Penousal Machado

University of Coimbra | UC · Centre for Informatics and Systems (CISUC)

Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation (EC). The algorithm not only searches for the best network topology (e.g., number of layers, type of layers), but also tunes hyper-parameters, such as, learning parameters or data...

Generative Adversarial Networks (GAN) is an adversarial model that became relevant in the last years, displaying impressive results in generative tasks. A GAN combines two neural networks, a discriminator and a generator, trained in an adversarial way. The discriminator learns to distinguish between real samples of an input dataset and fake samples...

Recent developments on artificial intelligence expedited the computational fabrication of visual information, especially photography, with realism and easiness never seen before. In this paper, we present an interactive installation that explores the generation of facial portraits in the borderline between the real and artificial. The presented ins...

The field of computational biology has become largely dependent on data visualization tools to analyze the increasing quantities of data gathered through the use of new and growing technologies. Aside from the volume, which often results in large amounts of noise and complex relationships with no clear structure, the visualization of biological dat...

A descriptive approach for automatic generation of visual blends is presented. The implemented system, the Blender, is composed of two components: the Mapper and the Visual Blender. The approach uses structured visual representations along with sets of visual relations which describe how the elements – in which the visual representation can be deco...

Artificial Intelligence (AI) has driven innovations and created new opportunities across various sectors. However, leveraging domain-specific knowledge often requires automated tools to design and configure models effectively. In the case of Deep Neural Networks (DNNs), researchers and practitioners usually resort to Neural Architecture Search (NAS...

In recent years, the development of metrics to evaluate image aesthetics and photographic quality has proliferated. However, validating these metrics presents challenges due to the inherently subjective nature of aesthetics and photographic quality, which can be influenced by cultural contexts and individual preferences that evolve over time. This...

In recent years, the application of Artificial Intelligence (AI) for creative and artistic endeavours has attracted considerable attention, increasing the opportunities to use AI for many art and design tasks. This paper describes our response to a unique challenge presented by the Portuguese National Press-Mint (INCM): to use AI to design a commem...

The study of creative collaboration between humans and computational systems is a recurring topic in the area of computational creativity. With the rapid developments of Generative AI systems with increasingly improved performance and greater agency, this topic assumes growing importance. In this paper, we explore a specific paradigm of human-AI co...

This paper describes our response to a unique challenge presented by the Portuguese National Press-Mint: to use Artificial Intelligence to design a commemorative coin that celebrates the "digital world". We explain the process of this coin's co-creation, from conceptualisation to production, highlighting the design process, the underlying rationale...

Decision Trees (DTs) stand out as a prevalent choice among supervised Machine Learning algorithms. These algorithms form binary structures, effectively dividing data into smaller segments based on distinct rules. Consequently, DTs serve as a learning mechanism to identify optimal rules for the separation and classification of all elements within a...

Artificial neural networks are a staple of modern artificial intelligence. These systems must often undergo a training procedure to learn how to solve a designated task. Properly choosing and tuning an optimizer for a problem can significantly improve training speed and quality. Research into optimizers focuses on creating solutions that are genera...

Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on labelled data, which can sometimes be costly and hard to obtain. In order to address the first problem, neuroev...

PhDs - Portugal has Doctors is an interactive installation presenting Portuguese doctoral theses from 1970 to 2022, tracking their historical evolution and distribution across universities and research sectors. This work resulted in an installation that served a dual purpose: to raise awareness and value the work of national doctorates and to reduc...

Finding unconventional visual solutions that stand out and draw attention is frequently one of the goals of Graphic Design (GD). However, to save time, graphic designers often adhere to design trends and templates, resulting in creations that frequently lack distinctive qualities. To speed up the creative process, among other techniques, researcher...

Languages that describe two-dimensional (2-D) structures have emerged as powerful tools in various fields, encompassing pattern recognition and image processing, as well as modeling physical and chemical phenomena. One kind of two-dimensional structures is given by labeled polyominoes, i.e., geometric shapes composed of connected unit squares repre...

The increasing usage of Artificial Intelligence (AI) models, especially Deep Neural Networks (DNNs), is increasing the power consumption during training and inference, posing environmental concerns and driving the need for more energy-efficient algorithms and hardware solutions. This work addresses the growing energy consumption problem in Machine...

The increasing usage of Artificial Intelligence (AI) models, especially Deep Neural Networks (DNNs), is increasing the power consumption during training and inference, posing environmental concerns and driving the need for more energy-efficient algorithms and hardware solutions. This work addresses the growing energy consumption problem in Machine...

In recent years, there has been a growing application of mixed-initiative co-creative approaches in the creation of video games. The rapid advances in the capabilities of artificial intelligence (AI) systems further propel creative collaboration between humans and computational agents. In this tutorial, we present guidelines for researchers and pra...

To address the problem that existing quantum image watermarking schemes have only a single watermarking mode with weak robustness, in this paper we propose a novel multi-modal quantum watermarking (MMQW) scheme using the generalized model of novel enhanced quantum representation. Our scheme provides four quantum watermarking modes (G_G, G_C, C_C, C...

To address the size limitations of existing quantum image models in terms of accurate image representation, as well as inaccurate image operation and retrieval, we propose a Novel Generalized Quantum Image Representation (NGQR) for images of arbitrary size and type. For generalizing the size model, we first propose the Perception-Aided Encoding (PE...

Nowadays, it is possible to characterise, visualise, and analyse urban mobility using digital footprints, in particular, cellphones. However, movement patterns from vast heterogeneous datasets must be parsed, filtered, and aggregated using dynamic and scalable methods. ANTENNA, is a visual analytic tool that depicts trajectories of movement gathere...

More and more, graphic designers need to deliver faster and cheaper. To help speed up the creative process, we propose a computational approach for automatically stylising graphics so that these can relate to given semantic concepts. More specifically, by automatically selecting transformation and styling properties that better relate to a list of...

Being able to evaluate aesthetics automatically is one of the fundamental needs for creating robust and autonomous computational creativity systems. In Graphic Design (GD), many aesthetic features might need to be considered simultaneously to properly evaluate GD artefacts, e.g. their visual relation to the concept of the work, legibility, innovati...

The history of graphic design suggests that the introduction of new tools in people's workflow might promote new creative paths. This article discusses the impact of computational tools on performing creative tasks. We conducted semi-structured interviews with twelve professionals working on graphic design, data science, computer art, music and dat...

Deep-neuroevolution is the optimisation of deep neural architectures using evolutionary computation. Amongst these techniques, Fast-Deep Evolutionary Network Structured Representation (Fast-DENSER) has achieved considerable success in the development of Convolutional Neural Networks (CNNs) for image classification. In this study, variants of this a...

Type Design is a domain that multiple times has profited from the emergence of new tools and technologies. The transformation of type from physical to digital, the dissemination of font design software and the adoption of web typography make type design better known and more accessible. This domain has received an even greater push with the increas...

The dissemination of open-source text-to-image generative models and the increasing quality of their output has led to a growth in interest in the field. The quality of the images greatly depends on the prompt used, i.e. a phrase that includes descriptive terms to be used as input on text-to-image model. However, choosing the right prompt is a comp...

Graphic Design (gd) artefacts, like posters on the streets or book covers on store shelves, often compete with each other to be seen, catch attention and communicate effectively. Nevertheless, due to the democratisation of gd and because finding disruptive aesthetics might be time-consuming, graphic designers often follow existing trends, lacking d...

Maintaining genetic diversity as a means to avoid premature convergence is critical in Genetic Programming. Several approaches have been proposed to achieve this, with some focusing on the mating phase from coupling dissimilar solutions to some form of self-adaptive selection mechanism. In nature, genetic diversity can be the consequence of many di...

This work proposes Adaptive Facilitated Mutation, a self-adaptive mutation method for Structured Grammatical Evolution (SGE), biologically inspired by the theory of facilitated variation. In SGE, the genotype of individuals contains a list for each non-terminal of the grammar that defines the search space. In our proposed mutation, each individual...

Maintaining genetic diversity as a means to avoid premature convergence is critical in Genetic Programming. Several approaches have been proposed to achieve this, with some focusing on the mating phase from coupling dissimilar solutions to some form of self-adaptive selection mechanism. In nature, genetic diversity can be the consequence of many di...

This work proposes Adaptive Facilitated Mutation, a self-adaptive mutation method for Structured Grammatical Evolution (SGE), biologically inspired by the theory of facilitated variation. In SGE, the genotype of individuals contains a list for each non-terminal of the grammar that defines the search space. In our proposed mutation, each individual...

Grammar-Guided Genetic Programming (GGGP) employs a variety of insights from evolutionary theory to autonomously design solutions for a given task. Recent insights from evolutionary biology can lead to further improvements in GGGP algorithms. In this paper, we apply principles from the theory of Facilitated Variation and knowledge about heterogeneo...

The dissemination of open-source text-to-image generative models and the increasing quality of their output has led to a growth in interest in the field. The quality of the images greatly depends on the prompt used, i.e. a phrase that includes descriptive terms to be used as input on text-to-image model. However, choosing the right prompt is a comp...

Frequently, one of the goals of Graphic Design (gd) is discovering disruptive visual solutions that stand out and attract people’s attention. However, due to the increasing democratisation of gd, graphic designers tend to adopt design trends, leading to designs that many times lack innovative and catchy features. EvoDesigner is an evolutionary exte...

The development of computational artifacts to study cross-modal associations has been a growing research topic, as they allow new degrees of abstraction. In this context, we propose a novel approach to the computational exploration of relationships between music and abstract images, grounded by findings from cognitive sciences (emotion and percepti...

Image enhancement is an image processing procedure in which the image’s original information is refined, for example by highlighting specific features to ease post-processing analyses by a human or machine. This procedure remains challenging since each set of images is often taken under diverse conditions which makes it hard to find an image enhanc...

We present ESSYS* Sharing #UC, an audiovisual installation artwork that reflects upon the emotional context related to the university and the city of Coimbra, based on the data shared about them on Twitter. The installation was presented in an urban art gallery of C\'irculo de Artes Pl\'asticas de Coimbra during the summer and autumn of 2021. In th...

Computational approaches are beginning to be used to design dynamic visual identities fuelled by data and generative processes. In this work, we explore these computational approaches in order to generate a visual identity that creates bespoke letterings and images. We achieve this developing a generative design system that automatically assembles...

Field of Leaves is an interactive installation that depicts public contracts held in Portugal and their distribution over its five regions and two autonomous regions. The installation presents information about the public contracts available at the online portal of public procurements called Portal Basegov. The installation attempts to advocate the...

In the context of generative models, text-to-image generation achieved impressive results in recent years. Models using different approaches were proposed and trained in huge datasets of pairs of texts and images. However, some methods rely on pre-trained models such as Generative Adversarial Networks, searching through the latent space of the gene...

This review presents a state of the art in artificial intelligence applied to urban planning and particularly to land-use predictions. In this review, different articles after the year 2016 are analyzed mostly focusing on those that are not mentioned in earlier publications. Most of the articles analyzed used a combination of Markov chains and cell...

Urban spaces are rich in environmental stimuli. This high represents a challenge when creating visual communication objects that address the public’s attention. However, the presence of digital screens turns this into an opportunity to explore new resources for the creation of visual strategies and address the contemporary context of urban spaces....

Fraud detection is related to the suppression of possible financial losses for institutions and their clients. It is a task of high responsibility and, therefore, an important phase of the decision-making chain. Nowadays, experts in charge base their analysis on tabular data, usually presented in spreadsheets and seldom supplemented with simple vis...

The analysis and detection of fraudulent patterns in banking transactions are of most importance. However, it can be a laborious and time-consuming task. We propose a visualization tool—VaBank—to ease the analysis of banking transactions over time and enhance the detection of the transactions’ topology and suspicious behaviours. To reduce the visua...

The grammars used in grammar-based Genetic Programming (GP) methods have a significant impact on the quality of the solutions generated since they define the search space by restricting the solutions to its syntax. In this work, we propose Probabilistic Structured Grammatical Evolution (PSGE), a new approach that combines the Structured Grammatical...

Deep Learning Algorithms are widely implemented and have reached state-of-the-art results in several scientific investigations. In medical images domain and Computer-Assisted Detection (CAD) systems, Convolution Neural Networks (CNNs) are the preferred deep network architecture. Despite getting good results, there are still some obstacles to overco...

This work proposes an extension to Structured Grammatical Evolution (SGE) called Co-evolutionary Probabilistic Structured Grammatical Evolution (Co-PSGE). In Co-PSGE each individual in the population is composed by a grammar and a genotype, which is a list of dynamic lists, each corresponding to a non-terminal of the grammar containing real numbers...

Graphic Design (GD) artefacts aim to attract people’s attention before any forward objectives. Thus, one of the goals of GD is frequently to find innovative aesthetics that stand out over competing design artefacts (such as other book covers in a store or other posters on the street). However, as gd is increasingly being democratised and broadly sh...

Many authors consider typography as what language looks like. Over time, designers explored connections between type design and sound, trying to bridge the gap between the two areas. This paper describes SpeechTyper, an ongoing system that generates typographic compositions based on speech. Our goal is to create typographic representations that con...