Cognition is meant as the process of acquiring knowledge from the world. This process is supposed... more Cognition is meant as the process of acquiring knowledge from the world. This process is supposed to happen within agents, which build such knowledge with the purpose to use it to determine their actions on the world. Following Peircean ideas, we postulate that such knowledge is encoded by means of signs. According to Peirce, signs are anything that can be used to represent anything else. Also, for Peirce, to represent means to be able to generate another sign, called the interpretant of the original sign, which still holds the same power of interpretability, I.e, its power to be transformed into a new sign, holding this same power. This happens through a process called semiosis, the process by which a sign is transformed into an interpretant. This whole process is performed with the aim of subsidizing the agent in deciding its behavior. So, even though the semiosis process has the power to continue infinitely, it usually stops whenever the generated interpretant brings enough infor...
In this article we describe an application of Evolutionary Computation to Algorithm Composition. ... more In this article we describe an application of Evolutionary Computation to Algorithm Composition. The individuals of the population were defined as groups of four voices: soprano, contralto, tenor and bass, or “chords”; and they are potential solutions for a selection process. Each choir was evaluated under three criteria: melody, harmony and octave. Based on the ordering of consonance of musical intervals we use the notion of approximating a sequence of notes to its harmonically compatible note or tonal center. ...
The purpose of this paper is to discuss methods for evaluating the intelligence of intelligent sy... more The purpose of this paper is to discuss methods for evaluating the intelligence of intelligent systems by means of Computational Semiotics concepts. Instead of looking at the system as a black box and testing its behavior, the process described in this paper focus on architectural details of structures, organizations, processes and algorithms used in the construction of the intelligent system, evaluating the impact of using these elements in the overall intelligent behavior exhibited by the system. It proposes then an "insider" type of metrics that, coupled to "outsider" metrics, we hope will be important for the determination of general metrics of intelligence in intelligent systems.
Recently, semiotics has started being the focus of attention of AI researchers due to its interes... more Recently, semiotics has started being the focus of attention of AI researchers due to its interesting capabilities in symbolic processing and knowledge representation. In this paper, we propose the Fielded Object Network (FON), a framework aimed at integrating many scientific fields related to artificial intelligence, e.g. artificial life and distributed artificial intelligence (DAI), in order to get a knowledge representation tool capable of performing semiotic processing. Following this trend, this work presents the basis of FON and shows how it can be used to a hierarchical knowledge processing in intelligent systems. To show that, we implement a Generalized Subsistence Machine (GSM) proposed by Meystel [6] using a FON approach. We also provide simulation results for an AGV application built under the proposed framework.
In this paper we introduce the use of contextual transformation functions to adjust membership fu... more In this paper we introduce the use of contextual transformation functions to adjust membership functions in fuzzy systems. We address both linear and nonlinear functions to perform linear or nonlinear context adaptation, respectively. The key issue is to encode knowledge in a standard frame of reference, and have its meaning tuned to the situation by means of an adequate transformation reflecting the influence of context in the interpretation of a concept. Linear context adaptation is simple and fast. Nonlinear context adaptation is more computationally expensive, but due to its nonlinear characteristic, different parts of base membership functions can be stretched or expanded to best fit the desired format. Here we use a genetic algorithm to find a nonlinear transformation function, given the base membership functions and a set of data extracted from environment classified by means of fuzzy concepts.
The aim of this paper is to introduce a unified framework for soft computing based on the computa... more The aim of this paper is to introduce a unified framework for soft computing based on the computational semiotics approach. Derived from semiotics, a classic discipline in human sciences, computational semiotics provides a mathematical foundation for the concept of knowledge and for knowledge processing that is suitable for intelligent systems design and implementation. As a result, a new perspective to study and to develop intelligent systems emerges. The theory introduces the mathematical definition of objects, object systems and object networks. They are used to model the different types of knowledge used in building intelligent systems. Particularly in this paper, we focus on the use of computational semiotics framework to construct fuzzy systems, neural networks and evolutive systems. The paper also addresses soft computing system in an unified manner.
– Meaning is a key problem in intelligent systems design. Most approaches in literature still ado... more – Meaning is a key problem in intelligent systems design. Most approaches in literature still adopt naïve definitions, which cause them many subtle problems such as the symbol grounding problem. In this work we propose a semiotic approach to this problem based on the triadic model of sign developed by C.S. Peirce. In order to observe the key aspects of this model of simulated semiosis (meaning processes) we developed an experimental protocol inspired on the work of Luc Steels (the talking heads experiment). We argue that, with the proposed theory, meaning emerges within each agent without any external interference (from other agents or the creature designer himself); they can exhibit semiosis, in a simulated form. 1.
This paper deals with the influence of the context in fuzzy rule base systems. The linguistic var... more This paper deals with the influence of the context in fuzzy rule base systems. The linguistic variable definition of Zadeh is modified to permit context adaptation, and inference procedure is modified to handle context adaptation when evaluating fuzzy concepts. Procedures to determine context in different situations are provided. Context determination may be viewed as a kind of learning. An application example concerning supervisory control of group of elevators is also considered.
A busca pela compreensão de si mesma é um dos propósitos mais antigos da humanidade. Em boa parte... more A busca pela compreensão de si mesma é um dos propósitos mais antigos da humanidade. Em boa parte das investigações sobre o assunto, entende-se que os seres são constituídos de cognição, emoções e ações em constante interação. Embora possuam semelhanças, as abordagens propostas apresentam inconsistências, divergindo, por exemplo, na natureza das interconexões ou nos portadores destes elementos. Muitas perspectivas consideram unicamente os humanos como detentores da cognição e emoção, enquanto outras entendem que animais não humanos ou sistemas como robôs poderiam, de um modo ou de outro, possuir cognição, emoções e, assim, de alguma forma, ser considerados agentes morais. Este livro reúne contribuições de diversas áreas e perspectivas referentes ao estudo da cognição, emoção e ação e das conexões entre elas. Os seus capítulos foram agrupados em três partes, de acordo com a predominância de seu conteúdo: história da filosofia; ciências cognitivas; ciências humanas e sociais. Há, aind...
Abstract: In this paper we present the development of an episodic memory module for the cognitive... more Abstract: In this paper we present the development of an episodic memory module for the cognitive architecture controlling an autonomous mobile simulated robot, in a simulated 3D environment. The episodic memory has the role of improving the navigation system of the robot, by evoking the objects to be considered in planning, according to episodic remembrance of earlier contacts with those objects in the past. We introduce the main background on human memory systems and episodic memory study, and provide the main ideas behind our experiment. Keywords: navigation 1.
Autonomous mobile robots emerged as an important kind of transportation system in warehouses and ... more Autonomous mobile robots emerged as an important kind of transportation system in warehouses and factories. In this work, we present the use of MECA cognitive architecture in the development of an artificial mind for an autonomous robot responsible for multiple tasks, including transportation of packages along a factory floor, environment exploration, warehouse inventory, its internal energy management, self-monitoring and dealing with human operators and other robots. The present text provides a detailed specification for the architecture and its software implementation. Future work will present the simulation results under different configurations, together with a detailed analysis of the architecture performance and its generalization for autonomous robot control.
This work describes the application of the Baars-Franklin Architecture (BFA), an artificial consc... more This work describes the application of the Baars-Franklin Architecture (BFA), an artificial consciousness approach, to synthesize a mind (a control system) for an artificial creature. The BFA was reported in the literature as a successful control system to different kinds of agents: CMattie, IDA and CTS. In this paper, BFA is for the first time applied for controlling an artificial (virtual) creature. Firstly we introduce the theoretical foundations of this approach for the development of a conscious agent. Then we explain the architecture of our agent and at the end we discuss the results and first impressions of this approach.
Cognition is meant as the process of acquiring knowledge from the world. This process is supposed... more Cognition is meant as the process of acquiring knowledge from the world. This process is supposed to happen within agents, which build such knowledge with the purpose to use it to determine their actions on the world. Following Peircean ideas, we postulate that such knowledge is encoded by means of signs. According to Peirce, signs are anything that can be used to represent anything else. Also, for Peirce, to represent means to be able to generate another sign, called the interpretant of the original sign, which still holds the same power of interpretability, I.e, its power to be transformed into a new sign, holding this same power. This happens through a process called semiosis, the process by which a sign is transformed into an interpretant. This whole process is performed with the aim of subsidizing the agent in deciding its behavior. So, even though the semiosis process has the power to continue infinitely, it usually stops whenever the generated interpretant brings enough infor...
In this article we describe an application of Evolutionary Computation to Algorithm Composition. ... more In this article we describe an application of Evolutionary Computation to Algorithm Composition. The individuals of the population were defined as groups of four voices: soprano, contralto, tenor and bass, or “chords”; and they are potential solutions for a selection process. Each choir was evaluated under three criteria: melody, harmony and octave. Based on the ordering of consonance of musical intervals we use the notion of approximating a sequence of notes to its harmonically compatible note or tonal center. ...
The purpose of this paper is to discuss methods for evaluating the intelligence of intelligent sy... more The purpose of this paper is to discuss methods for evaluating the intelligence of intelligent systems by means of Computational Semiotics concepts. Instead of looking at the system as a black box and testing its behavior, the process described in this paper focus on architectural details of structures, organizations, processes and algorithms used in the construction of the intelligent system, evaluating the impact of using these elements in the overall intelligent behavior exhibited by the system. It proposes then an "insider" type of metrics that, coupled to "outsider" metrics, we hope will be important for the determination of general metrics of intelligence in intelligent systems.
Recently, semiotics has started being the focus of attention of AI researchers due to its interes... more Recently, semiotics has started being the focus of attention of AI researchers due to its interesting capabilities in symbolic processing and knowledge representation. In this paper, we propose the Fielded Object Network (FON), a framework aimed at integrating many scientific fields related to artificial intelligence, e.g. artificial life and distributed artificial intelligence (DAI), in order to get a knowledge representation tool capable of performing semiotic processing. Following this trend, this work presents the basis of FON and shows how it can be used to a hierarchical knowledge processing in intelligent systems. To show that, we implement a Generalized Subsistence Machine (GSM) proposed by Meystel [6] using a FON approach. We also provide simulation results for an AGV application built under the proposed framework.
In this paper we introduce the use of contextual transformation functions to adjust membership fu... more In this paper we introduce the use of contextual transformation functions to adjust membership functions in fuzzy systems. We address both linear and nonlinear functions to perform linear or nonlinear context adaptation, respectively. The key issue is to encode knowledge in a standard frame of reference, and have its meaning tuned to the situation by means of an adequate transformation reflecting the influence of context in the interpretation of a concept. Linear context adaptation is simple and fast. Nonlinear context adaptation is more computationally expensive, but due to its nonlinear characteristic, different parts of base membership functions can be stretched or expanded to best fit the desired format. Here we use a genetic algorithm to find a nonlinear transformation function, given the base membership functions and a set of data extracted from environment classified by means of fuzzy concepts.
The aim of this paper is to introduce a unified framework for soft computing based on the computa... more The aim of this paper is to introduce a unified framework for soft computing based on the computational semiotics approach. Derived from semiotics, a classic discipline in human sciences, computational semiotics provides a mathematical foundation for the concept of knowledge and for knowledge processing that is suitable for intelligent systems design and implementation. As a result, a new perspective to study and to develop intelligent systems emerges. The theory introduces the mathematical definition of objects, object systems and object networks. They are used to model the different types of knowledge used in building intelligent systems. Particularly in this paper, we focus on the use of computational semiotics framework to construct fuzzy systems, neural networks and evolutive systems. The paper also addresses soft computing system in an unified manner.
– Meaning is a key problem in intelligent systems design. Most approaches in literature still ado... more – Meaning is a key problem in intelligent systems design. Most approaches in literature still adopt naïve definitions, which cause them many subtle problems such as the symbol grounding problem. In this work we propose a semiotic approach to this problem based on the triadic model of sign developed by C.S. Peirce. In order to observe the key aspects of this model of simulated semiosis (meaning processes) we developed an experimental protocol inspired on the work of Luc Steels (the talking heads experiment). We argue that, with the proposed theory, meaning emerges within each agent without any external interference (from other agents or the creature designer himself); they can exhibit semiosis, in a simulated form. 1.
This paper deals with the influence of the context in fuzzy rule base systems. The linguistic var... more This paper deals with the influence of the context in fuzzy rule base systems. The linguistic variable definition of Zadeh is modified to permit context adaptation, and inference procedure is modified to handle context adaptation when evaluating fuzzy concepts. Procedures to determine context in different situations are provided. Context determination may be viewed as a kind of learning. An application example concerning supervisory control of group of elevators is also considered.
A busca pela compreensão de si mesma é um dos propósitos mais antigos da humanidade. Em boa parte... more A busca pela compreensão de si mesma é um dos propósitos mais antigos da humanidade. Em boa parte das investigações sobre o assunto, entende-se que os seres são constituídos de cognição, emoções e ações em constante interação. Embora possuam semelhanças, as abordagens propostas apresentam inconsistências, divergindo, por exemplo, na natureza das interconexões ou nos portadores destes elementos. Muitas perspectivas consideram unicamente os humanos como detentores da cognição e emoção, enquanto outras entendem que animais não humanos ou sistemas como robôs poderiam, de um modo ou de outro, possuir cognição, emoções e, assim, de alguma forma, ser considerados agentes morais. Este livro reúne contribuições de diversas áreas e perspectivas referentes ao estudo da cognição, emoção e ação e das conexões entre elas. Os seus capítulos foram agrupados em três partes, de acordo com a predominância de seu conteúdo: história da filosofia; ciências cognitivas; ciências humanas e sociais. Há, aind...
Abstract: In this paper we present the development of an episodic memory module for the cognitive... more Abstract: In this paper we present the development of an episodic memory module for the cognitive architecture controlling an autonomous mobile simulated robot, in a simulated 3D environment. The episodic memory has the role of improving the navigation system of the robot, by evoking the objects to be considered in planning, according to episodic remembrance of earlier contacts with those objects in the past. We introduce the main background on human memory systems and episodic memory study, and provide the main ideas behind our experiment. Keywords: navigation 1.
Autonomous mobile robots emerged as an important kind of transportation system in warehouses and ... more Autonomous mobile robots emerged as an important kind of transportation system in warehouses and factories. In this work, we present the use of MECA cognitive architecture in the development of an artificial mind for an autonomous robot responsible for multiple tasks, including transportation of packages along a factory floor, environment exploration, warehouse inventory, its internal energy management, self-monitoring and dealing with human operators and other robots. The present text provides a detailed specification for the architecture and its software implementation. Future work will present the simulation results under different configurations, together with a detailed analysis of the architecture performance and its generalization for autonomous robot control.
This work describes the application of the Baars-Franklin Architecture (BFA), an artificial consc... more This work describes the application of the Baars-Franklin Architecture (BFA), an artificial consciousness approach, to synthesize a mind (a control system) for an artificial creature. The BFA was reported in the literature as a successful control system to different kinds of agents: CMattie, IDA and CTS. In this paper, BFA is for the first time applied for controlling an artificial (virtual) creature. Firstly we introduce the theoretical foundations of this approach for the development of a conscious agent. Then we explain the architecture of our agent and at the end we discuss the results and first impressions of this approach.
In this work, we propose a computational approach to the triadic model of Peircean semiosis (mean... more In this work, we propose a computational approach to the triadic model of Peircean semiosis (meaning processes). We investigate theoretical constraints about the feasibility of simulated semiosis. These constraints, which are basic requirements for the simulation of semiosis, refer to the synthesis of irreducible triadic relations (Sign–Object–Interpretant). We examine the internal organization of the triad S–O–I, that is, the relative position of its elements and how they relate to each other. We also suggest a multi-level approach based on self-organization principles. In this context, semiosis is described as an emergent process. Nevertheless, the term ‘emergence’ is often used in a very informal way in the so called ‘emergent’ computation, without clear explanations and/or definitions. In this paper, we discuss in some detail the meaning of the theoretical terms ‘emergence’ and ‘emergent’, showing how such an analysis can lead to improvements of the algorithm proposed. Keywords Meaning - Semiosis - Emergence - Simulation - C. S. Peirce
Modern semiotics is a branch of logics that formally defines symbol-based communication. In recen... more Modern semiotics is a branch of logics that formally defines symbol-based communication. In recent years, the semiotic classification of signs has been invoked to support the notion that symbols are uniquely human. Here we show that alarm-calls such as those used by African vervet monkeys (Cercopithecus aethiops), logically satisfy the semiotic definition of symbol. We also show that the acquisition of vocal symbols in vervet monkeys can be successfully simulated by a computer program based on minimal semiotic and neurobiological constraints. The simulations indicate that learning depends on the tutor–predator ratio, andthat apprentice-generated auditory mistakes in vocal symbol interpretation have little effect on the learning rates of apprentices (up to 80% of mistakes are tolerated). In contrast, just 10% of apprentice-generated visual mistakes in predator identification will prevent any vocal symbol to be correctly associated with a predator call in a stable manner. Tutor unreliability was also deleterious to vocal symbol learning: a mere 5% of “lying” tutors were able to completely disrupt symbol learning, invariably leading to the acquisition of incorrect associations by apprentices. Our investigation corroborates the existence of vocal symbols in a non-human species, and indicates that symbolic competence emerges spontaneously from classical associative learning mechanisms when the conditioned stimuli are self-generated, arbitrary and socially efficacious.We propose that more exclusive properties of human language, such as syntax, may derive from the evolution of higher-order domains for neural association, more removed from both the sensory input and the motor output, able to support the gradual complexification of grammatical categories into syntax.
In last decades, neuroscience and psychology research findings about emotion have been increasing... more In last decades, neuroscience and psychology research findings about emotion have been increasingly attracting the attention of many researchers in Computer Science and Artificial Intelligence (AI) areas. AI, interested in cognitive processes modeling and simulation, clearly see that emotion is a crucial element to model perception, learning, decision processes, memory, behavior and others functions. Currently, two Computer Science areas use emotion concepts on their research: Human-Computer Interaction and systems whose internal architecture is emotion-based.Even considering current state-of-art projects, theoretical aspects of emotion to be employed in computational systems projects are scarcely discussed. Our research intends to discuss these problems and propose tentative directions to solve them.First, (ii) the lack of a well defined scientific framework to approach 'Artificial Emotion', with few advanced attempts been published suggesting one. Besides that, a close look at some projects provides a non-exhausted list of (ii) important questions they might face to achieve trustworthy results. They can be grouped in two types, theoretical-conceptual or computational questions. Examples are: How to integrate emotion with other mechanisms, such as: sensory, learn, selection and communication? Can artificial emotion be an emergent property? What kind of data structure and computational mechanisms should be used to both capture and represent the complexity of emotion processes? What kind of experimental test allows to better explore emotion-based models? Moreover, an essential question to be answered is related to which extent supposed structural complexity involved in emotion phenomenon can be abstracted and modeled, not missing important brain structure interactions and not being too complex to impair computational representation.Last, these facts mainly contribute to a third noticeable problem: (iii) lack of comparative analysis between projects and also within same project, with beneficial comparisons of emotion and non-emotion-based experiments. Positively, overcome these challenges can be an important step to field progress goes beyond engineering applications and towards a more scientific discipline.
Advances in Artificial IntelligenceSBIA …, Jan 1, 2004
This is a project on Articial Life where we simulate an ecosystem that allows cooperative intera... more This is a project on Articial Life where we simulate an ecosystem that allows cooperative interaction between agents, including intra-specic predatorwarning communication in a virtual environment of predatory events. We propose, based on Peircean semiotics and informed by neuroethological constraints, an experiment to simulate the emergence of symbolic communication among articial creatures. Here we describe the simulation environment and the creatures' control architectures, and briey present obtained results.
"In this book, our goal is to present the most representative research projects in computational ... more "In this book, our goal is to present the most representative research projects in computational semiotics at the present time. Considering the relevance of the semiotic approach for future developments in artificial intelligence, we suggest—and certainly hope—that the collection will be a major contribution to the field. Within the book, we have contributions from philosophers, cognitive scientists, computer scientists, and engineers, all focused on the singular agenda of inquiring how semiotics works with intelligent system techniques in order to create newer and more robust types of intelligent systems. One of the main criticisms of which intelligent systems developers are accused is being naïve in their approaches to the question, “What is intelligence?” Therefore, it is as important to take into
account the philosophy of the mind and to be aware of the issues of that field within current philosophic speculations as it is to develop a practical methodology of the technologies of semiotic intelligent systems.
The book is divided into four parts. Section I: Theoretical Issues includes chapters with a more philosophical tone. Section II: Discussions on Semiotic Intelligent Systems includes chapters that still have a philosophical flavor but move beyond philosophical speculations toward some kind of implementation of intelligent systems. Section III: Semiotics in the Development of Intelligent Systems includes chapters that use semiotics in some sense for the development of an intelligent system. Finally, the fourth part, Semiotic Systems Implementations, includes chapters whose authors claim to be using semiotic concepts in intelligent systems implementation."
Este livro reúne contribuições de diversas áreas e perspectivas referentes ao estudo da cognição,... more Este livro reúne contribuições de diversas áreas e perspectivas referentes ao estudo da cognição, emoção e ação e das conexões entre elas. Os seus capítulos foram agrupados em três partes, de acordo com a predominância de seu conteúdo: história da filosofia; ciências cognitivas; ciências humanas e sociais. Há, ainda, uma entrevista com o Prof. Lauro F. B. da Silveira, a quem a obra é dedicada.
Uploads
Papers by Ricardo Gudwin
Keywords Meaning - Semiosis - Emergence - Simulation - C. S. Peirce
symbol learning: a mere 5% of “lying” tutors were able to completely disrupt symbol learning, invariably leading to the acquisition of incorrect associations by apprentices. Our investigation corroborates the existence of vocal symbols in a non-human species, and indicates that symbolic competence emerges spontaneously from classical associative learning mechanisms when the conditioned stimuli are self-generated, arbitrary and socially efficacious.We propose that more exclusive properties of human language, such as syntax, may derive from the evolution of higher-order domains for neural association, more removed from both the sensory input
and the motor output, able to support the gradual complexification of grammatical categories into syntax.
control architectures, and briey present obtained results.
account the philosophy of the mind and to be aware of the issues of that field within current philosophic speculations as it is to develop a practical methodology of the technologies of semiotic intelligent systems.
The book is divided into four parts. Section I: Theoretical Issues includes chapters with a more philosophical tone. Section II: Discussions on Semiotic Intelligent Systems includes chapters that still have a philosophical flavor but move beyond philosophical speculations toward some kind of implementation of intelligent systems. Section III: Semiotics in the Development of Intelligent Systems includes chapters that use semiotics in some sense for the development of an intelligent system. Finally, the fourth part, Semiotic Systems Implementations, includes chapters whose authors claim to be using semiotic concepts in intelligent systems implementation."