The role of forgetting in the evolution and learning of language

Lewis signalling games illustrate how language might evolve from random behaviour. The probability of evolving an optimal signalling language is, in part, a function of what learning strategy the agents use. Here we investigate three learning strategies, each of which allows agents to forget old experience. In each case, we find that forgetting increases the probability of evolving an optimal language. It does this by making it less likely that past partial success will continue to reinforce suboptimal practice. The learning strategies considered here show how forgetting past experience can promote learning in the context of games with suboptimal equilibria.     

Learning Game-Specific Spatially-Oriented Heuristics

This paper describes an architecture that begins with enough general knowledge to play any board game as a novice, and then shifts its decision-making emphasis to learned, game-specific, spatially-oriented heuristics. From its playing experience, it acquires game-specific knowledge about both patterns and spatial concepts. The latter are proceduralized as learned, spatially-oriented heuristics. These heuristics represent a new level of feature aggregation that effectively focuses the program's attention. While training against an external expert, the program integrates these heuristics robustly. After training it exhibits both a new emphasis on spatially-oriented play and the ability to respond to novel situations in a spatially-oriented manner. This significantly improves performance against a variety of opponents. In addition, we address the issue of context on pattern learning. The procedures described here move toward learning spatially-oriented heuristics for autonomous programs in other spatial domains.     

Learning,goals, and learning goals: A perspective on goal-driven learning

In cognitive science, artificial intelligence, psychology, and education, a growing body of research supports the view that the learning process is strongly influenced by the learner's goals. The fundamental tenet ofgoal-driven learning is that learning is largely an active and strategic process in which the learner, human or machine, attempts to identify and satisfy its information needs in the context of its tasks and goals, its prior knowledge, its capabilities, and environmental opportunities for learning. This article examines the motivations for adopting a goal-driven model of learning, the relationship between task goals and learning goals, the influences goals can have on learning, and the pragmatic implications of the goal-driven learning model. It presents a new integrative framework for understanding the goal-driven learning process and applies this framework to characterizing research on goal-driven learning.     

The role of feedback and self-efficacy on web-based learning: The social cognitive perspective

The social cognitive perspective of self-regulated learning suggests that effective learning is determined by the interactions among personal, behavioral, and environmental influences; particularly, high self-regulated learners hold higher motivation (personal), apply better learning strategies (behavioral) and respond to environmental demand more appropriately (environmental). The study thus uses the social cognitive perspective to explore the role of self-efficacy (personal), student feedback behavior, use of learning strategies (behavioral), performance and receiving feedback (environmental) in Web-based learning. There were 76 university students participated in this study. Both quantitative and qualitative methods were applied for data analysis. The results supported that self-efficacy predicted student use of learning strategies and related to elaborated feedback behavior (personal → behavioral). High self-efficacy students applied more high-level learning strategies, such as elaborative strategy and critical thinking. Students who provided elaborated feedback also had higher self-efficacy than those who did not. Moreover, receiving elaborative feedback significantly promoted student self-efficacy (environmental → personal), while receiving knowledge of correct response improved student performance. However, the results indicated that feedback behaviors did not predict academic performance, which may be interfered by modeling effects.     

The effect of learning by imitation on a multi-robot system based on the coupling of low-level imitation strategy and online learning for cognitive map building

It is assumed that future robots must coexist with human beings and behave as their companions. Consequently, the complexities of their tasks would increase. To cope with these complexities, scientists are inclined to adopt the anatomical functions of the brain for the mapping and the navigation in the field of robotics. While admitting the continuous works in improving the brain models and the cognitive mapping for robots’ navigation, we show, in this paper, that learning by imitation leads to a positive effect not only in human behavior but also in the behavior of a multi-robot system. We present the interest of low-level imitation strategy at individual and social levels in the case of robots. Particularly, we show that adding a simple imitation capability to the brain model for building a cognitive map improves the ability of individual cognitive map building and boosts sharing information in an unknown environment. Taking into account the notion of imitative behavior, we also show that the individual discoveries (i.e. goals) could have an effect at the social level and therefore inducing the learning of new behaviors at the individual level. To analyze and validate our hypothesis, a series of experiments has been performed with and without a low-level imitation strategy in the multi-robot system.     

An algorithmic theory of learning: Robust concepts and random projection

We study the phenomenon of cognitive learning from an algorithmic standpoint. How does the brain effectively learn concepts from a small number of examples despite the fact that each example contains a huge amount of information? We provide a novel algorithmic analysis via a model of robust concept learning (closely related to “margin classifiers”), and show that a relatively small number of examples are sufficient to learn rich concept classes. The new algorithms have several advantages—they are faster, conceptually simpler, and resistant to low levels of noise. For example, a robust half-space can be learned in linear time using only a constant number of training examples, regardless of the number of attributes. A general (algorithmic) consequence of the model, that “more robust concepts are easier to learn”, is supported by a multitude of psychological studies.     

The role of errors in learning computer software

Little research has been done examining the role of errors in learning computer software. It is argued, though, that understanding the errors that people make while learning new software is important to improving instruction. The purpose of the current study was to (a) develop a meaningful and practical system for classifying computer software errors, (b) determine the relative effect of specific error types on learning, and (c) examine the impact of computer ability on error behaviour. Thirty-six adults (18 males, 18 females), representing three computer ability levels (beginner, intermediate, and advanced), volunteered to think out loud while they learned the rudimentary steps (moving the cursor, using a menu, entering data) required to use a spreadsheet software package. Classifying errors according to six basic categories (action, orientation, knowledge processing, seeking information, state, and style) proved to be useful. Errors related to knowledge processing, seeking information, and actions were observed most frequently, however, state, style, and orientation errors had the largest immediate negative impact on learning. A more detailed analysis revealed that subjects were most vulnerable when observing, trying to remember, and building mental models. The effect of errors was partially related to computer ability, however beginner, intermediate and advanced users were remarkably similar with respect to the prevalence of errors.     

Cognitive agents and machine learning by example: Representation with conceptual graphs

As machine learning (ML) and artificial intelligence progress, more complex tasks can be addressed, quite often by cascading or combining existing models and technologies, known as the bottom‐up design. Some of those tasks are addressed by agents, which attempt to simulate or emulate higher cognitive abilities that cover a broad range of functions; hence, those agents are named cognitive agents. We formulate, implement, and evaluate such a cognitive agent, which combines learning by example with ML. The mechanisms, algorithms, and theories to be merged when training a cognitive agent to read and learn how to represent knowledge have not, to the best of our knowledge, been defined by the current state‐of‐the‐art research. The task of learning to represent knowledge is known as semantic parsing, and we demonstrate that it is an ability that may be attained by cognitive agents using ML, and the knowledge acquired can be represented by using conceptual graphs. By doing so, we create a cognitive agent that simulates properties of “learning by example,” while performing semantic parsing with good accuracy. Due to the unique and unconventional design of this agent, we first present the model and then gauge its performance, showcasing its strengths and weaknesses.     

Strategic best-response learning in multiagent systems

We present a novel and uniform formulation of the problem of reinforcement learning against bounded memory adaptive adversaries in repeated games, and the methodologies to accomplish learning in this novel framework. First we delineate a novel strategic definition of best response that optimises rewards over multiple steps, as opposed to the notion of tactical best response in game theory. We show that the problem of learning a strategic best response reduces to that of learning an optimal policy in a Markov Decision Process (MDP). We deal with both finite and infinite horizon versions of this problem. We adapt an existing Monte Carlo based algorithm for learning optimal policies in such MDPs over finite horizon, in polynomial time. We show that this new efficient algorithm can obtain higher average rewards than a previously known efficient algorithm against some opponents in the contract game. Though this improvement comes at the cost of increased domain knowledge, simple experiments in the Prisoner's Dilemma, and coordination games show that even when no extra domain knowledge (besides that an upper bound on the opponent's memory size is known) is assumed, the error can still be small. We also experiment with a general infinite-horizon learner (using function-approximation to tackle the complexity of history space) against a greedy bounded memory opponent and show that while it can create and exploit opportunities of mutual cooperation in the Prisoner's Dilemma game, it is cautious enough to ensure minimax payoffs in the Rock–Scissors–Paper game.     

并行机器学习算法基础体系前沿进展综述

大数据环境下,机器学习算法受到前所未有的重视。总结和分析了传统机器学习算法在海量数据场景下出现的若干问题,基于当代并行机分类回顾了国内外并行机器学习算法的研究现状,并归纳总结了并行机器学习算法在各种基础体系下存在的问题。针对大数据环境下并行机器学习算法进行了简要的总结,并对其发展趋势作了展望。     

结合集成学习与迁移学习的标签比例学习方法

标签比例学习（LLP）是一种将实例放入包中的机器学习方法,它只提供包中的实例信息和标签比例信息,而不提供标签信息。针对多个相关任务的LLP问题,提出了一种基于迁移学习的标签比例集成学习模型,简称AT-LLP,该模型通过在任务之间构建共享参数来连接相关任务,将源任务中学习到的知识迁移到目标任务中,从而提高目标任务的学习效率。同时该算法引入了集成学习算法,在分类器多轮迭代的学习过程中,不断调整训练集的权重系数,进一步将弱分类器训练为强分类器。实验表明,所提AT-LLP模型比现有LLP方法具有更好的性能。     

Supervised machine learning in multimodal learning analytics for estimating success in project‐based learning

Multimodal learning analytics provides researchers new tools and techniques to capture different types of data from complex learning activities in dynamic learning environments. This paper investigates the use of diverse sensors, including computer vision, user‐generated content, and data from the learning objects (physical computing components), to record high‐fidelity synchronised multimodal recordings of small groups of learners interacting. We processed and extracted different aspects of the students' interactions to answer the following question: Which features of student group work are good predictors of team success in open‐ended tasks with physical computing? To answer this question, we have explored different supervised machine learning approaches (traditional and deep learning techniques) to analyse the data coming from multiple sources. The results illustrate that state‐of‐the‐art computational techniques can be used to generate insights into the "black box" of learning in students' project‐based activities. The features identified from the analysis show that distance between learners' hands and faces is a strong predictor of students' artefact quality, which can indicate the value of student collaboration. Our research shows that new and promising approaches such as neural networks, and more traditional regression approaches can both be used to classify multimodal learning analytics data, and both have advantages and disadvantages depending on the research questions and contexts being investigated. The work presented here is a significant contribution towards developing techniques to automatically identify the key aspects of students success in project‐based learning environments, and to ultimately help teachers provide appropriate and timely support to students in these fundamental aspects.     

统计学习理论的原理与应用

经验风险与实际风险间的不一致是一个长期困扰机器学习（各种分类或拟合问题）的难题。统计学习理论提供了对这一问题的部分解决方法。本文从理论及现实两方面介绍经验风险与实际风险间的不一致现象，定义了算法的泛化能力，简单介绍了统计学习理论各组成部分的主要结论，并总结了这一理论的应用方向和存在的问题。     

From learning in the limit to stochastic finite learning

Inductive inference can be considered as one of the fundamental paradigms of algorithmic learning theory. We survey results recently obtained and show their impact to potential applications.     

变长增量型极限学习机及其泛化性能研究*

极限学习机（ELM）在训练过程中无需调整隐层节点参数,因其高效的训练方式被广泛应用于分类和回归,然而极限学习机也面临着结构选择与过拟合等严重等问题。为了解决此问题,针对隐层节点增量数目对收敛速度以及训练时间的影响进行了研究,提出一种利用网络输出误差的变化率控制网络增长速度的变长增量型极限学习机算法(VI-ELM)。通过对多个数据集进行回归和分类问题分析实验,结果表明,本文提出的方法能够以更高效的训练方式获得良好的泛化性能。     

Using 3D printing technology with experiential learning strategies to improve preengineering students' comprehension of abstract scientific concepts and hands‐on ability

This study combined 3D printing technology with experiential learning strategies (ELS) to design a hands‐on curriculum for preengineering students. The participants learned interdisciplinary knowledge and abstract scientific concepts through the curriculum. The study implemented a quasi‐experimental design to examine whether the students who learned using the 3D printing technology with ELS demonstrated better learning performances regarding the comprehension of abstract scientific concepts and hands‐on ability. This study selected 184 10th‐grade students from five classes, which were divided into three groups. The experimental process was conducted over a period of 11 weeks (for a total duration of 960 min). It was found that all of the preengineering students improved their comprehension of abstract scientific concepts. The students who learned using the 3D printing technology understood abstract scientific concepts better than those who learned using the traditional hands‐on tools, and the students who learned using the 3D printing technology with ELS demonstrated better hands‐on ability than the other two groups. Using 3D printing technology with ELS resulted in significant positive effects on the participants' handmade processes, in which the students reinforced the connection between knowledge and handmade products, resulting in better comprehension of abstract scientific concepts and hands‐on ability.