ISSN / EISSN : 1064-5462 / 1530-9185
Published by: MIT Press - Journals (10.1162)
Total articles ≅ 796
Latest articles in this journal
Artificial Life pp 1-28; https://doi.org/10.1162/artl_a_00389
While interest in artificial neural networks (ANNs) has been renewed by the ubiquitous use of deep learning to solve high-dimensional problems, we are still far from general artificial intelligence. In this article, we address the problem of emergent cognitive capabilities and, more crucially, of their detection, by relying on co-evolving creatures with mutable morphology and neural structure. The former is implemented via both static and mobile structures whose shapes are controlled by cubic splines. The latter uses ESHyperNEAT to discover not only appropriate combinations of connections and weights but also to extrapolate hidden neuron distribution. The creatures integrate low-level perceptions (touch/pain proprioceptors, retina-based vision, frequency-based hearing) to inform their actions. By discovering a functional mapping between individual neurons and specific stimuli, we extract a high-level module-based abstraction of a creature’s brain. This drastically simplifies the discovery of relationships between naturally occurring events and their neural implementation. Applying this methodology to creatures resulting from solitary and tag-team co-evolution showed remarkable dynamics such as range-finding and structured communication. Such discovery was made possible by the abstraction provided by the modular ANN which allowed groups of neurons to be viewed as functionally enclosed entities.
Artificial Life pp 1-11; https://doi.org/10.1162/artl_a_00382
Cooperation among individuals has been key to sustaining societies. However, natural selection favors defection over cooperation. Cooperation can be favored when the mobility of individuals allows cooperators to form a cluster (or group). Mobility patterns of animals sometimes follow a Lévy flight. A Lévy flight is a kind of random walk but it is composed of many small movements with a few big movements. The role of Lévy flights for cooperation has been studied by Antonioni and Tomassini, who showed that Lévy flights promoted cooperation combined with conditional movements triggered by neighboring defectors. However, the optimal condition for neighboring defectors and how the condition changes with the intensity of Lévy flights are still unclear. Here, we developed an agent-based model in a square lattice where agents perform Lévy flights depending on the fraction of neighboring defectors. We systematically studied the relationships among three factors for cooperation: sensitivity to defectors, the intensity of Lévy flights, and population density. Results of evolutionary simulations showed that moderate sensitivity most promoted cooperation. Then, we found that the shortest movements were best for cooperation when the sensitivity to defectors was high. In contrast, when the sensitivity was low, longer movements were best for cooperation. Thus, Lévy flights, the balance between short and long jumps, promoted cooperation in any sensitivity, which was confirmed by evolutionary simulations. Finally, as the population density became larger, higher sensitivity was more beneficial for cooperation to evolve. Our study highlights that Lévy flights are an optimal searching strategy not only for foraging but also for constructing cooperative relationships with others.
Artificial Life pp 1-18; https://doi.org/10.1162/artl_a_00377
Evolvable hardware is a field of study exploring the application of evolutionary algorithms to hardware systems during design, operation, or both. The work presented here focuses on the use of field programmable gate arrays (FPGAs), a type of dynamically reconfigurable hardware device typically used for electronic prototyping in conjunction with a newly created open-source platform for performing intrinsic analog evolvable hardware experiments. This work targets the reproduction of seminal field experiments that generated complex analog dynamics of unclocked FPGAs evolved through genetic manipulation of their binary circuit representation: the bitstream. Further, it demonstrates the intrinsic evolution of two nontrivial analog circuits with intriguing properties, amplitude maximization and pulse oscillation, as well as the robustness of evolved circuits to temperature variation and across-chip circuit translation.
Artificial Life pp 1-20; https://doi.org/10.1162/artl_a_00374
In Evolutionary Robotics, Lexicase selection has proven effective when a single task is broken down into many individual parameterizations. Evolved individuals have generalized across unique configurations of an overarching task. Here, we investigate the ability of Lexicase selection to generalize across multiple tasks, with each task again broken down into many instances. There are three objectives: to determine the feasibility of introducing additional tasks to the existing platform; to investigate any consequential effects of introducing these additional tasks during evolutionary adaptation; and to explore whether the schedule of presentation of the additional tasks over evolutionary time affects the final outcome. To address these aims we use a quadruped animat controlled by a feed-forward neural network with joint-angle, bearing-to-target, and spontaneous sinusoidal inputs. Weights in this network are trained using evolution with Lexicase-based parent selection. Simultaneous adaptation in a wall crossing task (labelled wall-cross) is explored when one of two different alternative tasks is also present: turn-and-seek or cargo-carry. Each task is parameterized into 100 distinct variants, and these variants are used as environments for evaluation and selection with Lexicase. We use performance in a single-task wall-cross environment as a baseline against which to examine the multi-task configurations. In addition, the objective sampling strategy (the manner in which tasks are presented over evolutionary time) is varied, and so data for treatments implementing uniform sampling, even sampling, or degrees of generational sampling are also presented. The Lexicase mechanism successfully integrates evolution of both turn-and-seek and cargo-carry with wall-cross, though there is a performance penalty compared to single task evolution. The size of the penalty depends on the similarity of the tasks. Complementary tasks (wallcross/turn-and-seek) show better performance than antagonistic tasks (wall-cross/cargo-carry). In complementary tasks performance is not affected by the sampling strategy. Where tasks are antagonistic, uniform and even sampling strategies yield significantly better performance than generational sampling. In all cases the generational sampling requires more evaluations and consequently more computational resources. The results indicate that Lexicase is a viable mechanism for multitask evolution of animat neurocontrollers, though the degree of interference between tasks is a key consideration. The results also support the conclusion that the naive, uniform random sampling strategy is the best choice when considering final task performance, simplicity of implementation, and computational efficiency.
Artificial Life pp 1-22; https://doi.org/10.1162/artl_a_00381
Crowd simulations are used extensively to study the dynamics of human collectives. Such studies are underpinned by specific movement models, which encode rules and assumptions about how people navigate a space and handle interactions with others. These models often give rise to macroscopic simulated crowd behaviours that are statistically valid, but which lack the noisy microscopic behaviours that are the signature of believable real crowds. In this article, we use an existing Turing test for crowds to identify realistic features of real crowds that are generally omitted from simulation models. Our previous study using this test established that untrained individuals have difficulty in classifying movies of crowds as real or simulated, and that such people often have an idealised view of how crowds move. In this follow-up study (with new participants) we perform a second trial, which now includes a training phase (showing participants movies of real crowds). We find that classification performance significantly improves after training, confirming the existence of features that allow participants to identify real crowds. High-performing individuals are able to identify the features of real crowds that should be incorporated into future simulations if they are to be considered realistic.
Artificial Life pp 1-21; https://doi.org/10.1162/artl_a_00383
It has long been hypothesized that operating close to the critical state is beneficial for natural and artificial evolutionary systems. We put this hypothesis to test in a system of evolving foraging agents controlled by neural networks that can adapt the agents’ dynamical regime throughout evolution. Surprisingly, we find that all populations that discover solutions evolve to be subcritical. By a resilience analysis, we find that there are still benefits of starting the evolution in the critical regime. Namely, initially critical agents maintain their fitness level under environmental changes (for example, in the lifespan) and degrade gracefully when their genome is perturbed. At the same time, initially subcritical agents, even when evolved to the same fitness, are often inadequate to withstand the changes in the lifespan and degrade catastrophically with genetic perturbations. Furthermore, we find the optimal distance to criticality depends on the task complexity. To test it we introduce a hard task and a simple task: For the hard task, agents evolve closer to criticality, whereas more subcritical solutions are found for the simple task. We verify that our results are independent of the selected evolutionary mechanisms by testing them on two principally different approaches: a genetic algorithm and an evolutionary strategy. In summary, our study suggests that although optimal behaviour in the simple task is obtained in a subcritical regime, initializing near criticality is important to be efficient at finding optimal solutions for new tasks of unknown complexity.
Artificial Life pp 1-4; https://doi.org/10.1162/artl_e_00385
Artificial Life pp 1-18; https://doi.org/10.1162/artl_a_00373
DNA supercoiling, the level of under- or overwinding of the DNA polymer around itself, is widely recognized as an ancestral regulation mechanism of gene expression in bacteria. Higher levels of negative supercoiling facilitate the opening of the DNA double helix at gene promoters and thereby increase gene transcription rates. Different levels of supercoiling have been measured in bacteria exposed to different environments, leading to the hypothesis that variations in supercoiling could be a response to changes in the environment. Moreover, DNA transcription has been shown to generate local variations in the supercoiling level and, therefore, to impact the transcription rate of neighboring genes. In this work, we study the coupled dynamics of DNA supercoiling and transcription at the genome scale. We implement a genome-wide model of gene expression based on the transcription-supercoiling coupling. We show that, in this model, a simple change in global DNA supercoiling is sufficient to trigger differentiated responses in gene expression levels via the transcription-supercoiling coupling. Then, studying our model in the light of evolution, we demonstrate that this non-linear response to different environments, mediated by the transcription-supercoiling coupling, can serve as the basis for the evolution of specialized phenotypes.
Artificial Life, Volume 28, pp 289-309; https://doi.org/10.1162/artl_a_00368
What role do affective feelings (feelings/emotions/moods) play in adaptive behaviour? What are the implications of this for understanding and developing artificial general intelligence? Leading theoretical models of brain function are beginning to shed light on these questions. While artificial agents have excelled within narrowly circumscribed and specialised domains, domain-general intelligence has remained an elusive goal in artificial intelligence research. By contrast, humans and nonhuman animals are characterised by a capacity for flexible behaviour and general intelligence. In this article I argue that computational models of mental phenomena in predictive processing theories of the brain are starting to reveal the mechanisms underpinning domain-general intelligence in biological agents, and can inform the understanding and development of artificial general intelligence. I focus particularly on approaches to computational phenomenology in the active inference framework. Specifically, I argue that computational mechanisms of affective feelings in active inference—affective self-modelling—are revealing of how biological agents are able to achieve flexible behavioural repertoires and general intelligence. I argue that (i) affective self-modelling functions to “tune” organisms to the most tractable goals in the environmental context; and (ii) affective and agentic self-modelling is central to the capacity to perform mental actions in goal-directed imagination and creative cognition. I use this account as a basis to argue that general intelligence of the level and kind found in biological agents will likely require machines to be implemented with analogues of affective self-modelling.
Artificial Life, Volume 28, pp 287-288; https://doi.org/10.1162/artl_e_00386