Carlos Gershenson

Gerardo Altamirano-Gomez, Carlos Gershenson

Since their first applications, Convolutional Neural Networks (CNNs) have solved problems that have advanced the state-of-the-art in several domains. CNNs represent information using real numbers. Despite encouraging results, theoretical analysis shows that representations such as hyper-complex numbers can achieve richer representational capacities than real numbers, and that Hamilton products can capture intrinsic interchannel relationships. Moreover, in the last few years, experimental research has shown that Quaternion-Valued CNNs (QCNNs) can achieve similar performance with fewer parameters than their real-valued counterparts. This paper condenses research in the development of QCNNs from its very beginnings. We propose a conceptual organization of current trends and analyze the main building blocks used in the design of QCNN models. Based on this conceptual organization, we propose future directions of research.

Alberto García-Rodríguez, Matias Núñez, Miguel Robles Pérez et al.

The 2030 Agenda for Sustainable Development of the United Nations outlines 17 goals for countries of the world to address global challenges in their development. However, the progress of countries towards these goal has been slower than expected and, consequently, there is a need to investigate the reasons behind this fact. In this study, we have used a novel data-driven methodology to analyze time-series data for over 20 years (2000-2022) from 107 countries using unsupervised machine learning (ML) techniques. Our analysis reveals strong positive and negative correlations between certain SDGs (Sustainable Development Goals). Our findings show that progress toward the SDGs is heavily influenced by geographical, cultural and socioeconomic factors, with no country on track to achieve all the goals by 2030. This highlights the need for a region-specific, systemic approach to sustainable development that acknowledges the complex interdependencies between the goals and the variable capacities of countries to reach them. For this our machine learning based approach provides a robust framework for developing efficient and data-informed strategies to promote cooperative and targeted initiatives for sustainable progress.

Fernanda Sánchez-Puig, Rogelio Lozano-Aranda, Dante Pérez-Méndez et al.

Statistical linguistics has advanced considerably in recent decades as data has become available. This has allowed researchers to study how statistical properties of languages change over time. In this work, we use data from Twitter to explore English and Spanish considering the rank diversity at different scales: temporal (from 3 to 96 hour intervals), spatial (from 3km to 3000+km radii), and grammatical (from monograms to pentagrams). We find that all three scales are relevant. However, the greatest changes come from variations in the grammatical scale. At the lowest grammatical scale (monograms), the rank diversity curves are most similar, independently on the values of other scales, languages, and countries. As the grammatical scale grows, the rank diversity curves vary more depending on the temporal and spatial scales, as well as on the language and country. We also study the statistics of Twitter-specific tokens: emojis, hashtags, and user mentions. These particular type of tokens show a sigmoid kind of behaviour as a rank diversity function. Our results are helpful to quantify aspects of language statistics that seem universal and what may lead to variations.

Josué Ely Molina, Jorge Flores, Carlos Gershenson et al.

A recent increase in data availability has allowed the possibility to perform different statistical linguistic studies. Here we use the Google Books Ngram dataset to analyze word flow among English, French, German, Italian, and Spanish. We study what we define as ``migrant words'', a type of loanwords that do not change their spelling. We quantify migrant words from one language to another for different decades, and notice that most migrant words can be aggregated in semantic fields and associated to historic events. We also study the statistical properties of accumulated migrant words and their rank dynamics. We propose a measure of use of migrant words that could be used as a proxy of cultural influence. Our methodology is not exempt of caveats, but our results are encouraging to promote further studies in this direction.

Gerardo Altamirano-Gómez, Carlos Gershenson

In recent years, several models using Quaternion-Valued Convolutional Neural Networks (QCNNs) for different problems have been proposed. Although the definition of the quaternion convolution layer is the same, there are different adaptations of other atomic components to the quaternion domain, e.g., pooling layers, activation functions, fully connected layers, etc. However, the effect of selecting a specific type of these components and the way in which their interactions affect the performance of the model still unclear. Understanding the impact of these choices on model performance is vital for effectively utilizing QCNNs. This paper presents a statistical analysis carried out on experimental data to compare the performance of existing components for the image classification problem. In addition, we introduce a novel Fully Quaternion ReLU activation function, which exploits the unique properties of quaternion algebra to improve model performance.

Mario Franco, Carlos Gershenson

Nowadays, neural networks act as a synonym for artificial intelligence. Present neural network models, although remarkably powerful, are inefficient both in terms of data and energy. Several alternative forms of neural networks have been proposed to address some of these problems. Specifically, spiking neural networks are suitable for efficient hardware implementations. However, effective learning algorithms for spiking networks remain elusive, although it is suspected that effective plasticity mechanisms could alleviate the problem of data efficiency. Here, we present a new framework for spiking neural networks - Spark - built upon the idea of modular design, from simple components to entire models. The aim of this framework is to provide an efficient and streamlined pipeline for spiking neural networks. We showcase this framework by solving the sparse-reward cartpole problem with simple plasticity mechanisms. We hope that a framework compatible with traditional ML pipelines may accelerate research in the area, specifically for continuous and unbatched learning, akin to the one animals exhibit.

Mario Franco, Gerardo Febres, Nelson Fernández et al.

Classification is a ubiquitous and fundamental problem in artificial intelligence and machine learning, with extensive efforts dedicated to developing more powerful classifiers and larger datasets. However, the classification task is ultimately constrained by the intrinsic properties of datasets, independently of computational power or model complexity. In this work, we introduce a formal entropy-based measure of classificability, which quantifies the inherent difficulty of a classification problem by assessing the uncertainty in class assignments given feature representations. This measure captures the degree of class overlap and aligns with human intuition, serving as an upper bound on classification performance for classification problems. Our results establish a theoretical limit beyond which no classifier can improve the classification accuracy, regardless of the architecture or amount of data, in a given problem. Our approach provides a principled framework for understanding when classification is inherently fallible and fundamentally ambiguous.

Yoshio Martinez, Katya Rodriguez, Carlos Gershenson

Genetic algorithms have been used in recent decades to solve a broad variety of search problems. These algorithms simulate natural selection to explore a parameter space in search of solutions for a broad variety of problems. In this paper, we explore the effects of introducing temporal heterogeneity in genetic algorithms. In particular, we set the crossover probability to be inversely proportional to the individual's fitness, i.e., better solutions change slower than those with a lower fitness. As case studies, we apply heterogeneity to solve the $N$-Queens and Traveling Salesperson problems. We find that temporal heterogeneity consistently improves search without having prior knowledge of the parameter space.

Carlos Gershenson

There is no agreed definition of intelligence, so it is problematic to simply ask whether brains, swarms, computers, or other systems are intelligent or not. To compare the potential intelligence exhibited by different cognitive systems, I use the common approach used by artificial intelligence and artificial life: Instead of studying the substrate of systems, let us focus on their organization. This organization can be measured with information. Thus, I apply an informationist epistemology to describe cognitive systems, including brains and computers. This allows me to frame the usefulness and limitations of the brain-computer analogy in different contexts. I also use this perspective to discuss the evolution and ecology of intelligence.

Carlos Gershenson, Jitka Cejkova

Nature has found one method of organizing living matter, but maybe other options exist -- not yet discovered -- on how to create life. To study the life "as it could be" is the objective of an interdisciplinary field called Artificial Life (commonly abbreviated as ALife). The word "artificial" refers to the fact that humans are involved in the creation process. The artificial life forms might be completely unlike natural forms of life, with different chemical compositions, and even computer programs exhibiting life-like behaviours.

Carlos Gershenson

Even when concepts similar to emergence have been used since antiquity, we lack an agreed definition. However, emergence has been identified as one of the main features of complex systems. Most would agree on the statement ``life is complex''. Thus, understanding emergence and complexity should benefit the study of living systems. It can be said that life emerges from the interactions of complex molecules. But how useful is this to understand living systems? Artificial life (ALife) has been developed in recent decades to study life using a synthetic approach: build it to understand it. ALife systems are not so complex, be them soft (simulations), hard (robots), or wet (protocells). Then, we can aim at first understanding emergence in ALife, for then using this knowledge in biology. I argue that to understand emergence and life, it becomes useful to use information as a framework. In a general sense, I define emergence as information that is not present at one scale but is present at another scale. This perspective avoids problems of studying emergence from a materialist framework, and can be also useful in the study of self-organization and complexity.

Hyobin Kim, Stalin Muñoz, Pamela Osuna et al.

Robustness and evolvability are essential properties to the evolution of biological networks. To determine if a biological network is robust and/or evolvable, it is required to compare its functions before and after mutations. However, this sometimes takes a high computational cost as the network size grows. Here we develop a predictive method to estimate the robustness and evolvability of biological networks without an explicit comparison of functions. We measure antifragility in Boolean network models of biological systems and use this as the predictor. Antifragility occurs when a system benefits from external perturbations. By means of the differences of antifragility between the original and mutated biological networks, we train a convolutional neural network (CNN) and test it to classify the properties of robustness and evolvability. We found that our CNN model successfully classified the properties. Thus, we conclude that our antifragility measure can be used as a predictor of the robustness and evolvability of biological networks.

Carlos Gershenson, Vito Trianni, Justin Werfel et al.

Self-organization can be broadly defined as the ability of a system to display ordered spatio-temporal patterns solely as the result of the interactions among the system components. Processes of this kind characterize both living and artificial systems, making self-organization a concept that is at the basis of several disciplines, from physics to biology and engineering. Placed at the frontiers between disciplines, Artificial Life (ALife) has heavily borrowed concepts and tools from the study of self-organization, providing mechanistic interpretations of life-like phenomena as well as useful constructivist approaches to artificial system design. Despite its broad usage within ALife, the concept of self-organization has been often excessively stretched or misinterpreted, calling for a clarification that could help with tracing the borders between what can and cannot be considered self-organization. In this review, we discuss the fundamental aspects of self-organization and list the main usages within three primary ALife domains, namely "soft" (mathematical/computational modeling), "hard" (physical robots), and "wet" (chemical/biological systems) ALife. We also provide a classification to locate this research. Finally, we discuss the usefulness of self-organization and related concepts within ALife studies, point to perspectives and challenges for future research, and list open questions. We hope that this work will motivate discussions related to self-organization in ALife and related fields.

Carlos Gershenson, Vito Trianni, Justin Werfel et al.

Self-organization has been an important concept within a number of disciplines, which Artificial Life (ALife) also has heavily utilized since its inception. The term and its implications, however, are often confusing or misinterpreted. In this work, we provide a mini-review of self-organization and its relationship with ALife, aiming at initiating discussions on this important topic with the interested audience. We first articulate some fundamental aspects of self-organization, outline its usage, and review its applications to ALife within its soft, hard, and wet domains. We also provide perspectives for further research.

Sanjay Goel, Stephen F. Bush, Carlos Gershenson

Traffic signals are ubiquitous devices that first appeared in 1868. Recent advances in information and communications technology (ICT) have led to unprecedented improvements in such areas as mobile handheld devices (i.e., smartphones), the electric power industry (i.e., smart grids), transportation infrastructure, and vehicle area networks. Given the trend towards interconnectivity, it is only a matter of time before vehicles communicate with one another and with infrastructure. In fact, several pilots of such vehicle-to-vehicle and vehicle-to-infrastructure (e.g. traffic lights and parking spaces) communication systems are already operational. This survey of autonomous and self-organized traffic signaling control has been undertaken with these potential developments in mind. Our research results indicate that, while many sophisticated techniques have attempted to improve the scheduling of traffic signal control, either real-time sensing of traffic patterns or a priori knowledge of traffic flow is required to optimize traffic. Once this is achieved, communication between traffic signals will serve to vastly improve overall traffic efficiency.

C. A. Piña-García, Dongbing Gu, J. Mario Siqueiros-García et al.

In this paper, we conduct a literature review of laws of motion based on stochastic search strategies which are mainly focused on exploring highly dynamic environments. In this regard, stochastic search strategies represent an interesting alternative to cope with uncertainty and reduced perceptual capabilities. This study aims to present an introductory overview of research in terms of directional rules and searching methods mainly based on bio-inspired approaches. This study critically examines the role of animal searching behavior applied to random walk models using stochastic rules and kinesis or taxis. The aim of this study is to examine existing techniques and to select relevant work on random walks and analyze their actual contributions. In this regard, we cover a wide range of displacement events with an orientation mechanism given by a reactive behavior or a source-seeking behavior. Finally, we conclude with a discussion concerning the usefulness of using optimal foraging strategies as a reliable methodology.

Carlos Gershenson, Dirk Helbing

The slower is faster (SIF) effect occurs when a system performs worse as its components try to do better. Thus, a moderate individual efficiency actually leads to a better systemic performance. The SIF effect takes place in a variety of phenomena. We review studies and examples of the SIF effect in pedestrian dynamics, vehicle traffic, traffic light control, logistics, public transport, social dynamics, ecological systems, and adaptation. Drawing on these examples, we generalize common features of the SIF effect and suggest possible future lines of research.

Germinal Cocho, Jorge Flores, Carlos Gershenson et al.

Statistical studies of languages have focused on the rank-frequency distribution of words. Instead, we introduce here a measure of how word ranks change in time and call this distribution \emph{rank diversity}. We calculate this diversity for books published in six European languages since 1800, and find that it follows a universal lognormal distribution. Based on the mean and standard deviation associated with the lognormal distribution, we define three different word regimes of languages: "heads" consist of words which almost do not change their rank in time, "bodies" are words of general use, while "tails" are comprised by context-specific words and vary their rank considerably in time. The heads and bodies reflect the size of language cores identified by linguists for basic communication. We propose a Gaussian random walk model which reproduces the rank variation of words in time and thus the diversity. Rank diversity of words can be understood as the result of random variations in rank, where the size of the variation depends on the rank itself. We find that the core size is similar for all languages studied.

Gerardo Febres, Klaus Jaffe, Carlos Gershenson

We compared entropy for texts written in natural languages (English, Spanish) and artificial languages (computer software) based on a simple expression for the entropy as a function of message length and specific word diversity. Code text written in artificial languages showed higher entropy than text of similar length expressed in natural languages. Spanish texts exhibit more symbolic diversity than English ones. Results showed that algorithms based on complexity measures differentiate artificial from natural languages, and that text analysis based on complexity measures allows the unveiling of important aspects of their nature. We propose specific expressions to examine entropy related aspects of tests and estimate the values of entropy, emergence, self-organization and complexity based on specific diversity and message length.

Tom Froese, Carlos Gershenson, David A. Rosenblueth

The extended mind hypothesis has stimulated much interest in cognitive science. However, its core claim, i.e. that the process of cognition can extend beyond the brain via the body and into the environment, has been heavily criticized. A prominent critique of this claim holds that when some part of the world is coupled to a cognitive system this does not necessarily entail that the part is also constitutive of that cognitive system. This critique is known as the "coupling-constitution fallacy". In this paper we respond to this reductionist challenge by using an evolutionary robotics approach to create a minimal model of two acoustically coupled agents. We demonstrate how the interaction process as a whole has properties that cannot be reduced to the contributions of the isolated agents. We also show that the neural dynamics of the coupled agents has formal properties that are inherently impossible for those neural networks in isolation. By keeping the complexity of the model to an absolute minimum, we are able to illustrate how the coupling-constitution fallacy is in fact based on an inadequate understanding of the constitutive role of nonlinear interactions in dynamical systems theory.

Carlos Gershenson

In this chapter, concepts related to information and computation are reviewed in the context of human computation. A brief introduction to information theory and different types of computation is given. Two examples of human computation systems, online social networks and Wikipedia, are used to illustrate how these can be described and compared in terms of information and computation.

Michele Amoretti, Carlos Gershenson

Ultra-large scale (ULS) systems are becoming pervasive. They are inherently complex, which makes their design and control a challenge for traditional methods. Here we propose the design and analysis of ULS systems using measures of complexity, emergence, self-organization, and homeostasis based on information theory. These measures allow the evaluation of ULS systems and thus can be used to guide their design. We evaluate the proposal with a ULS computing system provided with adaptation mechanisms. We show the evolution of the system with stable and also changing workload, using different fitness functions. When the adaptive plan forces the system to converge to a predefined performance level, the nodes may result in highly unstable configurations, that correspond to a high variance in time of the measured complexity. Conversely, if the adaptive plan is less "aggressive", the system may be more stable, but the optimal performance may not be achieved.

Bruce Edmonds, Carlos Gershenson

The Turing Test (TT) checks for human intelligence, rather than any putative general intelligence. It involves repeated interaction requiring learning in the form of adaption to the human conversation partner. It is a macro-level post-hoc test in contrast to the definition of a Turing Machine (TM), which is a prior micro-level definition. This raises the question of whether learning is just another computational process, i.e. can be implemented as a TM. Here we argue that learning or adaption is fundamentally different from computation, though it does involve processes that can be seen as computations. To illustrate this difference we compare (a) designing a TM and (b) learning a TM, defining them for the purpose of the argument. We show that there is a well-defined sequence of problems which are not effectively designable but are learnable, in the form of the bounded halting problem. Some characteristics of human intelligence are reviewed including it's: interactive nature, learning abilities, imitative tendencies, linguistic ability and context-dependency. A story that explains some of these is the Social Intelligence Hypothesis. If this is broadly correct, this points to the necessity of a considerable period of acculturation (social learning in context) if an artificial intelligence is to pass the TT. Whilst it is always possible to 'compile' the results of learning into a TM, this would not be a designed TM and would not be able to continually adapt (pass future TTs). We conclude three things, namely that: a purely "designed" TM will never pass the TT; that there is no such thing as a general intelligence since it necessary involves learning; and that learning/adaption and computation should be clearly distinguished.