Deep Creations: Intellectual Property and the Automata

Deltorn, Jean-Marc

doi:10.3389/fdigh.2017.00003

Cited by 17 publications

(22 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When represented extensionally, chords are usually encoded with simultaneous notes as a vector. An interesting alternative extensional representation of chords, named Chord2Vec 34 , has recently been proposed in [122] 35 . Rather than thinking of chords (vertically) as vectors, it represents chords (horizontally) as sequences of constituent notes.…”

Section: Chord and Polyphonymentioning

confidence: 99%

“…With a similar objective, the sum units and the activation function units are also almost always omitted, resulting in a more abstract view such as that shown in Figure 5.12. We can further abstract each layer by representing it as an oblong form (by hiding its nodes) 34…”

Section: Abstract Representationmentioning

confidence: 99%

“…One could also do interpolation between several (two or more) plans melodies that have been learnt 34 . Examples are shown in Figure 6 [190] [190] Objective Melody Representation Symbolic; Piano roll; One-hot; Note begin; Implicit rest Architecture RNN Strategy Iterative feedforward Table 6.12 Sequential architecture summary…”

Section: #2 Example: Sequential Melody Symbolic Music Generation Systemmentioning

confidence: 99%

“…Actually, as an optimization, Todd proposes in the following of his description to pass back the target values and not the output values 34. Note that this way of doing is actually some precursor of doing interpolation on embeddings of melodies to be generated by combining a decoder feedforward strategy and an iterative feedforward strategy, such as for example in the VRAE or the MusicVAE systems, to be described in Sections 6.10.2.3 and 6.12.1, respectively.…”

mentioning

confidence: 99%

“…On this issue, see the recent paper by Deltorn[34] 100. Note that this addresses the issue of significant recopying from the training corpus, but it does not prevent a system from reinventing existing music outside of the training corpus.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning Techniques for Music Generation

Briot¹,

Hadjeres²,

Pachet³

2020

Computational Synthesis and Creative Systems

202

148

View full text Add to dashboard Cite

8 As Richard Feynman coined it: "What I cannot create, I do not understand." 9 Initially codified in 1950 by Alan Turing and named by him the "imitation game" [191], the "Turing test" is a test of the ability for a machine to exhibit intelligent behavior equivalent to (and more precisely, indistinguishable from) the behavior of a human. In his imaginary experimental setting, Turing proposed the test to be a natural language conversation between a human (the evaluator) and a hidden actor (another human or a machine). If the evaluator cannot reliably tell the machine from the human, the machine is said to have passed the test. 10 This is to avoid the bias (synthetic flavor) of a computer rendered generated music. 11 Improvisation is a form of real time composition. 12 With some precaution, as this division is not that strict. 13 The general objective of integrating sub-symbolic and symbolic levels into a complete AI system is among the "Holy Grails" of AI. Chapter 2 Method In our analysis, we consider five main dimensions to characterize different ways of applying deep learning techniques to generate musical content. This typology is aimed at helping the analysis of the various perspectives (and elements) leading to the design of different deep learning-based music generation systems 1. 2.1 Dimensions The five dimensions that we consider are as follows. 2.1.1 Objective The objective 2 consists in: • The musical nature of the content to be generated. Examples are a melody, a polyphony or an accompaniment; and • The destination and use of the content generated. Examples are a musical score to be performed by some human musician(s) or an audio file to be played. 2.1.2 Representation The representation is the nature and format of the information (data) used to train and to generate musical content. Examples are signal, transformed signal (e.g., a spectrum, via a Fourier transform), piano roll, MIDI or text. 2.1.3 Architecture The architecture is the nature of the assemblage of processing units (the artificial neurons) and their connexions.

show abstract

Section: Chord and Polyphonymentioning

confidence: 99%

Section: Abstract Representationmentioning

confidence: 99%

Section: #2 Example: Sequential Melody Symbolic Music Generation Systemmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning Techniques for Music Generation

Briot¹,

Hadjeres²,

Pachet³

2020

Computational Synthesis and Creative Systems

202

148

View full text Add to dashboard Cite

show abstract

Deep learning for music generation: challenges and directions

Briot

Pachet²

2018

Neural Comput & Applic

107

View full text Add to dashboard Cite

Copyright in generative deep learning

Giorgio

Musolesi

2022

Data & Policy

View full text Add to dashboard Cite

Machine-generated artworks are now part of the contemporary art scene: they are attracting significant investments and they are presented in exhibitions together with those created by human artists. These artworks are mainly based on generative deep learning (GDL) techniques, which have seen a formidable development and remarkable refinement in the very recent years. Given the inherent characteristics of these techniques, a series of novel legal problems arise. In this article, we consider a set of key questions in the area of GDL for the arts, including the following: is it possible to use copyrighted works as training set for generative models? How do we legally store their copies in order to perform the training process? Who (if someone) will own the copyright on the generated data? We try to answer these questions considering the law in force in both the United States and the European Union, and potential future alternatives. We then extend our analysis to code generation, which is an emerging area of GDL. Finally, we also formulate a set of practical guidelines for artists and developers working on deep learning generated art, as well as some policy suggestions for policymakers.

show abstract

Deep Creations: Intellectual Property and the Automata

Cited by 17 publications

References 29 publications

Deep Learning Techniques for Music Generation

Deep Learning Techniques for Music Generation

Deep learning for music generation: challenges and directions

Copyright in generative deep learning

Contact Info

Product

Resources

About