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.

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 benchmarks meant to compare both the performance and evolution capabilities of different vectorized and iterative implementation approaches across several existing frameworks. Namely, TensorGP, a novel open-source engine written in Python, is shown to greatly benefit from the TensorFlow library to accelerate the domain evaluation phase in GP. The presented performance benchmarks demonstrate that the TensorGP engine manages to pull ahead, with relative speedups above two orders of magnitude for problems with a higher number of fitness cases. Additionally, as a consequence of being able to compute larger domains, we argue that TensorGP performance gains aid the discovery of more accurate candidate solutions.

Generative adversarial networks (GANs) achieved relevant advances in the field of generative algorithms, presenting high-quality results mainly in the context of images. However, GANs are hard to train, and several aspects of the model should be previously designed by hand to ensure training success. In this context, evolutionary algorithms such as COEGAN were proposed to solve the challenges in GAN training. Nevertheless, the lack of diversity and premature optimization can be found in some of these solutions. We propose in this paper the application of a quality-diversity algorithm in the evolution of GANs. The solution is based on the Novelty Search with Local Competition (NSLC) algorithm, adapting the concepts used in COEGAN to this new proposal. We compare our proposal with the original COEGAN model and with an alternative version using a global competition approach. The experimental results evidenced that our proposal increases the diversity of the discovered solutions and leverage the performance of the models found by the algorithm. Furthermore, the global competition approach was able to consistently find better models for GANs.

Portraits of No One is an internet artwork that generates and displays artificial photo-realistic portraits of human faces. This artwork assumes the form of a web page that synthesises new portraits by automatically recombining the facial features of the users who interacted with it. The generated portraits invoke the capabilities of Artificial Intelligence to generate visual content that makes people question themselves about the veracity of what they are seeing.

Generative adversarial networks (GAN) present state-of-the-art results in the generation of samples following the distribution of the input dataset. However, GANs are difficult to train, and several aspects of the model should be previously designed by hand. Neuroevolution is a well-known technique used to provide the automatic design of network architectures which was recently expanded to deep neural networks.

Typography plays a key communication role in the contemporary information-dense culture. Type design is a central, complex, and time consuming task. In this work we develop the generative system to type design based on an evolutionary algorithm. The key novel contributions are twofold. First, in terms of representation it relies on the use of assemblages of shapes to form glyphs. There are no limitations to the types of shapes that can be used. Second, we explore a compromise between legibility and expressiveness, testing different automatic fitness assignment schemes. The attained results show that we are able to evolve a wide variety of alternative glyphs, making the proposed system a viable alternative for real-world applications in the field of type design.

In the past few years the use of semantic aware crossover and mutation has become a hot topic of research within the Genetic Programming community. Unlike traditional genetic operators that perform syntactic manipulations of programs regardless of their behavior, semantic driven operators promote direct search on the underlying behavioral space. Based on previous work on semantic Genetic Programming and Genetic Morphing, we propose and implement semantic driven crossover and mutation operators for evolutionary art. The experimental results focus on assessing how these operators compare with traditional ones.