MU_PSYC : Algorithmic music composition with a music-psychology enriched genetic algorithm
Bibliographic record
Abstract
Recent advancement of artificial intelligence (AI) techniques have impacted the field of algorithmic music composition, and that has been evidenced by live concert performances wherein the audience reportedly often could not tell whether music was composed by machine or by human. Among the various AI techniques, genetic algorithms dominate the field due to their suitability for both creativity and optimization. Many attempts have been made to incorporate rules from traditional music theory to design and automate genetic algorithms. Another popular approach is to incorporate statistical or mathematical measures of fitness. However, these rules and measures are rarely tested for their validity. This thesis is aimed at addressing the above limitation and hence paving the way to advance the field towards composing human-quality music. The basic idea is to look beyond this constrained set of traditional music rules and statistical/mathematical methods towards a more concrete foundation. We look to a field at the intersection of musicology and psychology, referred to as music-psychology. To demonstrate our proposed approach, we implemented a genetic algorithm exclusively using rules found in music-psychology. An online survey was conducted testing the quality of our algorithm’s output compositions. Moreover, algorithm performance was analyzed by experimental study. The initial results are encouraging and warrant further research. The societal implications of our work and other research in the field are also discussed.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".