Creativity and Machine Learning: A Survey

Giorgio, Franceschelli,; Musolesi, Mirco

doi:10.48550/arxiv.2104.02726

Cited by 11 publications

(15 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the years, several computational approaches have been proposed to automatically assess the creativity in products made by (human or artificial) agents, differing in the scope of evaluation or in the method. A complete survey can be found in [13]. All of them consider value and novelty as aspects of creativity, while only some of them also consider surprise.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

DeepCreativity: Measuring Creativity with Deep Learning Techniques

Giorgio¹,

Musolesi²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Measuring machine creativity is one of the most fascinating challenges in Artificial Intelligence. This paper explores the possibility of using generative learning techniques for automatic assessment of creativity. The proposed solution does not involve human judgement, it is modular and of general applicability. We introduce a new measure, namely DeepCreativity, based on Margaret Boden's definition of creativity as composed by value, novelty and surprise. We evaluate our methodology (and related measure) considering a case study, i.e., the generation of 19th century American poetry, showing its effectiveness and expressiveness.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The goal is to define a measure of more general applicability. Deep Learning is used for avoiding the need of identifying the required attributes to describe the artifacts or the components of creativity [13]. This leads to a measure that allows for automatic evaluation of artifacts.…”

Section: Measuring Creativity Using Deep Learningmentioning

confidence: 99%

DeepCreativity: Measuring Creativity with Deep Learning Techniques

Giorgio¹,

Musolesi²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several generative models based on deep learning have been proposed in last years (for a more exhaustive list, see Franceschelli and Musolesi (2021)). However, it is possible to identify a few families of techniques: Variational Auto-Encoders (first proposed by Kingma and Welling (2014), but also used by Gregor et al (2015)); autoregressive models (first proposed by Van Den Oord et al (2016b), but also used by Van Den Oord et al (2016a,c) 2020)); sequence prediction models (very well explained by Karpathy (2015), and used by Zhang and Lapata (2014); Potash et al (2015); Sturm et al (2016); Jaques et al (2016); Lau et al (2018); Yi et al (2018); Zugarini et al (2019)); Generative Adversarial Nets (first proposed by Goodfellow et al (2014) and then used by Vernier et al (2020); modifications of the first proposal have been done by Yu et al (2017); Dong et al (2018); Elgammal et al (2017); Isola et al (2017); Karras et al (2018); Zhang et al (2019); Brock et al (2018); Karras et al (2019); Engel et al (2019)).…”

Section: Generative Deep Learningmentioning

confidence: 99%

Copyright in Generative Deep Learning

Giorgio¹,

Musolesi²

2021

Preprint

Self Cite

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 techniques. Also given their success, several legal problems arise when working with these techniques. In this article we consider a set of key questions in the area of generative deep learning for the arts. 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? And then, who (if someone) will own the copyright on the generated data? We try to answer these questions considering the law in force in both US and EU and the future alternatives, trying to define a set of guidelines for artists and developers working on deep learning generated art.

show abstract

“…There are also challenges regarding evaluation of the models. Except for generating paintings that reflect the semantics of poems and the painting style of the artist, creativity is also an important criteria and it is unclear how to evaluate the creativity yet [12].…”

Section: Zikai-poemmentioning

confidence: 99%

“…Therefore creativity should be considered as another important criteria except for pictorial quality, stylistic relevance, semantic relevance. Yet, modelling and evaluating creativity is challenging and still at its early stage [12].…”

Section: Research Challenges and Future Workmentioning

confidence: 99%

Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poems

Li,

Wang,

Zou

et al. 2021

Preprint

View full text Add to dashboard Cite

In this work we propose a new task -artistic visualization of classical Chinese poems, where the goal is to generate paintings of a certain artistic style for classical Chinese poems. For this purpose, we construct a new dataset called Paint4Poem. The first part of Paint4Poem consists of 301 high-quality poem-painting pairs collected manually from an influential modern Chinese artist Feng Zikai. As its small scale poses challenges for effectively training poem-to-painting generation models, we introduce the second part of Paint4Poem, which consists of 3,648 caption-painting pairs collected manually from Feng Zikai's paintings and 89,204 poem-painting pairs collected automatically from the web. We expect the former to help learning the artist painting style as it contains his most paintings, and the latter to help learning the semantic relevance between poems and paintings. Further, we analyze Paint4Poem regarding poem diversity, painting style, and the semantic relevance between poems and paintings. We create a benchmark for Paint4Poem: we train two representative text-to-image generation models -AttnGAN and MirrorGAN, and evaluate their performance regarding painting pictorial quality, painting stylistic relevance, and semantic relevance between poems and paintings. The results indicate that the models are able to generate paintings that have good pictorial quality and mimic Feng Zikai's style, but the reflection of poem semantics is limited. The dataset also poses many interesting research directions on this task, including transfer learning, few-shot learning, text-to-image generation for low-resource data etc. The dataset is publicly available. (https://github.com/paint4poem/paint4poem)

show abstract

Creativity and Machine Learning: A Survey

Cited by 11 publications

References 54 publications

DeepCreativity: Measuring Creativity with Deep Learning Techniques

DeepCreativity: Measuring Creativity with Deep Learning Techniques

Copyright in Generative Deep Learning

Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poems

Contact Info

Product

Resources

About