Penousal Machado

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

PhD

About

342
Publications
75,404
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,554
Citations
Introduction
Penousal Machado, PhD, is Associate Professor at the Department of Informatics Engineering of FCTUC and the scientific director of the Computational Design and Visualization Lab. of the Centre of Informatics and Systems of the University of Coimbra. His research interests include Nature-Inspired Computation, Artificial Intelligence, Computational Creativity, Computational Art and Design.
Additional affiliations
May 2007 - May 2016
University of Coimbra
Position
  • Professor (Assistant)
June 2004 - May 2016
University of Coimbra
Position
  • Professor (Assistant)
June 1997 - present
University of Coimbra
Position
  • Senior Researcher

Publications

Publications (342)
Article
Full-text available
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...
Chapter
Full-text available
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...
Chapter
Full-text available
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...
Article
Full-text available
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...
Conference Paper
Full-text available
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...
Preprint
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...
Article
Full-text available
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...
Article
Full-text available
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...
Preprint
Full-text available
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...
Preprint
Full-text available
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...
Preprint
Full-text available
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...
Article
Full-text available
In this paper, we resort to the TensorFlow framework to investigate the benefits of applying data vectorization and fitness caching methods to domain evaluation in Genetic Programming. For this purpose, an independent engine was developed, TensorGP, along with a testing suite to extract comparative timing results across different architectures and...
Article
Full-text available
Image Enhancement (IE) is an image processing procedure in which the image’s original information is improved, highlighting specific features to ease post-processing analyses by a human or machine. State-of-the-art image enhancement pipelines apply solutions to fixed and static constraints to solve specific issues in isolation. In this work, an IE...
Chapter
Full-text available
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...
Chapter
Full-text available
The evolution of hardware has enabled Artificial Neural Networks to become a staple solution to many modern Artificial Intelligence problems such as natural language processing and computer vision. The neural network’s effectiveness is highly dependent on the optimizer used during training, which motivated significant research into the design of ne...
Article
Many fields of study still face the challenges inherent to the analysis of complex multidimensional datasets, such as the field of computational biology, whose research of infectious diseases must contend with large protein-protein interaction networks with thousands of genes that vary in expression values over time. In this paper, we explore the v...
Conference Paper
Full-text available
In recent years computer simulations have proven to be useful in the study of the origin and evolution of communication. In this paper, we present a system that is able to evolve image-based communication protocols to transmit information. We trained an encoder and a de-coder in an architecture similar to a model of communication where the generato...
Article
Visualization has shown to be a valuable tool in the analysis of large and complex temporal datasets, aided by the emergence of new models such as Time Curves, which distorts timelines to position time points based on their similarity with each other, reflecting changes in the data over time. In this paper, we further explore time-series functional...
Chapter
Casa das Máquinas is an audiovisual confrontation between two artificial engines—Máquina de Ouver and Máquina Canora—in a multimodal dialogue that explores the poetic language of Mário de Sá-Carneiro. The poems Epígrafe, Anto and Fim, serve as feedstock to the machines, with their words oiling the internal engines of both entities, pulsating their...
Conference Paper
Full-text available
We live in a society governed by information, much of which is produced by us through the most diverse ubiquitous computing devices. Every day more people are connected to the Internet and more information is produced. In large part, this increase in online production is due to social networks and the content we produce and share on them. Instagram...
Conference Paper
Full-text available
Automatic fraud detection and prevention are challenging problems that have attracted the attention of many researchers in academia and industry. Over the last few years, many improvements have been achieved, especially in predictive models based on Machine Learning. However, a considerable amount of these models only provide a prediction score and...
Article
Full-text available
This paper presents our work on the computational creation of photorealistic face images with a focus on how we transformed our generative and evolutionary system X-Faces into an interactive Media Art installation entitled Portraits of No One. The X-Faces system resorts to Computer Vision and Computer Graphics to automatically create new face image...
Conference Paper
Full-text available
The recent popularity of creative coding tools and Computational Creativity approaches are promoting a paradigm shift in the creation, development and production of Graphic Design artefacts. In this work, we present an evolutionary system for the automatic typesetting of typographic posters. This system is inspired by the letterpress typesetting pr...
Article
This paper introduces a grammar-based general purpose framework for the automatic search and deployment of potentially Deep Artificial Neural Networks (DANNs). The approach is known as Fast Deep Evolutionary Network Structured Representation (Fast-DENSER) and is capable of simultaneously optimising the topology, learning strategy and any other requ...
Preprint
Full-text available
Neuroevolutionary algorithms, automatic searches of neural network structures by means of evolutionary techniques, are computationally costly procedures. In spite of this, due to the great performance provided by the architectures which are found, these methods are widely applied. The final outcome of neuroevolutionary processes is the best structu...
Preprint
Full-text available
Genetic Programming (GP) is known to suffer from the burden of being computationally expensive by design. While, over the years, many techniques have been developed to mitigate this issue, data vectorization, in particular, is arguably still the most attractive strategy due to the parallel nature of GP. In this work, we employ a series of benchmark...
Chapter
Full-text available
The recent developments on Artificial Intelligence are expanding the tools, methods, media, and production processes on Graphic Design. Poster designs are no exception. In this paper, we present a web system that generates letterpress-inspired typographic posters using, as content, tweets posted online. The proposed system employs Natural Language...
Chapter
Image enhancement is an image processing procedure in which the original information of the image is improved. It alters an image in several different ways, for instance, by highlighting a specific feature in order to ease post-processing analyses by a human or machine. In this work, we show our approach to image enhancement for digital real-estate...
Chapter
In this paper, we resort to the TensorFlow framework to investigate the benefits of applying data vectorization and fitness caching methods to domain evaluation in Genetic Programming. For this purpose, an independent engine was developed, TensorGP, along with a testing suite to extract comparative timing results across different architectures and...
Chapter
Indirect encoding is a promising area of research in machine learning/evolutionary computation, however, it is rarely able to achieve performance on par with state of the art directly encoded methods. One of the most important properties of indirect encoding is the ability to control exploration during learning by transforming random genotypic vari...
Chapter
Full-text available
Generative Adversarial Networks (GANs) are powerful generative models that achieved strong results, mainly in the image domain. However, the training of GANs is not trivial, presenting some challenges tackled by different strategies. Evolutionary algorithms, such as COEGAN, were recently proposed as a solution to improve the GAN training, overcomin...
Preprint
Full-text available
Artificial Neural Networks (ANNs) became popular due to their successful application difficult problems such image and speech recognition. However, when practitioners want to design an ANN they need to undergo laborious process of selecting a set of parameters and topology. Currently, there are several state-of-the art methods that allow for the au...
Preprint
Full-text available
Grammatical Evolution (GE) is one of the most popular Genetic Programming (GP) variants, and it has been used with success in several problem domains. Since the original proposal, many enhancements have been proposed to GE in order to address some of its main issues and improve its performance. In this paper we propose Probabilistic Grammatical Evo...
Preprint
Full-text available
In this paper, we resort to the TensorFlow framework to investigate the benefits of applying data vectorization and fitness caching methods to domain evaluation in Genetic Programming. For this purpose, an independent engine was developed, TensorGP, along with a testing suite to extract comparative timing results across different architectures and...
Preprint
Full-text available
The introduction of new tools in people's workflow has always been promotive of new creative paths. This paper discusses the impact of using computational tools in the performance of creative tasks, especially focusing on graphic design. The study was driven by a grounded theory methodology, applied to a set of semi-structured interviews, made to t...
Chapter
Full-text available
Grammatical Evolution (GE) is one of the most popular Genetic Programming (GP) variants, and it has been used with success in several problem domains. Since the original proposal, many enhancements have been proposed to GE in order to address some of its main issues and improve its performance. In this paper we propose Probabilistic Grammatical Evo...
Preprint
Full-text available
Generative Adversarial Networks (GANs) are powerful generative models that achieved strong results, mainly in the image domain. However, the training of GANs is not trivial, presenting some challenges tackled by different strategies. Evolutionary algorithms, such as COEGAN, were recently proposed as a solution to improve the GAN training, overcomin...
Conference Paper
Full-text available
Image enhancement is an image processing procedure in which the original information of the image is improved. It alters an image in several different ways, for instance, by highlighting a specific feature in order to ease post-processing analyses by a human or machine. In this work, we show our approach to image enhancement for digital real-estate...
Chapter
Dynamic visual identities differ from the conventional ones by the occurrence of variation in at least one of the elements of their visual system. The type of dynamism depends on the variation mechanisms used, which may confer different features to the visual identity. Flexibility is one of these features and consists in the ability to adapt to dif...
Article
Full-text available
RealTimeBattle is an environment in which robots controlled by programs fight each other. Programs control the simulated robots using low-level messages (e.g., turn radar, accelerate). Unlike other tools like Robocode, each of these robots can be developed using different programming languages. Our purpose is to generate, without human programming...
Conference Paper
Full-text available
Glowing Lichen is a media-art installation that explores a series of sensitive connections between a physical-digital artefact and an audience. This installation comprehends two luminous organisms that cohabit in the same ecosystem and react to the surrounding environment in distinct ways. Each organism has an individual predisposition , i.e., pers...
Conference Paper
Full-text available
The field of Information Visualization has undergone major changes in the last decades due to the growing computational power and easier access to various technologies by a greater number of people. However, Information Visualization and its techniques literacy continue to be a knowledge associated to a reduced audience. In order to surpass this co...
Conference Paper
Full-text available
An interactive evolutionary system to generate letterings is presented. The system allows the creation of a wide range of alternative designs that can be used as stimuli for inspiration or for the creation of visual identities with different variations. This work began as a parametric system that generated glyph designs by recombining parts of skel...
Article
The emoji connection between visual representation and semantic knowledge, together with its large conceptual coverage have the potential to be exploited in computational approaches to the visual representation of concepts. An example of a system that explores this potential is Emojinating-a system that uses a process of visual blending of existing...
Conference Paper
Full-text available
Co-creative systems are useful in fostering creativity, often leading to unexpected results. Despite this, the relation between user and system is complex. The level of autonomy given to the system directly influences its potential for creative behaviour and degree of contribution to the cooperation with the user. In this paper, we present our effo...