Information Theory for Agents in Artificial Intelligence,Psychology, and Economics

This review looks at some of the central relationships between artificial intelligence, psychology, and economics through the lens of information theory, specifically focusing on formal models of decision-theory. In doing so we look at a particular approach that each field has adopted and how information theory has informed the development of the ideas of each field. A key theme is expected utility theory, its connection to information theory, the Bayesian approach to decision-making and forms of (bounded) rationality. What emerges from this review is a broadly unified formal perspective derived from three very different starting points that reflect the unique principles of each field. Each of the three approaches reviewed can, in principle at least, be implemented in a computational model in such a way that, with sufficient computational power, they could be compared with human abilities in complex tasks. However, a central critique that can be applied to all three approaches was first put forward by Savage in The Foundations of Statistics and recently brought to the fore by the economist Binmore: Bayesian approaches to decision-making work in what Savage called ‘small worlds’ but cannot work in ‘large worlds’. This point, in various different guises, is central to some of the current debates about the power of artificial intelligence and its relationship to human-like learning and decision-making. Recent work on artificial intelligence has gone some way to bridging this gap but significant questions remain to be answered in all three fields in order to make progress in producing realistic models of human decision-making in the real world in which we live in.     

The Markov blanket trick: On the scope of the free energy principle and active inference

The free energy principle (FEP) has been presented as a unified brain theory, as a general principle for the self-organization of biological systems, and most recently as a principle for a theory of every thing. Additionally, active inference has been proposed as the process theory entailed by FEP that is able to model the full range of biological and cognitive events. In this paper, we challenge these two claims. We argue that FEP is not the general principle it is claimed to be, and that active inference is not the all-encompassing process theory it is purported to be either. The core aspects of our argumentation are that (i) FEP is just a way to generalize Bayesian inference to all domains by the use of a Markov blanket formalism, a generalization we call the Markov blanket trick; and that (ii) active inference presupposes successful perception and action instead of explaining them.     

Graphical Models in Reconstructability Analysis and Bayesian Networks

Reconstructability Analysis (RA) and Bayesian Networks (BN) are both probabilistic graphical modeling methodologies used in machine learning and artificial intelligence. There are RA models that are statistically equivalent to BN models and there are also models unique to RA and models unique to BN. The primary goal of this paper is to unify these two methodologies via a lattice of structures that offers an expanded set of models to represent complex systems more accurately or more simply. The conceptualization of this lattice also offers a framework for additional innovations beyond what is presented here. Specifically, this paper integrates RA and BN by developing and visualizing: (1) a BN neutral system lattice of general and specific graphs, (2) a joint RA-BN neutral system lattice of general and specific graphs, (3) an augmented RA directed system lattice of prediction graphs, and (4) a BN directed system lattice of prediction graphs. Additionally, it (5) extends RA notation to encompass BN graphs and (6) offers an algorithm to search the joint RA-BN neutral system lattice to find the best representation of system structure from underlying system variables. All lattices shown in this paper are for four variables, but the theory and methodology presented in this paper are general and apply to any number of variables. These methodological innovations are contributions to machine learning and artificial intelligence and more generally to complex systems analysis. The paper also reviews some relevant prior work of others so that the innovations offered here can be understood in a self-contained way within the context of this paper.     

A Security-Enhanced Image Communication Scheme Using Cellular Neural Network

In the current network and big data environment, the secure transmission of digital images is facing huge challenges. The use of some methodologies in artificial intelligence to enhance its security is extremely cutting-edge and also a development trend. To this end, this paper proposes a security-enhanced image communication scheme based on cellular neural network (CNN) under cryptanalysis. First, the complex characteristics of CNN are used to create pseudorandom sequences for image encryption. Then, a plain image is sequentially confused, permuted and diffused to get the cipher image by these CNN-based sequences. Based on cryptanalysis theory, a security-enhanced algorithm structure and relevant steps are detailed. Theoretical analysis and experimental results both demonstrate its safety performance. Moreover, the structure of image cipher can effectively resist various common attacks in cryptography. Therefore, the image communication scheme based on CNN proposed in this paper is a competitive security technology method.     

Quantum-Like Interdependence Theory Advances Autonomous Human–Machine Teams (A-HMTs)

As humanity grapples with the concept of autonomy for human–machine teams (A-HMTs), unresolved is the necessity for the control of autonomy that instills trust. For non-autonomous systems in states with a high degree of certainty, rational approaches exist to solve, model or control stable interactions; e.g., game theory, scale-free network theory, multi-agent systems, drone swarms. As an example, guided by artificial intelligence (AI, including machine learning, ML) or by human operators, swarms of drones have made spectacular gains in applications too numerous to list (e.g., crop management; mapping, surveillance and fire-fighting systems; weapon systems). But under states of uncertainty or where conflict exists, rational models fail, exactly where interdependence theory thrives. Large, coupled physical or information systems can also experience synergism or dysergism from interdependence. Synergistically, the best human teams are not only highly interdependent, but they also exploit interdependence to reduce uncertainty, the focus of this work-in-progress and roadmap. We have long argued that interdependence is fundamental to human autonomy in teams. But for A-HMTs, no mathematics exists to build from rational theory or social science for their design nor safe or effective operation, a severe weakness. Compared to the rational and traditional social theory, we hope to advance interdependence theory first by mapping similarities between quantum theory and our prior findings; e.g., to maintain interdependence, we previously established that boundaries reduce dysergic effects to allow teams to function (akin to blocking interference to prevent quantum decoherence). Second, we extend our prior findings with case studies to predict with interdependence theory that as uncertainty increases in non-factorable situations for humans, the duality in two-sided beliefs serves debaters who explore alternatives with tradeoffs in the search for the best path going forward. Third, applied to autonomous teams, we conclude that a machine in an A-HMT must be able to express itself to its human teammates in causal language however imperfectly.     

Neural Dynamics under Active Inference: Plausibility and Efficiency of Information Processing

Active inference is a normative framework for explaining behaviour under the free energy principle—a theory of self-organisation originating in neuroscience. It specifies neuronal dynamics for state-estimation in terms of a descent on (variational) free energy—a measure of the fit between an internal (generative) model and sensory observations. The free energy gradient is a prediction error—plausibly encoded in the average membrane potentials of neuronal populations. Conversely, the expected probability of a state can be expressed in terms of neuronal firing rates. We show that this is consistent with current models of neuronal dynamics and establish face validity by synthesising plausible electrophysiological responses. We then show that these neuronal dynamics approximate natural gradient descent, a well-known optimisation algorithm from information geometry that follows the steepest descent of the objective in information space. We compare the information length of belief updating in both schemes, a measure of the distance travelled in information space that has a direct interpretation in terms of metabolic cost. We show that neural dynamics under active inference are metabolically efficient and suggest that neural representations in biological agents may evolve by approximating steepest descent in information space towards the point of optimal inference.     

Hierarchical Human Action Recognition with Self-Selection Classifiers via Skeleton Data

Human action recognition has become one of the most active research topics in human-computer interaction and artificial intelligence, and has attracted much attention. Here, we employ a low-cost optical sensor Kinect to capture the action information of the human skeleton. We then propose a two-level hierarchical human action recognition model with self-selection classifiers via skeleton data. Especially different optimal classifiers are selected by probability voting mechanism and 10 times 10-fold cross validation at different coarse grained levels. Extensive simulations on a well-known open dataset and results demonstrate that our proposed method is efficient in human action recognition, achieving 94.19% the average recognition rate and 95.61% the best rate.     

基于模型的制冷系统智能化仿真研究

为提高仿真方法对实际制冷空调装置多样性和复杂性的自适应性,将人工智能引入到制冷系统仿真研究中,构建基于数学模型与人工智能技术相结合方式的制冷系统智能仿真理论．本文介绍了上海交通大学在此方面所取得的研究成果,并提出了今后进一步发展的方向．本项研究有利于推进制冷装置设计方法现代化,研究思路对于一般热力系统仿真亦有参考价值．     

基于人工智能技术的IETM业务规则研究

为有效管理人工智能技术操作步骤的规范性,需要对人工智能技术的IETM业务规则进行研究。而当前已经制定的IETM业务规则,在人工智能技术复杂繁多的操作步骤中,许多细节问题没有得到规范管理。为此,提出一种基于人工智能技术的IETM业务规则研究方法。该方法首先确定人工智能技术的IETM业务规则数据模块,再将所有人工智能数据模块进行分类,并分配给各部门相关技术人员进行IETM业务规则的制定,数据模块ETM业务规则的制定过程将采用PCR技术以层次形式来表述,然后将所有分类数据模块IETM业务规则进行汇总、协商、统一,形成完整的人工智能技术的IETM业务规则,管理人工智能技术操作步骤的规范性。实验仿真证明,所提方法能够有效管理人工智能技术操作步骤的规范性。     

Universal scaling law in human behavioral organization

We describe the nature of human behavioral organization, specifically how resting and active periods are interwoven throughout daily life. Active period durations with physical activity count successively above a predefined threshold, when rescaled with individual means, follow a universal stretched exponential (gamma-type) cumulative distribution with characteristic time, both in healthy individuals and in patients with major depressive disorder. On the other hand, resting period durations below the threshold for both groups obey a scale-free power-law cumulative distribution over two decades, with significantly lower scaling exponents in the patients. We thus find universal distribution laws governing human behavioral organization, with a parameter altered in depression.     

红外无损检测在面向等离子体部件检测的应用

建立了主动式内热源激励的红外无损检测平台,并进行了不同缺陷大小的EAST W/Cu 面向等离子体部件(PFC)的无损检测实验(NDT),得到试件表面的红外热图。通过最大温差值融合法消除由试件表面发射率不均匀引起的温度误差,通过快速离散傅里叶变换法提高了图像的信噪比,实现了对W/Cu 面向等离子体部件缺陷的分辨。通过数值模拟的手段对可能影响该检测技术的关键因素进行了定量分析。     

Modeling and simulating human teamwork behaviors using intelligent agents

Among researchers in multi-agent systems there has been growing interest in using intelligent agents to model and simulate human teamwork behaviors. Teamwork modeling is important for training humans in gaining collaborative skills, for supporting humans in making critical decisions by proactively gathering, fusing, and sharing information, and for building coherent teams with both humans and agents working effectively on intelligence-intensive problems. Teamwork modeling is also challenging because the research has spanned diverse disciplines from business management to cognitive science, human discourse, and distributed artificial intelligence. This article presents an extensive, but not exhaustive, list of work in the field, where the taxonomy is organized along two main dimensions: team social structure and social behaviors. Along the dimension of social structure, we consider agent-only teams and mixed human–agent teams. Along the dimension of social behaviors, we consider collaborative behaviors, communicative behaviors, helping behaviors, and the underpinning of effective teamwork—shared mental models. The contribution of this article is that it presents an organizational framework for analyzing a variety of teamwork simulation systems and for further studying simulated teamwork behaviors.     

A Review of Intelligent Fault Diagnosis for High-Speed Trains: Qualitative Approaches

For ensuring the safety and reliability of high-speed trains, fault diagnosis (FD) technique plays an important role. Benefiting from the rapid developments of artificial intelligence, intelligent FD (IFD) strategies have obtained much attention in the field of academics and applications, where the qualitative approach is an important branch. Therefore, this survey will present a comprehensive review of these qualitative approaches from both theoretical and practical aspects. The primary task of this paper is to review the current development of these qualitative IFD techniques and then to present some of the latest results. Another major focus of our research is to introduce the background of high-speed trains, like the composition of the core subsystems, system structure, etc., based on which it becomes convenient for researchers to extract the diagnostic knowledge of high-speed trains, where the purpose is to understand how to use these types of knowledge. By reasonable utilization of the knowledge, it is hopeful to address various challenges caused by the coupling among subsystems of high-speed trains. Furthermore, future research trends for qualitative IFD approaches are also presented.     

人工智能技术的教学讨论——以粒子群算法为例

近年来人工智能技术迅速发展,各高校广泛开展了人工智能课程.但对人工智能教学平台缺乏详细的分析.为此,本文以粒子群算法为例对人工智能课程进行了阐述,并讨论了教学注意事项.研究表明,及时预习基础知识有利于学生理解人工智能模型,结合具体问题讨论人工智能算法将有利于学生掌握技术,拓展人工智能技术应用范围并引导学生对算法本身思考将有助于学生建立正确概念,建立互动式解决实验问题将有助于增加学生的学习热情.     

Information and Self-Organization II: Steady State and Phase Transition

This paper starts from Schrödinger’s famous question “what is life” and elucidates answers that invoke, in particular, Friston’s free energy principle and its relation to the method of Bayesian inference and to Synergetics 2nd foundation that utilizes Jaynes’ maximum entropy principle. Our presentation reflects the shift from the emphasis on physical principles to principles of information theory and Synergetics. In view of the expected general audience of this issue, we have chosen a somewhat tutorial style that does not require special knowledge on physics but familiarizes the reader with concepts rooted in information theory and Synergetics.     

活性行走——图样形成、自组织、复杂系统

活性行走是描述复杂 (或简单 )系统的图样形成和自组织的一个范式 (paradigm) .一个活性行走者的每一步都改变地形 ,其如何选择下一步受改变后地形的影响 .活性行走模型已经成功地应用于很多生物、物理与社会科学系统中 ,其中包括视网膜神经细胞和液体薄层表面反应的图样形成、玻璃中离子的异常传输、蚂蚁群的觅食、高科技经济学中产品的市场竞争 ,等等 .     

A Diversity Model Based on Dimension Entropy and Its Application to Swarm Intelligence Algorithm

The swarm intelligence algorithm has become an important method to solve optimization problems because of its excellent self-organization, self-adaptation, and self-learning characteristics. However, when a traditional swarm intelligence algorithm faces high and complex multi-peak problems, population diversity is quickly lost, which leads to the premature convergence of the algorithm. In order to solve this problem, dimension entropy is proposed as a measure of population diversity, and a diversity control mechanism is proposed to guide the updating of the swarm intelligence algorithm. It maintains the diversity of the algorithm in the early stage and ensures the convergence of the algorithm in the later stage. Experimental results show that the performance of the improved algorithm is better than that of the original algorithm.     

基于忆容器件的神经形态计算研究进展

人工智能的快速发展需要人工智能专用硬件的快速发展,受人脑存算一体、并行处理启发而构建的包含突触与神经元的神经形态计算架构,可以有效地降低人工智能中计算工作的能耗.记忆元件在神经形态计算的硬件实现中展现出巨大的应用价值;相比传统器件,用忆阻器构建突触、神经元能极大地降低计算能耗,然而在基于忆阻器构建的神经网络中,更新、读取等操作存在由忆阻电压电流造成的系统性能量损失.忆容器作为忆阻器衍生器件,被认为是实现低耗能神经网络的潜在器件,引起国内外研究者关注.本文综述了实物/仿真忆容器件及其在神经形态计算中的最新进展,主要包括目:前实物/仿真忆容器原理与特性,代表性的忆容突触、神经元及神经形态计算架构,并通过总结近年来忆容器研究所取得的成果,对当前该领域面临的挑战及未来忆容神经网络发展的重点进行总结与展望.