面向产品研发任务的知识层次协调模型及仿真研究

从微观视角量化分析产品研发团队中的知识协调过程,可以更为深入地揭示本质性规律.在理论研究基础上,提炼产品研发任务的复杂性,并提出团队学习是实现知识协调的重要方式.将研发任务的完成以相应知识层次的概率密度函数予以表征,并将团队中的个体学习与协同学习表述为对应层次的知识水平增长.从而构建出复杂知识性任务情境下的知识层次协调...     

Dynamic systems view of learning a three‐tiered theory in physics: robust learning outcomes as attractors

The process of learning scientific knowledge from the dynamic systems viewpoint is studied in terms probabilistic learning model (PLM), where learning accrues from foraging in the epistemic landscape. The PLM leads to the formation of attractor‐type regions of preferred models in an epistemic landscape. The attractor‐type states correspond to robust learning outcomes which are more probable than others. These can be assigned either to the high confidence in model selection or to the dynamic evolution of a learner's proficiency, which depends on the learning history. The results suggest that robust learning states are essentially context dependent, and that learning is a continuous development between these context dependent states. © 2016 Wiley Periodicals, Inc. Complexity 21: 259–267, 2016     

The weight-decay technique in learning from data: an optimization point of view

The technique known as “weight decay” in the literature about learning from data is investigated using tools from regularization theory. Weight-decay regularization is compared with Tikhonov’s regularization of the learning problem and with a mixed regularized learning technique. The accuracies of suboptimal solutions to weight-decay learning are estimated for connectionistic models with a-priori fixed numbers of computational units. The Authors were partially supported by a PRIN grant from the Italian Ministry for University and Research, project “Models and Algorithms for Robust Network Optimization”.     

Properties of learning models in collective action: Rationality of backward-looking players

This article intends to clarify properties of learning models in simulation studies and to conduct a comparison of preceding learning models. Learning models are often used in many simulation studies, but there is no uniform rule of learning. We introduce three technical properties (monotonicity, condition of probability, neutrality) and three rational properties (rationality is fixed situations, rationality in first order stochastic domination, rationality with risk preference in stocahstic situations). We examine Michael Macy's model, the Erev & Roth model, and some others. We find that these models have different properties. Though learning is treated as one of the solutions of social dilemma from the results of Macy's model (Kollock, 1998), Macy's model is peculiar learning model. Learning is not always a solution of social dilemma. A comparison of learning models from a uniform point of view clarifies the properties of each model, and helps to probe conformity of a learning model and human behavior.     

A Gaussian Mixed Model for Learning Discrete Bayesian Networks

In this paper, we address the problem of learning discrete Bayesian networks from noisy data. A graphical model based on a mixture of Gaussian distributions with categorical mixing structure coming from a discrete Bayesian network is considered. The network learning is formulated as a maximum likelihood estimation problem and performed by employing an EM algorithm. The proposed approach is relevant to a variety of statistical problems for which Bayesian network models are suitable—from simple regression analysis to learning gene/protein regulatory networks from microarray data.     

Error Analysis on Hérmite Learning with Gradient Data

This paper deals with Hérmite learning which aims at obtaining the target function from the samples of function values and the gradient values. Error analysis is conducted for these algorithms by means of approaches from convex analysis in the framework of multi-task vector learning and the improved learning rates are derived.     

Emergence of order from chaos by cooperative non-biased learning between random bit-strings

Numerical experiments show that non-biased learning between families of independent and random bit-strings causes order. A parallel distributed learning between these bit-strings is performed by a neural network of the type pattern associator. The system allows emergence of some order in the learning matrix when a non-linear process is used, while a linear learning is unable to break the learning-matrix randomness. This neural network is in fact a complex and non-linear dynamical system, and consequently is able to self-organize order from chaos. It is also a model of collective proto-cognition that would describe biological evolution in species by cooperative learning. Our model suggests that the cause of evolution towards order in complex systems, can be just the learning process.     

Optimal incremental learning under covariate shift

Learning strategies under covariate shift have recently been widely discussed. The density of learning inputs under covariate shift is different from that of test inputs. Learning machines in such environments need to employ special learning strategies to acquire greater capabilities of generalizing through learning. However, incremental learning methods are also used for learning in non-stationary learning environments, which represent a kind of covariate shift. However, the relation between covariate-shift environments and incremental-learning environments has not been adequately discussed. This paper focuses on the covariate shift in incremental-learning environments and our re-construction of a suitable incremental-learning method. Then, the model-selection criterion is also derived, which is to be an essential object function for memetic algorithms to solve these kinds of learning problems.     

基于“动态生成”的大学数学课堂教学

"动态生成"教学观的建立旨在摆脱课堂教学中以教师为中心、强调知识传授的传统教学模式的缺陷,从根本上正确理解课堂教学的复杂性和动态性,构建充满生命活力的大学数学课堂教学生态环境.在用动态生成的视角审视当前大学数学课堂教学中存在的问题的基础上,文章对在课堂教学中如何有效地进行动态生成提出了一些具体的策略:更新教学观念,精心预设弹性化的数学课堂教学方案;根据学生课堂反馈情况及时调整预设,并及时捕捉可利用的动态资源,为学生的生成创造可能的机会;加强教学研究,不断提高课堂教学智慧.     

基于复杂网络上监督学习方法的研究综述

复杂网络已经成为复杂系统分析问题的通用方法,随着人工智能和机器学习的广泛兴起,越来越多的学者开始关注在复杂网络上进行机器学习。监督学习作为机器学习的一个重要组成部分,本文深入研究和总结了基于复杂网络的监督学习方法。首先,本文分别从复杂网络和监督学习的理论基础入手,明确了相似性函数和相异性函数的概念和测度方法,系统梳理了复杂网络的构建方法,并阐明了监督学习的概念及其在机器学习中的地位。其次,介绍了监督学习的几种常用算法,梳理了各种算法的研究现状。然后,提出了基于复杂网络监督学习方法未来关注方向。最后,说明了基于复杂网络监督学习方法的局限性,为相关学者的研究提供了参考。     

Learning horizon and optimal alliance formation

We develop a theoretical Bayesian learning model to examine how a firm’s learning horizon, defined as the maximum distance in a network of alliances across which the firm learns from other firms, conditions its optimal number of direct alliance partners under technological uncertainty. We compare theoretical optima for a ‘close’ learning horizon, where a firm learns only from direct alliance partners, and a ‘distant’ learning horizon, where a firm learns both from direct and indirect alliance partners. Our theory implies that in high tech industries, a distant learning horizon allows a firm to substitute indirect for direct partners, while in low tech industries indirect partners complement direct partners. Moreover, in high tech industries, optimal alliance formation is less sensitive to changes in structural model parameters when a firm’s learning horizon is distant rather than close. Our contribution lies in offering a formal theory of the role of indirect partners in optimal alliance portfolio design that generates normative propositions amenable to future empirical refutation.     

概率统计课程中研究性学习方法探讨

研究性学习的关键问题之一是充分调动学生主动学习的兴趣与热情,提高学生学习效率,变被动学习为主动学习.结合实例给出了四种激发学生学习兴趣的研究性学习方法,即逆向思维、发散思维、基于Matlab的验证学习以及基于实际问题的教学研究方法.这四种学习方式的有机结合能在理论和实践上有效激发学生主动学习热情及学习兴趣,从而大大提高学生学习效率.     

多视角学习综述

随着计算机技术的飞速发展,数据的收集和存储能力得到了极大的提高,在科学研究和社会生活的各个领域,海量表现形式复杂的数据涌现。针对同一对象从不同途径或不同层面获得的特征数据被称为多视角数据。多视角学习是利用事物的多种视角表征进行建模求解的一种新的机器学习方法,它一般需遵循两个原则:1)一致性原则;2)互补性原则。近年来,多视角学习已经引起了广泛的关注和研究。本文对多视角学习算法的研究以及相关理论研究的进展进行了综述,并指出了多视角学习面临的挑战及下一步可能的研究方向。     

A social perspective on technology-enhanced mathematical learning: from collaboration to performance

This paper documents both developments in the technologies used to promote learning mathematics and the influence on research of social theories of learning, through reference to the activities of the International Commission on Mathematical Instruction (ICMI), and argues that these changes provide opportunity for the reconceptualization of our understanding of mathematical learning. Firstly, changes in technology are traced from discipline-specific computer-based software through to Web 2.0-based learning tools. Secondly, the increasing influence of social theories of learning on mathematics education research is reviewed by examining the prevalence of papers and presentations, which acknowledge the role of social interaction in learning, at ICMI conferences over the past 20 years. Finally, it is argued that the confluence of these developments means that it is necessary to re-examine what it means to learn and do mathematics and proposes that it is now possible to view learning mathematics as an activity that is performed rather than passively acquired.     

多示例学习问题研究进展综述

多示例学习是一种特殊的机器学习问题,近年来得到了广泛的关注和研究,许多不同类型的多示例学习算法被提出,用以处理各个领域中的实际问题. 针对多示例学习的算法研究和应用进行了较为详细的综述, 介绍了多示例学习的各种背景假设, 从基于示例水平、包水平、嵌入空间三个方面对多示例学习的常见算法进行了描述, 并给出了多示例学习的算法拓展和若干领域的主要应用.     

Making Organizational Learning Operational: Implications from Learning Classifier Systems

The concepts of organizational learning in organization and management science cover a very wide range of organization-related activities in organization. Since socially situated intelligence is one of such activities, this paper makes the concept of organizational learning operational from the computational viewpoint for investigating socially situated intelligence. In particular, this paper focuses on the characteristics of multiagent learning as one kind of socially situated intelligence, and analyzes them using four operationalized learning mechanisms in organizational learning. A careful investigation on the characteristics of multiagent learning has revealed the following implications: (1) there are two levels in the learning mechanisms for multiagent learning (the individual level and organizational level) and each mechanism is divided into two types (single- and double-loop learning). The integration of these four learning mechanisms improves socially situated intelligence; and (2) the following properties support socially situated intelligence: (a) different dimensions in learning mechanisms, (b) interaction among various levels and types of learning mechanisms in addition to interaction among agents, and (c) combination of exploration at an individual level and exploitation at an organizational level.     

Robot motion classification from the standpoint of learning control

In robot learning control, the learning space for executing the general motions of multi-joint robot manipulators is very complicated. Thus, when the learning controllers are employed as major roles in motion governing, the motion variety requires them to consume excessive amount of memory. Therefore, in spite of their ability to generalize, the learning controllers are usually used as subordinates to conventional controllers or the learning process needs to be repeated each time a new trajectory is encountered. To simplify learning space complexity, we propose, from the standpoint of learning control, that robot motions be classified according to their similarities. The learning controller can then be designed to govern groups of robot motions with high degrees of similarity without consuming excessive memory resources. Motion classification based on using the PUMA 560 robot manipulator demonstrates the effectiveness of the proposed scheme.     

有限时间迭代学习控制

针对任意初态情形, 借助于初始修正吸引子的概念,讨论不确定时变系统能够达到实际完全跟踪性能的迭代学习控制方法.闭环系统中含有限时间控制作用, 在预先指定的区间上实现零误差跟踪,且起始段的系统输出轨迹也可预先规划.分别讨论部分限幅学习与完全限幅学习, 证明闭环系统中各变量的一致有界性以及误差序列的一致收敛性. 变量有界性证明得益于提出的限幅学习算法,特别是完全限幅学习算法可确保参数估值的变化范围.     

Learning with coefficient-based regularization and ℓ1 −penalty

The least-square regression problem is considered by coefficient-based regularization schemes with ?¹??penalty. The learning algorithm is analyzed with samples drawn from unbounded sampling processes. The purpose of this paper is to present an elaborate concentration estimate for the algorithms by means of a novel stepping stone technique. The learning rates derived from our analysis can be achieved in a more general setting. Our refined analysis will lead to satisfactory learning rates even for non-smooth kernels.     

A neural fuzzy control system with structure and parameter learning

A general connectionist model, called neural fuzzy control network (NFCN), is proposed for the realization of a fuzzy logic control system. The proposed NFCN is a feedforward multilayered network which integrates the basic elements and functions of a traditional fuzzy logic controller into a connectionist structure which has distributed learning abilities. The NFCN can be constructed from supervised training examples by machine learning techniques, and the connectionist structure can be trained to develop fuzzy logic rules and find membership functions. Associated with the NFCN is a two-phase hybrid learning algorithm which utilizes unsupervised learning schemes for structure learning and the backpropagation learning scheme for parameter learning. By combining both unsupervised and supervised learning schemes, the learning speed converges much faster than the original backpropagation algorithm. The two-phase hybrid learning algorithm requires exact supervised training data for learning. In some real-time applications, exact training data may be expensive or even impossible to obtain. To solve this problem, a reinforcement neural fuzzy control network (RNFCN) is further proposed. The RNFCN is constructed by integrating two NFCNs, one functioning as a fuzzy predictor and the other as a fuzzy controller. By combining a proposed on-line supervised structure-parameter learning technique, the temporal difference prediction method, and the stochastic exploratory algorithm, a reinforcement learning algorithm is proposed, which can construct a RNFCN automatically and dynamically through a reward-penalty signal (i.e., “good” or “bad” signal). Two examples are presented to illustrate the performance and applicability of the proposed models and learning algorithms.