Portugal

ICCC&#39;20

Philosophy and Evaluation 1

Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviours that unbiased observers would deem to be creative. As a field of research, this area is thriving, with progress in formalising what it means for software to be creative, along with many exciting and valuable applications of creative software in the sciences, the arts, literature, gaming and elsewhere.

The ICCC conference series organized by the Association for Computational Creativity since 2010 is the only scientific conference that focuses on computational creativity alone and also covers all aspects of it.


ICCC'20

The ICCC conference series organized by the Association for Computational Creativity since 2010 is the only scientific conference that focuses on computational creativity alone and also covers all aspects of it.
Computational creativity is the art, science, philosophy and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviors that unbiased observers would deem to be creative. As a field of research, this area is thriving, with progress in formalizing what it means for software to be creative, along with many exciting and valuable applications of creative software in the sciences, the arts, literature, gaming and elsewhere.



technical paper

From classifying handwritten digits to generating strings of text, the datasets which have received long-time focus from the machine learning community vary greatly in their subject matter. This has motivated a renewed interest in building datasets which are socially and culturally relevant, so that algorithmic research may have a more direct and immediate impact on society. One such area is in history and the humanities, where better and relevant machine learning models can accelerate research across various fields. To this end, newly released benchmarks and models have been proposed for transcribing historical Japanese cursive writing, yet for the field as a whole using machine learning for historical Japanese artworks still remains largely uncharted. To bridge this gap, in this work we propose a new dataset KaoKore which consists of faces extracted from pre-modern Japanese artwork. We demonstrate its value as both a dataset for image classification as well as a creative and artistic dataset, which we explore using generative models. Dataset available at https://github.com/rois-codh/kaokore

KaoKore: A Pre-modern Japanese Art Facial Expression Dataset

In his work “Mere Generation: Essential Barometer or Dated Concept?”, Ventura (Ventura 2016) categorizes creative processes along a spectrum of increasing creativity. While the spectrum provides insight into the dimensions through which creativity can be augmented, it does not of itself provide insights into how to advance a system through these dimensions. In this paper, we present some theoretical and practical insights on advancing along one commonly problematic rung of this ladder, namely from a system that exhibits generalization (i.e., the ability to generalize beyond an inspiring set) to a system that exhibits filtration (i.e., the ability to self-evaluate and filter results). One potential challenge in this transition is that filtration requires having a sufficiently large number of solutions to filter from the generalizing model. We propose that one solution to this problem is achieved not through increasing the size of the inspiring set (an obvious solution that brings additional problems), but rather through amplifying the generalization of the system to produce a greater set of novel artefacts to filter. We compare a new version of a system, NhMMonic, for generating creative mnemonic devices with a new conceptualization model that allows greater generalization. We demonstrate how filtration, which was not possible in the early version of NhMMonic, only becomes feasible with the more generalizable model.

A Leap of Creativity: From Systems that Generalize to Systems that Filter

"Neural style transfer is a popular deep learning algorithm to generate images to mimic human artistry. This work applies the psychological method of the two-alternative forced choice (2afc) task to measure aesthetic preferences for neural style generated images.
Portrait photos of three popular celebrities were generated by varying three parameters of neural style transfer in five configuration levels. Participants had to choose the image they preferred aesthetically from all pairwise combinations of con-figurations per style. The rate of being chosen was calculated for each neural style transfer configuration level. The findings show a differentiated picture of aesthetic preferences. On the one side, they indicate that people prefer images rendered with 500 iterations and a learning rate of 2e1, i.e. configurations that allow them to recognize the structure of the portrait image despite the stylization. On the other side, aesthetic preferences peak for two distinctly differ-ent content-to-style weight ratios. Whereas the medium-high configuration (100:100) may be favored by people who like abstract arts, the high configuration (300:100) may be chosen by people who prefer realistic art.
These results indicate that aesthetic preferences for neural style transfer-generated images can be characterized by unique pat-terns, and their optimal configuration levels can be captured by the 2afc task. "

Downloads

Next from ICCC'20

KaoKore: A Pre-modern Japanese Art Facial Expression Dataset

Similar lecture

Philosophy and Evaluation 2

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ICCC'20

KaoKore: A Pre-modern Japanese Art Facial Expression Dataset

Similar lecture

Philosophy and Evaluation 2

Downloads