Moonlight in Latent Space: Chirality and Structural Correspondence Between Beethoven's Op. 27 No. 2 and Machine Learning Mechanisms

• URL: http://arxiv.org/abs/2606.14612v1
• Date: Fri, 12 Jun 2026 16:35:17 GMT
• Title: Moonlight in Latent Space: Chirality and Structural Correspondence Between Beethoven's Op. 27 No. 2 and Machine Learning Mechanisms
• Abstract summary: We show that the three movements of Beethoven's "Moonlight Sonata" instantiate three distinct machine learning architectures.<n>We quantify the chirality of the encode-decode cycle: what distributions preserve and sequential ordering destroys.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We show that the three movements of Beethoven's "Moonlight Sonata" (Op. 27 No. 2) instantiate three distinct machine learning architectures -- not by analogy, but by structural correspondence. Through computational analysis of the score (entropy, Jensen-Shannon divergence, dissonance, hand distributional overlap, self-similarity matrices, temporal memory decay, and contextual pitch embeddings), we establish four counterintuitive findings: (1) perceived musical "temperature" is governed by throughput, not distributional width; (2) the lightest movement carries the highest dissonance; (3) the movements implement streaming, recurrent, and periodic positional encoding memory architectures; and (4) the same pitch class acquires different contextual identities across movements, analogous to contextual vs.static embeddings in NLP -- and unsupervised clustering recovers the tonal structure without music-theoretic input. We construct a reverse sonification (decoding analytical features back into MIDI) and quantify the chirality of the encode-decode cycle: what distributions preserve and sequential ordering destroys. Prompted by a listener's observation that the decoded piece sounds like "mirror isomers that can't be superimposed," the chirality measurement reveals reconstruction loss increasing monotonically with n-gram order. Bootstrap baselines and subsample checks confirm all movements carry sequential information above noise, though raw values are confounded by sample size. Cross-domain comparison shows natural language has higher chirality than music, reflecting stronger sequential constraints.

Related papers

• MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music [1.218340575383456]
  We present MIDI-RAE-JEPA, combining a pitch- and time-shift equivariance objective with LeJEPA and a Swin Transformer V2 encoder.<n>We learn such hierarchical representations of symbolic music encoded as piano roll images.<n>Results suggest that equivariance-based SSL objectives, combined with sufficient fine-level encoder capacity, provide a viable path toward semantically rich, generatively useful representations of symbolic music.
  arXiv  Detail & Related papers  (2026-07-16T03:42:35Z)
• Rhythm of the Deep: A Computational-Linguistic Test of Duality of Patterning in Sperm Whale Codas [0.0]
  We test for this design feature, duality of patterning, in sperm whale codas using 1,483 codas from the Dominica Sperm Whale Project.<n>Because acoustic similarity can imitate symbolic structure, we treat the problem as computational-linguistic structure from continuous audio.<n>We do not claim language, semantics, perception, or human-like phonemes.
  arXiv  Detail & Related papers  (2026-06-15T00:49:18Z)
• SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton [26.272034375469943]
  SymphonyGen is a 3D hierarchical framework for cinematic orchestration.<n>We introduce "short-score" conditioning via a beat-quantized multi-voice harmony skeleton.<n>We implement a dissonance-averse sampling algorithm to suppress unintended tonal clashes.
  arXiv  Detail & Related papers  (2026-04-28T11:01:21Z)
• On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking [49.1352577985191]
  We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task.<n>Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training dynamics.
  arXiv  Detail & Related papers  (2026-02-18T20:25:13Z)
• Selective Imperfection as a Generative Framework for Analysis, Creativity and Discovery [1.3537117504260623]
  We show how sound functions as a scientific probe, an inversion where listening becomes a mode of seeing and musical composition becomes a blueprint for matter.<n>We show that science and art are generative acts of world-building under constraint, with vibration as a shared grammar organizing structure across scales.
  arXiv  Detail & Related papers  (2025-12-30T11:14:51Z)
• Discovering "Words" in Music: Unsupervised Learning of Compositional Sparse Code for Symbolic Music [50.87225308217594]
  This paper presents an unsupervised machine learning algorithm that identifies recurring patterns -- referred to as music-words'' -- from symbolic music data.<n>We formulate the task of music-word discovery as a statistical optimization problem and propose a two-stage Expectation-Maximization (EM)-based learning framework.
  arXiv  Detail & Related papers  (2025-09-29T11:10:57Z)
• DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling [70.79846001735547]
  We present DuetGen, a framework for generating interactive two-person dances from music.<n>Inspired by the recent advances in motion synthesis, we propose a two-stage solution.<n>We represent both dancers' motions as a unified whole to learn the necessary motion tokens.
  arXiv  Detail & Related papers  (2025-06-23T14:22:50Z)
• Synthia's Melody: A Benchmark Framework for Unsupervised Domain Adaptation in Audio [4.537310370334197]
  We present Synthia's melody, a novel audio data generation framework capable of simulating an infinite variety of 4-second melodies. Unlike existing datasets collected under observational settings, Synthia's melody is free of unobserved biases. Our evaluations reveal that Synthia's melody provides a robust testbed for examining the susceptibility of these models to varying levels of distribution shift.
  arXiv  Detail & Related papers  (2023-09-26T15:46:06Z)
• Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks [50.2033914945157]
  We present a representation learning framework, Intensity Profile Projection, for continuous-time dynamic network data. The framework consists of three stages: estimating pairwise intensity functions, learning a projection which minimises a notion of intensity reconstruction error. Moreoever, we develop estimation theory providing tight control on the error of any estimated trajectory, indicating that the representations could even be used in quite noise-sensitive follow-on analyses.
  arXiv  Detail & Related papers  (2023-06-09T15:38:25Z)
• A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis [13.263771543118994]
  We propose a unified model for three inter-related tasks: 1) to textitseparate individual sound sources from a mixed music audio, 2) to textittranscribe each sound source to MIDI notes, and 3) totextit synthesize new pieces based on the timbre of separated sources. The model is inspired by the fact that when humans listen to music, our minds can not only separate the sounds of different instruments, but also at the same time perceive high-level representations such as score and timbre.
  arXiv  Detail & Related papers  (2021-08-07T14:28:21Z)
• Sequence Generation using Deep Recurrent Networks and Embeddings: A study case in music [69.2737664640826]
  This paper evaluates different types of memory mechanisms (memory cells) and analyses their performance in the field of music composition. A set of quantitative metrics is presented to evaluate the performance of the proposed architecture automatically.
  arXiv  Detail & Related papers  (2020-12-02T14:19:19Z)
• Vector-Quantized Timbre Representation [53.828476137089325]
  This paper targets a more flexible synthesis of an individual timbre by learning an approximate decomposition of its spectral properties with a set of generative features. We introduce an auto-encoder with a discrete latent space that is disentangled from loudness in order to learn a quantized representation of a given timbre distribution. We detail results for translating audio between orchestral instruments and singing voice, as well as transfers from vocal imitations to instruments.
  arXiv  Detail & Related papers  (2020-07-13T12:35:45Z)
• Continuous Melody Generation via Disentangled Short-Term Representations and Structural Conditions [14.786601824794369]
  We present a model for composing melodies given a user specified symbolic scenario combined with a previous music context. Our model is capable of generating long melodies by regarding 8-beat note sequences as basic units, and shares consistent rhythm pattern structure with another specific song. Results show that the music generated by our model tends to have salient repetition structures, rich motives, and stable rhythm patterns.
  arXiv  Detail & Related papers  (2020-02-05T06:23:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.