GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NAS

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) approaches, which are resource- and time-intensive, requiring the training and evaluation of numerous candidate architectures. This raises sustainability concerns, particularly due to the high energy demands involved, creating a paradox: the pursuit of the most effective model can undermine sustainability goals. To mitigate this issue, zero-cost proxies have emerged as a promising alternative. These proxies estimate a model's performance without the need for full training, offering a more efficient approach. This paper addresses the challenges of model evaluation by automatically designing zero-cost proxies to assess DNNs efficiently. Our method begins with a randomly generated set of zero-cost proxies, which are evolved and tested using the NATS-Bench benchmark. We assess the proxies' effectiveness using both randomly sampled and stratified subsets of the search space, ensuring they can differentiate between low- and high-performing networks and enhance generalizability. Results show our method outperforms existing approaches on the stratified sampling strategy, achieving strong correlations with ground truth performance, including a Kendall correlation of 0.89 on CIFAR-10 and 0.77 on CIFAR-100 with NATS-Bench-SSS and a Kendall correlation of 0.78 on CIFAR-10 and 0.71 on CIFAR-100 with NATS-Bench-TSS.

Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning

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, neuroevolution has been proved to be a plausible option to automate the design of DNNs. As for the second problem, self-supervised learning has been used to leverage unlabelled data to learn representations. Our goal is to study how neuroevolution can help self-supervised learning to bridge the gap to supervised learning in terms of performance. In this work, we propose a framework that is able to evolve deep neural networks using self-supervised learning. Our results on the CIFAR-10 dataset show that it is possible to evolve adequate neural networks while reducing the reliance on labelled data. Moreover, an analysis to the structure of the evolved networks suggests that the amount of labelled data fed to them has less effect on the structure of networks that learned via self-supervised learning, when compared to individuals that relied on supervised learning.

Evaluation Metrics for Automated Typographic Poster Generation

Computational Design approaches facilitate the generation of typographic design, but evaluating these designs remains a challenging task. In this paper, we propose a set of heuristic metrics for typographic design evaluation, focusing on their legibility, which assesses the text visibility, aesthetics, which evaluates the visual quality of the design, and semantic features, which estimate how effectively the design conveys the content semantics. We experiment with a constrained evolutionary approach for generating typographic posters, incorporating the proposed evaluation metrics with varied setups, and treating the legibility metrics as constraints. We also integrate emotion recognition to identify text semantics automatically and analyse the performance of the approach and the visual characteristics outputs.

Towards Physical Plausibility in Neuroevolution Systems

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 Learning (ML), particularly during the inference phase. Even a slight reduction in power usage can lead to significant energy savings, benefiting users, companies, and the environment. Our approach focuses on maximizing the accuracy of Artificial Neural Network (ANN) models using a neuroevolutionary framework whilst minimizing their power consumption. To do so, power consumption is considered in the fitness function. We introduce a new mutation strategy that stochastically reintroduces modules of layers, with power-efficient modules having a higher chance of being chosen. We introduce a novel technique that allows training two separate models in a single training step whilst promoting one of them to be more power efficient than the other while maintaining similar accuracy. The results demonstrate a reduction in power consumption of ANN models by up to 29.2% without a significant decrease in predictive performance.

All You Need Is Sex for Diversity

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 different factors, but when considering reproduction Sexual Selection can have an impact on promoting variety within a species. Specifically, Mate Choice often results in different selective pressures between sexes, which in turn may trigger evolutionary differences among them. Although some mechanisms of Sexual Selection have been applied to Genetic Programming in the past, the literature is scarce when it comes to mate choice. Recently, a way of modelling mating preferences by ideal mate representations was proposed, achieving good results when compared to a standard approach. These mating preferences evolve freely in a self-adaptive fashion, creating an evolutionary driving force of its own alongside fitness pressure. The inner mechanisms of this approach operate from personal choice, as each individual has its own representation of a perfect mate which affects the mate to be selected. In this paper, we compare this method against a random mate choice to assess whether there are advantages in evolving personal preferences. We conducted experiments using three symbolic regression problems and different mutation rates. The results show that self-adaptive mating preferences are able to create a more diverse set of solutions when compared to the traditional approach and a random mate approach (with statistically significant differences) and have a higher success rate in three of the six instances tested.

Context Matters: Adaptive Mutation for Grammars

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 contains an array with a different, self-adaptive mutation rate for each non-terminal. We also propose Function Grouped Grammars, a grammar design procedure, to enhance the benefits of the proposed mutation. Experiments were conducted on three symbolic regression benchmarks using Probabilistic Structured Grammatical Evolution (PSGE), a variant of SGE. Results show our approach is similar or better when compared with the standard grammar and mutation.

Structured mutation inspired by evolutionary theory enriches population performance and diversity

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 heterogeneous mutation rates and mutation effects to improve the variation operators. We term this new method of variation Facilitated Mutation (FM). We test FM performance on the evolution of neural network optimizers for image classification, a relevant task in evolutionary computation, with important implications for the field of machine learning. We compare FM and FM combined with crossover (FMX) against a typical mutation regime to assess the benefits of the approach. We find that FMX in particular provides statistical improvements in key metrics, creating a superior optimizer overall (+0.48\% average test accuracy), improving the average quality of solutions (+50\% average population fitness), and discovering more diverse high-quality behaviors (+400 high-quality solutions discovered per run on average). Additionally, FM and FMX can reduce the number of fitness evaluations in an evolutionary run, reducing computational costs in some scenarios.

Using Computational Approaches in Visual Identity Design: A Visual Identity for the Design and Multimedia Courses of Faculty of Sciences and Technology of University of Coimbra

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 black and white visual modules. This system generates designs performing two main methods: (i) Assisted generation; and (ii) Automatic generation. Assisted generation method produces outputs wherein the placement of modules is determined by a configuration file previous defined. On the other hand, the Automatic generation method produces outputs wherein the modules are assembled to depict an input image. This system speeds up the process of design and deployment of one visual identity design as well as it generates outputs visual coherent among them. In this paper, we compressively describe this system and its achievements.

ESSYS* Sharing #UC: An Emotion-driven Audiovisual Installation

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 the installation space, one may see a collection of typographic posters displaying the tweets and listening to an ever-changing ambient sound. The present audiovisuals are created by an autonomous computational creative approach, which employs a neural classifier to recognize the emotional context of a tweet and uses this resulting data as feedstock for the audiovisual generation. The installation's space is designed to promote an approach and blend between the online and physical perceptions of the same location. We applied multiple experiments with the proposed approach to evaluate the capability and performance. Also, we conduct interview-based evaluation sessions to understand how the installation elements, especially poster designs, are experienced by people regarding diversity, expressiveness and possible employment in other commercial and social scenarios.

Exploring Generative Adversarial Networks for Text-to-Image Generation with Evolution Strategies

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 generative model by using a gradient-based approach to update the latent vector, relying on loss functions such as the cosine similarity. In this work, we follow a different direction by proposing the use of Covariance Matrix Adaptation Evolution Strategy to explore the latent space of Generative Adversarial Networks. We compare this approach to the one using Adam and a hybrid strategy. We design an experimental study to compare the three approaches using different text inputs for image generation by adapting an evaluation method based on the projection of the resulting samples into a two-dimensional grid to inspect the diversity of the distributions. The results evidence that the evolutionary method achieves more diversity in the generation of samples, exploring different regions of the resulting grids. Besides, we show that the hybrid method combines the explored areas of the gradient-based and evolutionary approaches, leveraging the quality of the results.