. However, a priori
knowledge regarding the possible identity of the melody enables its
identification, by humans as well as by ARTIST.
ARTIST shares one more
feature with humans, namely the robustness regarding perturbations of the input:
even large random temporal fluctuations in the cycles of presentation of the
inputs do not provoke important degradation of ARTIST's performance.
All of
these characteristics contribute to the plausibility of ARTIST as a model of
musical learning by humans. Expanding the model by adding more layers of neurons
may enable it to develop even more human-like capabilities, such as the
recognition of melodies after transposition.