Capturing aesthetic intention during interactive evolution

Interactive Evolutionary Systems (IES) are capable of generating and evolving large numbers of alternative designs. When using such systems, users are continuously required to interact with the system by making evaluations and selections of the designs that are being generated and evolved. The evolutionary process is therefore led by the visual aesthetic intentions of the user. However, due to the limited size of the computer screen and fuzzy nature of aesthetic evaluations, evolution is usually a mutation-driven and divergent process. The convergent mechanisms typically found in standard Evolutionary Algorithms are more difficult to achieve with IES.To address this problem, this paper presents a computational framework that creates an IES with a higher level of convergence without requiring additional actions from the user. This can be achieved by incorporating a Neural Network based learning mechanism, called a General Regression Neural Network (GRNN), into an IES. GRNN analyses the user's aesthetic evaluations during the interactive evolutionary process and is thereby able to approximate their implicit aesthetic intentions. The approximation is a regression of aesthetic appeals conditioned on the corresponding designs. This learning mechanism allows the framework to infer which designs the users may find desirable. For the users, this reduces the tedious work of evaluating and selecting designs.Experiments have been conducted using the framework to support the process of parametric tuning of facial characters. In this paper we analyze the performance of our approach and discuss the issues that we believe are essential for improving the usability and efficiency of IES.     

智能代理和学习对象的集成—— 一种应用于在线教学的设计思想

讨论了一种很有发展前景的E教学开发设计思想,集智能代理和学习对象为一体来开发更智能化,更高交互性和高扩展性的在线教学系统。在该系统中,每个对象都被附加上一个智能代理,从而在在线学习中像一个代理程序一样,从学习环境中获得各项实时参数,然后根据这些参数采取相应的操作。此外,与内置智能代理的对象一样,用户模块被设计用来记录和保存一切与用户有关的信息,包括习惯的学习方式以及所有在线学习课程当中的活动事件。由于用户模块可以更好地了解每个用户,系统就会以一种更具有针对性的方式工作,就像老师在课堂上可以对不同的学生采取     

Evolving Least Squares Support Vector Machines for Stock Market Trend Mining

In this paper, an evolving least squares support vector machine (LSSVM) learning paradigm with a mixed kernel is proposed to explore stock market trends. In the proposed learning paradigm, a genetic algorithm (GA), one of the most popular evolutionary algorithms (EAs), is first used to select input features for LSSVM learning, i.e., evolution of input features. Then, another GA is used for parameters optimization of LSSVM, i.e., evolution of algorithmic parameters. Finally, the evolving LSSVM learning paradigm with best feature subset, optimal parameters, and a mixed kernel is used to predict stock market movement direction in terms of historical data series. For illustration and evaluation purposes, three important stock indices, S&P 500 Index, Dow Jones Industrial Average (DJIA) Index, and New York Stock Exchange (NYSE) Index, are used as testing targets. Experimental results obtained reveal that the proposed evolving LSSVM can produce some forecasting models that are easier to be interpreted by using a small number of predictive features and are more efficient than other parameter optimization methods. Furthermore, the produced forecasting model can significantly outperform other forecasting models listed in this paper in terms of the hit ratio. These findings imply that the proposed evolving LSSVM learning paradigm can be used as a promising approach to stock market tendency exploration.     

Evolutionary Design Systems and Generative Processes

Design tools that aim not only to analyse and evaluate, but also to generate and explore alternative design proposals are now under development. An evolutionary paradigm is presented as a basis for creating such tools. First, the evolutionary paradigm is shown to be the only successful design system on which this new phase of design tool could be based. Secondly, any characterisation of design as a search problem is argued to be a serious misconception. Instead it is proposed that evolutionary design systems should be seen as generative processes that are able to evaluate their own output. Thirdly, a generic framework for generative evolutionary design systems is presented. Fourth, the generative process is introduced as a key element within this generic framework. The role of the environment within this process is fundamental. Finally, the direction of future research within the evolutionary design paradigm is discussed with possible short and long term goals being presented.     

Evolution and Incremental Learning in the Iterated Prisoner's Dilemma

This paper examines the comparative performance and adaptability of evolutionary, learning, and memetic strategies to different environment settings in the iterated prisoner's dilemma (IPD). A memetic adaptation framework is developed for IPD strategies to exploit the complementary features of evolution and learning. In the paradigm, learning serves as a form of directed search to guide evolving strategies to attain eventual convergence towards good strategy traits, while evolution helps to minimize disparity in performance among learning strategies. Furthermore, a double-loop incremental learning scheme (ILS) that incorporates a classification component, probabilistic update of strategies and a feedback learning mechanism is proposed and incorporated into the evolutionary process. A series of simulation results verify that the two techniques, when employed together, are able to complement each other's strengths and compensate for each other's weaknesses, leading to the formation of strategies that will adapt and thrive well in complex, dynamic environments.     

Evolving Intelligence in Humans and Machines: Integrative Evolving Connectionist Systems Approach

One of the main properties of human intelligence is that it is evolving (developing, revealing, unfolding) based on: (1) Genetically "wired" rules; (2) Experience and learning during life time. The paper argues that we need to understand how the brain operates at its different levels of information processing and then use some of these principles "when building intelligent machines. Without "drowning" into the sea of details, some main principles of information processing in the brain at cognitive-, neuronal-, genetic-, and particle field information levels are reviewed. The paper takes the approach towards understanding and building integrative connectionist systems, that integrate principles and rules from different hierarchical levels of information processing in their dynamic interaction, as an approach to develop intelligent machines. Examples given include: simple evolving connectionist systems; evolving spiking neural networks; integrative neurogenetic models; genetically defined robots; quantum evolutionary algorithms for exponentially faster optimization; integrative quantum neural networks. Some of the new integrative models are significantly faster in feature selection and learning and can be used to solve efficiently NP complete biological and engineering problems for adaptive, incremental learning in a large dimensional space-an important feature of the human intelligence. They can also help to better understand complex information processes in the brain, especially how information processes at different information levels interact to achieve a higher level intelligent human behavior. Open questions, challenges and directions for further research are presented.     

Evolving fuzzy neural networks for supervised/unsupervised onlineknowledge-based learning

This paper introduces evolving fuzzy neural networks (EFuNNs) as a means for the implementation of the evolving connectionist systems (ECOS) paradigm that is aimed at building online, adaptive intelligent systems that have both their structure and functionality evolving in time. EFuNNs evolve their structure and parameter values through incremental, hybrid supervised/unsupervised, online learning. They can accommodate new input data, including new features, new classes, etc., through local element tuning. New connections and new neurons are created during the operation of the system. EFuNNs can learn spatial-temporal sequences in an adaptive way through one pass learning and automatically adapt their parameter values as they operate. Fuzzy or crisp rules can be inserted and extracted at any time of the EFuNN operation. The characteristics of EFuNNs are illustrated on several case study data sets for time series prediction and spoken word classification. Their performance is compared with traditional connectionist methods and systems. The applicability of EFuNNs as general purpose online learning machines, what concerns systems that learn from large databases, life-long learning systems, and online adaptive systems in different areas of engineering are discussed.     

Discovery as Autonomous Learning from the Environment

Discovery involves collaboration among many intelligent activities. However, little is known about how and in what form such collaboration occurs. In this article, a framework is proposed for autonomous systems that learn and discover from their environment. Within this framework, many intelligent activities such as perception, action, exploration, experimentation, learning, problem solving, and new term construction can be integrated in a coherent way. The framework is presented in detail through an implemented system called LIVE, and is evaluated through the performance of LIVE on several discovery tasks. The conclusion is that autonomous learning from the environment is a feasible approach for integrating the activities involved in a discovery process.     

Synergy between Activity Theory and goal/scenario modeling for requirements elicitation,analysis, and evolution

ContextIt is challenging to develop comprehensive, consistent, analyzable requirements models for evolving requirements. This is particularly critical for certain highly interactive types of socio-technical systems that involve a wide range of stakeholders with disparate backgrounds; system success is often dependent on how well local social constraints are addressed in system design.ObjectiveThis paper describes feasibility research, combining a holistic social system perspective provided by Activity Theory (AT), a psychological paradigm, with existing system development methodologies and tools, specifically goal and scenario modeling.MethodAT is used to understand the relationships between a system, its stakeholders, and the system’s evolving context. The User Requirements Notation (URN) is used to produce rigorous, analyzable specifications combining goal and scenario models. First, an AT language was developed constraining the framework for automation, second consistency heuristics were developed for constructing and analyzing combined AT/URN models, third a combined AT/URN methodology was developed, and consequently applied to a proof-of-concept system.ResultsAn AT language with limited tool support was developed, as was a combined AT/URN methodology. This methodology was applied to an evolving disease management system to demonstrate the feasibility of adapting AT for use in system development with existing methodologies and tools. Bi-directional transformations between the languages allow proposed changes in system design to be propagated to AT models for use in stakeholder discussions regarding system evolution.ConclusionsThe AT framework can be constrained for use in requirements elicitation and combined with URN tools to provide system designs that include social system perspectives. The developed AT/URN methodology can help engineers to track the impact on system design due to requirement changes triggered by changes in the system’s social context. The methodology also allows engineers to assess the impact of proposed system design changes on the social elements of the system context.     

具有行为强化学习能力的人工生命进化模型设计

人工生命进化模型设计的关键问题是学习与进化之间的关系,在自主体生存期内的学习过程可以通过不同的遗传方式指导个体行为的进化。该文利用进化算法和人工神经网络的研究方法,设计了两种不同的人工生命自主体的进化模型,模型解决了先天的遗传进化和后天的个体神经系统强化学习的有机结合问题,并且得出结论认为,强化学习有助于自主体适应复杂的外部环境,同时学习也可以直接或间接地使该适应性成为自主体遗传基因上的固定成分。     

面向流数据分类的在线学习综述

流数据分类旨在从连续不断到达的流式数据中增量学习一个从输入变量到类标变量的映射函数,以便对随时到达的测试数据进行准确分类.在线学习范式作为一种增量式的机器学习技术,是流数据分类的有效工具.主要从在线学习的角度对流数据分类算法的研究现状进行综述.具体地,首先介绍在线学习的基本框架和性能评估方法,然后着重介绍在线学习算法在一般流数据上的工作现状,在高维流数据上解决“维度诅咒”问题的工作现状,以及在演化流数据上处理“概念漂移”问题的工作现状,最后讨论高维和演化流数据分类未来仍然存在的挑战和亟待研究的方向.     

基于单亲生物无性繁殖的一种进化算法

基于单亲细胞的无性繁殖-分裂,提出了一类新的DNA分子自进化优化算法,算法模拟了单亲细胞在恒定环境下的一种进化演变过程,论证了在恒定环境中,单亲细胞DNA分子在生命进化的基本特征-分裂和变异的交互作用下,以1的概率演化到同一个体,即环境中的全局最优点,文中对算法进行了形式描述和理论探索,给出院 收敛性证明,通过
实例仿真和计算,得出了有益的结论。     

基于强化学习的综合能源系统管理综述

为了满足日益增长的能源需求并减少对环境的破坏, 节能成为全球经济和社会发展的一项长远战略方针, 加强能源管理能够提高能源利用效率、促进节能减排. 然而, 可再生能源和柔性负载的接入使得综合能源系统(Integrated energy system, IES)发展成为具有高度不确定性的复杂动态系统, 给现代化能源管理带来巨大的挑战. 强化学习(Reinforcement learning, RL)作为一种典型的交互试错型学习方法, 适用于求解具有不确定性的复杂动态系统优化问题, 因此在综合能源系统管理问题中得到广泛关注. 本文从模型和算法的层面系统地回顾了利用强化学习求解综合能源系统管理问题的现有研究成果, 并从多时间尺度特性、可解释性、迁移性和信息安全性4个方面提出展望.     

Modelling socio-ecological systems with MAIA: A biogas infrastructure simulation

Similar to other renewable energy technologies, the development of a biogas infrastructure in the Netherlands is going through social, institutional and ecological evolution. To study this complex evolutionary process, we built a comprehensive agent-based model of this infrastructure. We used an agent-based modelling framework called MAIA to build this model with the initial motivation that it facilitates modelling complex institutional structures. The modelling experience however proved that MAIA can also act as an integrated solution to address other major modelling challenges identified in the literature for modelling evolving socio-ecological systems. Building on comprehensive reviews, we reflect on our modelling experience and address four key challenges of modelling evolving socio-ecological systems using agents: (1) design and parameterization of models of agent behaviour and decision-making, (2) system representation in the social and spatial dimension, (3) integration of socio-demographic, ecological, and biophysical models, (4) verification, validation and sensitivity analysis of such ABMs.     

面向智能教育的自适应学习关键技术与应用

本文是关于我们获得2020年度吴文俊人工智能科学技术奖主要工作的一个介绍。该成果针对自适应学习中面临的教学资源表示困难、学习状态诊断困难以及学习策略设计困难等关键技术难题,首先构建数据驱动的教学资源无监督表示新框架,提高了教学资源质量评估和内容检索的精度和效率。其次提出基于深度学习的学习者认知诊断新方法,突破了以量表为基础的教育测量理论研究范式。然后设计基于知识匹配的个性化推荐技术以及多目标匹配的自适应推荐技术,满足了智能教育场景的复杂约束与学习者的多样目标需求。最后,本文成果研发了面向基础教育的智能教育系统——智学网,已在全国推广使用,对我国智能教育发展具有积极意义。     

COMBINING MULTI‐AGENT PARADIGM AND MEMETIC COMPUTING FOR PERSONALIZED AND ADAPTIVE LEARNING EXPERIENCES

Learning is a critical support mechanism for industrial and academic organizations to enhance the skills of employees and students and, consequently, the overall competitiveness in the new economy. The remarkable velocity and volatility of modern knowledge require novel learning methods offering additional features as efficiency, task relevance and personalization. Computational Intelligence methodologies can support e‐Learning system designers in two different aspects: (1) they represent the most suitable solution able to support learning content and activities, personalized to specific needs and influenced by specific preferences of the learner and (2) they assist designers with computationally efficient methods to develop “in time” e‐Learning environments. This article attempts to achieve both results by exploiting an ontological representations of learning environment and memetic approach of optimization, integrated into a cooperative distributed problem solving framework. This synergy enables multi‐island memetic approach managing a collection of models and processes for adapting an e‐Learning system to the learner expectations and to formulate objectives in an effective and dynamic intelligent way. More precisely, our proposal exploits ontological representations of learning environment and a memetic distributed problem‐solving approach to generate the best learning presentation and, at the same time, minimize the computational efforts necessary to compute optimal learning experiences.     

Student Behavior Modeling for an E-Learning System Offering Personalized Learning Experiences

With the advent of computing and communication technologies, it has become possible for a learner to expand his or her knowledge irrespective of the place and time. Web-based learning promotes active and independent learning. Large scale e-learning platforms revolutionized the concept of studying and it also paved the way for innovative and effective teaching-learning process. This digital learning improves the quality of teaching and also promotes educational equity. However, the challenges in e-learning platforms include dissimilarities in learner’s ability and needs, lack of student motivation towards learning activities and provision for adaptive learning environment. The quality of learning can be enhanced by analyzing the online learner’s behavioral characteristics and their application of intelligent instructional strategy. It is not possible to identify the difficulties faced during the process through evaluation after the completion of e-learning course. It is thus essential for an e-learning system to include component offering adaptive control of learning and maintain user’s interest level. In this research work, a framework is proposed to analyze the behavior of online learners and motivate the students towards the learning process accordingly so as to increase the rate of learner’s objective attainment. Catering to the demands of e-learner, an intelligent model is presented in this study for e-learning system that apply supervised machine learning algorithm. An adaptive e-learning system suits every category of learner, improves the learner’s performance and paves way for offering personalized learning experiences.     

Dynamic parameter optimization of evolutionary computation for on-line prediction of time series with changing dynamics

This paper introduces a dynamic evolving computation system (DECS) model, for adaptive on-line learning, and its application for dynamic time series prediction. DECS evolve through evolving clustering method and evolutionary computation for structure learning, Levenberg–Marquardt method for parameter learning, learning and accommodate new input data. DECS is created and updated during the operation of the system. At each time moment the output of DECS is calculated through a knowledge rule inference system based on m-most activated fuzzy rules which are dynamically chosen from a fuzzy rule set. An approach is proposed for a dynamic creation of a first order Takagi–Sugeno type fuzzy rule set for the DECS model. The fuzzy rules can be inserted into DECS before, or during its learning process, and the rules can also be extracted from DECS during, or after its learning process. It is demonstrated that DECS can effectively learn complex temporal sequences in an adaptive way and outperform some existing models.     

Genetic fuzzy systems to evolve interaction strategies in multiagent systems

This article suggests an evolutionary approach to designing interaction strategies for multiagent systems, focusing on strategies modeled as fuzzy rule‐based systems. The aim is to learn models evolving database and rule bases to improve agent performance when playing in a competitive environment. In competitive situations, data for learning and tuning are rare, and rule bases must jointly evolve with the databases. We introduce an evolutionary algorithm whose operators use variable length chromosomes, a hierarchical relationship among individuals through fitness, and a scheme that successively explores and exploits the search space along generations. Evolution of interaction strategies uncovers unknown and unexpected agent behaviors and allows a richer analysis of negotiation mechanisms and their role as a coordination protocol. An application concerning an electricity market illustrates the effectiveness of the approach. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 971–991, 2007.     

有效智慧学习环境的设计框架

随着信息技术的深入发展，使学习系统智能化是计算机科学和教育领域许多研究人员的共同目标。近年来， 智慧教室、智慧学习环境、下一代学习空间成为研究热点。文章系统梳理了智慧学习环境的定义、功能要素，站在认知学习视 角，提出了有效智慧学习环境的设计理念与技术模块设计框架。