Socially emotional brain-inspired cognitive architecture framework for artificial intelligence

Artificial Intelligence of the next generation needs to interact with users socially, convincing them in its ability to understand human minds, including emotions. For this to happen, an artificial emotional intelligence is needed, capable of adequate, believable behavior in social emotional interactions. Building on previous developments, the present work extends the general framework of emotional Biologically Inspired Cognitive Architecture (eBICA: Samsonovich, 2013, 2018), endowing it with fluents describing, in addition to appraisals, somatic markers, feelings, emotions, moods, emotional reactions and biases. Key building blocks that integrate them are moral schemas and semantic maps. The model describes interaction of three factors: plans and commitments, moral and ethical values, and somatic comfort. Learning in this framework includes self-organization of semantic maps that in turn may provide guidance for active humanlike learning. Implications for empirical studies and practical applications are discussed together with the expected impact.     

Cognitive technology to capture deep computational concepts with combinators

Computational activity is now recognized as a natural science, and computational and information processes have been discovered in the deep structures of many areas. Computations in the natural world were present long before the invention of computers, but a remarkable shift in understanding its fundamental nature occurs, in fact, before our eyes. The present moment, in fact, is a transition from the concept of computer science as an artificial science to the understanding that information processes are abundant in nature. Computing is recognized as a natural science that studies natural and artificial information processes.In everyday computing, operations are performed on the individual generators, with little attention paid to their internal structure. However, many common operations consist of more primitive constructions connected by a combination mode. The interaction of information processes and corresponding structures is carried out in an environment of “applicative interaction”, their applications to each other, and the study of the properties of this environment allows us to understand the nature of the computations.In the present work, the main attention is paid to elucidating the technological features of computations with individual generators, or objects. Their interaction is considered in an applicative environment, which allows us to elucidate the internal structure of ordinary operations, the knowledge of which allows us to understand their properties. The choice of initial constant generators, considered as generic ones and expressed by combinators, is discussed. These initial generators are used as the main “building blocks” that occur within the larger blocks of the applicative environment in interaction with each other. As a result of the interaction, constructions arise that give representative sets of ordinary operators and embedded computing systems.     

What is the Philosophy of Information?

Computational and information-theoretic research in philosophy has become increasingly fertile and pervasive, giving rise to a wealth of interesting results. In consequence, a new and vitally important field has emerged, the philosophy of information (PI). This essay is the first attempt to analyse the nature of PI systematically. PI is defined as the philosophical field concerned with the critical investigation of the conceptual nature and basic principles of information, including its dynamics, utilisation, and sciences, and the elaboration and application of information-theoretic and computational methodologies to philosophical problems. I argue that PI is a mature discipline for three reasons: it represents an autonomous field of research; it provides an innovative approach to both traditional and new philosophical topics; and it can stand beside other branches of philosophy, offering a systematic treatment of the conceptual foundations of the world of information and the information society.     

Representing decision-makers using styles of behavior: An approach designed for group decision support systems

Supporting decision-making processes when the elements of a group are geographically dispersed and on a tight schedule is a complex task. Aiming to support decision-makers anytime and anywhere, Web-based group decision support systems have been studied. However, the limitations in the decision-makers’ interactions associated to this scenario bring new challenges. In this work, we propose a set of behavioral styles from which decision-makers’ intentions can be modelled into agents. The goal is that, besides having agents represent typical preferences of the decision-makers (towards alternatives and criteria), they can also represent their intentions. To do so, we conducted a survey with 64 participants in order to find homogeneous operating values so as to numerically define the proposed behavioral styles in four dimensions. In addition, we also propose a communication model that simulates the dialogues made by decision-makers in face-to-face meetings. We developed a prototype to simulate decision scenarios and found that agents are capable of acting according to the decision-makers’ intentions and fundamentally benefit from different possible behavioral styles, just as a face-to-face meeting benefits from the heterogeneity of its participants.     

Hack or Die: How Humanity Steers Into Its Post-Digital Future

This article introduces stories as a link between culture and evolution. It elaborates how the decline of interhuman communication leads to a loss of perception, capability for cooperation, and human intelligence and contributes to the current ecocide. It shows how cybernetics hacked the relationship between evolution and machine development, which brought forth the outlines of man’s current digital transformation and future. It suggests that Lucas Pawlik is still working on a possible sustainable future for humanity that Heinz von Foerster tried to initiate.     

Determining Decision Values of Context Awareness in Ubiquitous Computing Environments

Research on context‐aware computing has been focusing on the technology aspect of context acquisition and interpretation of users' surrounding environment or physical context. There is no operational mechanism for integrating context awareness that is driven by user context such as users' ongoing activities and tasks. Although the necessity of integration of sensed context data with users' intent of conduct has been recognized by many researchers, it has never been empirically investigated. Using Analytic Hierarchy Process, we propose an integrated and comprehensive approach that takes into consideration both user and physical context in defining overall context awareness value. The approach is tested using secondary data of user activities in various situations and surrounding environment scenarios. The results suggest several preliminary guidelines for determining representative measures of user and physical context approaches in the design and evaluation of context‐aware systems. Copyright © 2011 John Wiley & Sons, Ltd.     

Empathy framework for embodied conversational agents

Empathy is a complex socio-emotional behavior that results from the interaction between affective and cognitive mechanisms. Equipping embodied conversational agents (ECAs) with empathic capacity can benefit from the integration and evaluation of these low and high level capabilities in a hierarchical manner. Following the theoretical background on empathic behavior in humans, this paper presents a framework to equip ECAs with real time multi-modal empathic interaction capabilities. We present the implementation of this framework, which includes basic dialogue capabilities as well as three levels of empathic behavior in a conversational scenario. Our approach is an inclusive stand on modeling levels of empathy and provides a baseline behavior for empathic interaction.     

A Classification Framework using a Diverse Intensified Strawberry Optimized Neural Network (DISON) for Clinical Decision-making

A novel classification framework for clinical decision making that uses an Extremely Randomized Tree (ERT) based feature selection and a Diverse Intensified Strawberry Optimized Neural network (DISON) is proposed. DISON is a Feed Forward Artificial Neural Network where the optimization of weights and bias is done using a two phase training strategy. Two algorithms namely Strawberry Plant Optimization (SPO) algorithm and Gradient-descent Back-propagation algorithm are used sequentially to identify the optimum weights and bias. The novel two phase training method and the stochastic duplicate-elimination strategy of SPO helps in addressing the issue of local optima associated with conventional neural networks. The relevant attributes are selected based on the feature importance values computed using an ERT classifier.Vertebral Column, Pima Indian diabetes (PID), Cleveland Heart disease (CHD) and Statlog Heart disease (SHD) datasets from the University of California Irvine machine learning repository are used for experimentation. The framework has achieved an accuracy of 87.17% for Vertebral Column, 90.92% for PID, 93.67% for CHD and 94.5% for SHD. The classifier performance has been compared with existing works and is found to be competitive in terms of accuracy, sensitivity and specificity. Wilcoxon test confirms the statistical superiority of the proposed method.     

Reading Emotion From Mouse Cursor Motions: Affective Computing Approach

Affective computing research has advanced emotion recognition systems using facial expressions, voices, gaits, and physiological signals, yet these methods are often impractical. This study integrates mouse cursor motion analysis into affective computing and investigates the idea that movements of the computer cursor can provide information about emotion of the computer user. We extracted 16–26 trajectory features during a choice‐reaching task and examined the link between emotion and cursor motions. Participants were induced for positive or negative emotions by music, film clips, or emotional pictures, and they indicated their emotions with questionnaires. Our 10‐fold cross‐validation analysis shows that statistical models formed from “known” participants (training data) could predict nearly 10%–20% of the variance of positive affect and attentiveness ratings of “unknown” participants, suggesting that cursor movement patterns such as the area under curve and direction change help infer emotions of computer users.     

认知诊断模型的标准误与置信区间估计：并行自助法

认知诊断模型的标准误(Standard Error, SE; 或方差—协方差矩阵)与置信区间(Confidence Interval, CI)在模型参数估计不确定性的度量、项目功能差异检验、项目水平上的模型比较、Q矩阵检验以及探索属性层级关系等领域有重要的理论与实践价值。本研究提出了两种新的SE和CI计算方法：并行参数化自助法和并行非参数化自助法。模拟研究发现：模型完全正确设定时, 在高质量及中等质量项目条件下, 这两种方法在计算模型参数的SE和CI时均有好的表现; 模型参数存在冗余时, 在高质量及中等质量项目条件下, 对于大部分允许存在的模型参数而言, 其SE和CI有好的表现。通过实证数据展示了新方法的价值及计算效率提升效果。