DeepCreativity: Measuring Creativity with Deep Learning Techniques

01/16/2022
by   Giorgio Franceschelli, et al.
0

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.

READ FULL TEXT
research
12/09/2020

Machine Learning for Cataract Classification and Grading on Ophthalmic Imaging Modalities: A Survey

Cataract is one of the leading causes of reversible visual impairment an...
research
06/06/2018

Quantitative Phase Imaging and Artificial Intelligence: A Review

Recent advances in quantitative phase imaging (QPI) and artificial intel...
research
11/11/2022

REVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of study

Explainable artificial intelligence is proposed to provide explanations ...
research
06/07/2023

Human in the Loop Novelty Generation

Developing artificial intelligence approaches to overcome novel, unexpec...
research
12/11/2018

Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity

The common view that our creativity is what makes us uniquely human sugg...
research
12/24/2015

Measuring pattern retention in anonymized data -- where one measure is not enough

In this paper, we explore how modifying data to preserve privacy affects...

Please sign up or login with your details

Forgot password? Click here to reset