Towards machine learning as an enabler of computational creativity

D Mateja, A Heinzl - IEEE Transactions on Artificial Intelligence, 2021 - ieeexplore.ieee.org
Computational creativity composes a collection of activities that are capable of achieving or
simulating behaviors, which can be deemed creative. A frequently articulated criticism for …

[PDF][PDF] On the power of special-purpose GPT models to create and evaluate new poetry in old styles

P Sawicki, M Grzes, LF Góes, D Brown, M Peeperkorn… - 2023 - figshare.le.ac.uk
ThisstudyinvestigatesthepossibilityofusingG…-3 modelstogeneratehigh-
qualitypoemsinaspecificauthor'sstyle, throughfine-tuningondatasetsofpoems accompaniedbytheirmetadataandautomatic …

[PDF][PDF] Incorporating Algorithmic Information Theory into Fundamental Concepts of Computational Creativity.

T Mondol, DG Brown - ICCC, 2021 - computationalcreativity.net
Can we attribute creativity to an artifact by examining its computational history? What can be
said about its value and novelty if the artifact is computationally laborious and interesting …

The Ai music generation challenge 2020: Double jigs in the style of'O'Neill's 1001'

BLT Sturm, H Maruri-Aguilar - Journal of Creative Music …, 2021 - search.informit.org
This article describes and analyses the Ai Music Generation Challenge 2020, where seven
participants competed to build artificial systems that generate the most plausible double jigs …

Quantifying musical style: Ranking symbolic music based on similarity to a style

J Ens, P Pasquier - arXiv preprint arXiv:2003.06226, 2020 - arxiv.org
Modelling human perception of musical similarity is critical for the evaluation of generative
music systems, musicological research, and many Music Information Retrieval tasks …

Training GPT-2 to represent two Romantic-era authors: challenges, evaluations and pitfalls

P Sawicki, M Grzes, A Jordanous, D Brown… - 2022 - kar.kent.ac.uk
Poetry generation within style constraints has many creative challenges, despite the recent
advances in Transformer models for text generation. We study 1) how overfitting of various …

Computational creativity and aesthetics with algorithmic information theory

T Mondol, DG Brown - Entropy, 2021 - mdpi.com
We build an analysis based on the Algorithmic Information Theory of computational creativity
and extend it to revisit computational aesthetics, thereby, improving on the existing efforts of …

Is style reproduction a computational creativity task?

DG Brown, A Jordanous - 2022 - kar.kent.ac.uk
Is style reproduction a valid computational creativity task? Does producing output'in the style
of'an existing creator contribute to computational creativity research? Where is the creativity …

Grammar-based Compression and its use in Symbolic Music Analysis

T Mondol, DG Brown - Journal of Mathematics and Music, 2023 - Taylor & Francis
We apply Context-free Grammars (CFG) to measure the structural information content of a
symbolic music string. CFGs are appropriate to this domain because they highlight …

[PDF][PDF] Ethics, Aesthetics and Computational Creativity.

D Brown, D Ventura - ICCC, 2022 - computationalcreativity.net
We explore how the aesthetic lens of computational creativity can be used to aid in the
development of ethical principles for artificial intelligence systems, and their application to …