Portugal

&quot;Recently, models in Computational Cognitive Neuroscience (CCN) have gained a renewed interest because they could help analyze current limitations in Artificial
Intelligence (AI) and propose operational ways to address them. These limitations are related to difficulties in giving a semantic grounding to manipulated concepts,
in coping with high dimensionality and in managing uncertainty. In this paper, we describe the main principles and mechanisms of these models and explain that they can be directly transferred to Computational Creativity (CC), to propose operational mechanisms but also a better understanding of what creativity is.&quot;

ICCC&#39;20

Creativity explained by Computational Cognitive Neuroscience

cognitive neuroscience

brain model

artificial intelligence

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.



"Recently, models in Computational Cognitive Neuroscience (CCN) have gained a renewed interest because they could help analyze current limitations in Artificial
Intelligence (AI) and propose operational ways to address them. These limitations are related to difficulties in giving a semantic grounding to manipulated concepts,
in coping with high dimensionality and in managing uncertainty. In this paper, we describe the main principles and mechanisms of these models and explain that they can be directly transferred to Computational Creativity (CC), to propose operational mechanisms but also a better understanding of what creativity is."

technical paper

This work describes the story of the Mexican International Colloquium on Computational Creativity, which has been carried out for 14 years. I describe the activities around this academic event and present a list of all invited speakers. I finish with some thoughts about the experience of organizing this Colloquium.

Mexican International Colloquium on Computational Creativity

"Sound and movement are closely coupled, particularly in dance.
Certain audio features have been found to affect the way we move to music.
Is this relationship between sound and movement something which can be modelled using machine learning? 
This work presents initial experiments wherein
high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance.  Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features."

Towards Movement Generation with Audio Features

Creative design is often accomplished through teams, and the specific composition of those teams can limit or enhance the sum creativity. However, it is not known how team composition is related to a team’s ability to achieve good solutions over various problems (i.e., robustness). Here, we build that relationship between composition and robustness through a series of agent-based simulations. The factor that we specifically investigate is cognitive style, which describes the manner in which individuals solve problems and present solutions in social interactions based on cognitive processes. Under Kirton’s Adaption Innovation (KAI) Theory, cognitive style is related to creativity. Specifically, an individual’s KAI score, the defining measure of cognitive style, describes the degree to which they prefer high-utility solutions, or high-novelty solutions – the two necessary conditions for creativity. In many cases the long-term success of a team is closely tied to their ability to perform consistently well across multiple design problems, termed robustness. Leveraging computational agents, we use adaption-innovation theory as the primary factor to examine robustness among homogenous and heterogeneous agents. Different approaches to composing teams with homogenous and heterogeneous cognitive styles did not substantially impact robustness. However, the average robustness of the teams improved as team size increased.

Utilizing Agent-Based Modeling to Quantify Robustness in Design Teams With Respect to Cognitive Style

"Creativity is the generation of an artifact that is judged to be novel and high-quality. Several computational creativity systems with diverse algorithmic foundations are
now meeting standards of novelty and quality, as judged by experts in creative fields. The existence of these myriad design approaches suggest a natural question analogous to the one addressed in information theory: Are there fundamental limits to creativity? Here, we first review a recent mathematical formalism that captures key aspects of combinatorial creativity and yields fundamental tradeoffs between novelty and quality. The fundamental limit resembles Shannon’s capacity-cost function. Then we extend the theory to capture intentionality in creativity, treating it as a communication problem, where a creative artifact must not only be novel and high-quality, but also reliably convey a message of given information rate. The resulting fundamental limit resembles the information bottleneck optimization
in machine learning."

Limits Theorems for Creativity with Intentionality

Computers can help us to trigger our intuition about how to solve a problem. But how does a computer take into account what a user wants and update these triggers? User preferences are hard to model as they are by nature vague, depend on the user's background and are not always deterministic, changing depending on the context and process under which they were established. We pose that the process of preference discovery should be the object of interest in computer aided design or ideation. The process should be transparent, informative, interactive and intuitive. We formulate HyperPref, a cyclic co-creative process between human and computer, which triggers the user's intuition about what is possible and is updated according to what the user wants based on their decisions. We combine quality diversity algorithms, a divergent optimization method that can produce many, diverse solutions, with variational autoencoders to both model that diversity as well as the user's preferences, discovering the preference hypervolume within large search spaces.

A Deep Dive Into Exploring the Preference Hypervolume

"Casual creators offer an enjoyable and readily accessible creative experience by enabling a safe and easy exploration of a creative space. This explorative and intrinsically motivating process lends itself to education applications, giving rise to a new category of casual creators, which we call Educational Creators. We illustrate this concept through EarthMood, an educational creator for deepening students’ understanding of Climate Change. We demonstrate EarthMood through historical data, showing the deterioration of the planet, as well as on recent data, illustrating an improvement in climate due to COVID-19. The remotely-accessible nature of educational creators makes them applicable to both traditional and remote
learning settings."

A Climate Change Educational Creator

"There are two classes of generative art approaches: neural, where a deep model is trained to generate samples from a data distribution, and “symbolic” or algorithmic, where an artist designs the primary parameters and an autonomous system generates samples within these constraints. In this work, we propose a new hybrid
genre: neuro-symbolic generative art. As a preliminary study, we train a generative deep neural network on samples from the symbolic approach. We demonstrate through human studies that subjects find the final artifacts and the creation process using our neuro-symbolic approach to be more creative than the symbolic approach 61% and 82% of the time respectively."

Neuro-Symbolic Generative Art: A Preliminary Study

We present how we built the dataset and models, summarize evaluation results and show a few examples of generated music at the end.

Automated Music Generation for Visual Art through Emotion

We present a proposal for meta-level evaluation in creative systems. In this paper, the Mexica creative system is the subject of our analysis. To achieve meta-level evaluation, we have constructed a program that interacts with Mexica's inputs and its outputs. The meta-level system evaluates the results and makes decisions based on them. For decision-making it includes heuristics that are defined in terms of Mexica's results; these are rules particular to the object- level system. We also include other general metrics that apply in any other creative system. For example, Ritchie's criteria for evaluating creative systems are included in this proposal.

Meta-level Evaluation and Transformational Creativity; An analysis of MEXICA

"Music variations consists of modifying an original music piece so that it remains harmonious and provides a sense of novelty while still remain relatable to the original song. The melody should progress in a harmonious way and under a reasonable chord hierarchy, due to this constraints, music 
variations can be considered as a rule based composition system. In this research, we develop a genetic algorithm to compose a variation on a given music piece. To achieve this we design a novel evaluation function and evolutionary operators which favor the modification process. These are designed to include components of melody similarity and tempo diversity in addition to harmony. The experimental results show that the proposed  system can generate variations that preserve musicality. A human evaluation study is also included to validate the proposed evaluation function. Additionally a link to listen to our generated compositions is provided."

Creativity explained by Computational Cognitive Neuroscience

Downloads

Next from ICCC'20

Mexican International Colloquium on Computational Creativity

Similar lecture

Shaping the Narrative Arc: Information-Theoretic Collaborative Dialogue

Creativity explained by Computational Cognitive Neuroscience

.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

Mexican International Colloquium on Computational Creativity

Similar lecture

Shaping the Narrative Arc: Information-Theoretic Collaborative Dialogue

Downloads