Can being scared cause tummy aches? Naive theories, ambiguous evidence, and preschoolers' causal inferences.

Causal learning requires integrating constraints provided by domain-specific theories with domain-general statistical learning. In order to investigate the interaction between these factors, the authors presented preschoolers with stories pitting their existing theories against statistical evidence. Each child heard 2 stories in which 2 candidate causes co-occurred with an effect. Evidence was presented in the form: AB→E; CA→E; AD→E; and so forth. In 1 story, all variables came from the same domain; in the other, the recurring candidate cause, A, came from a different domain (A was a psychological cause of a biological effect). After receiving this statistical evidence, children were asked to identify the cause of the effect on a new trial. Consistent with the predictions of a Bayesian model, all children were more likely to identify A as the cause within domains than across domains. Whereas 3.5-year-olds learned only from the within-domain evidence, 4- and 5-year-olds learned from the cross-domain evidence and were able to transfer their new expectations about psychosomatic causality to a novel task. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Activation of action rules in action observation.

Visually perceiving an action may activate corresponding motor programs. This automatic motor activation can occur both for higher level (i.e., the goal of an action) and for lower level (i.e., the specific effector with which it is executed) aspects of an action. The authors used a tool-use action paradigm to experimentally dissociate priming effects for observing the target, the movement, or the target-to-movement mapping of a tool-use action. In 3 experiments, participants took turns in acting, observing the tool-use action of another person in trial n-1, and executing an action in trial n. Trial transitions from n-1 to n were manipulated in 4 conditions with (a) mapping repeated and movement and target changed, (b) target repeated and movement and mapping changed, (c) movement repeated and target and mapping changed, or (d) all components repeated. Results indicate priming effects for repeating the target-to-movement mapping (i.e., the action rule) of a tool-use action and suggest that a rather abstract action schema is activated during action observation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An actor-critic algorithm for constrained Markov decision processes

An actor-critic type reinforcement learning algorithm is proposed and analyzed for constrained controlled Markov decision processes. The analysis uses multiscale stochastic approximation theory and the envelope theorem' of mathematical economics.     

THE IMPORTANCE OF NEUTRAL EXAMPLES FOR LEARNING SENTIMENT

Most research on learning to identify sentiment ignores "neutral" examples, learning only from examples of significant (positive or negative) polarity. We show that it is crucial to use neutral examples in learning polarity for a variety of reasons. Learning from negative and positive examples alone will not permit accurate classification of neutral examples. Moreover, the use of neutral training examples in learning facilitates better distinction between positive and negative examples.     

CAL delivery selection criteria and authoring systems

Abstract  In the past, authoring systems have been used to generate computer-assisted learning materials that have often followed the rather restrictive programmed learning format. A number of innovative ways of using recently developed systems to develop CAL packages that include a wider range of learning activities (access to data bases, simulations, interactive video, etc.) are described. Analogous to the concept of a media selection model, a computer delivery mode selection model is presented as an aid to decision making for designers. This increase in flexibility should broaden the applicability of computerassisted learning (CAL) to a wider range of educational objectives and raise the level of the cognitive emphasis in learning packages, as well as facilitate the implementation of visually appealing materials. The paper also implies a standard of acceptability for authoring systems.     

KNOWLEDGE-BASED FEATURE DISCOVERY FOR EVALUATION FUNCTIONS

Since Samuel's work on checkers over thirty years ago, much effort has been devoted to learning evaluation functions. However, all such methods are sensitive to the feature set chosen to represent the examples. If the features do not capture aspects of the examples significant for problem solving, the learned evaluation function may be inaccurate or inconsistent. Typically, good feature sets are carefully handcrafted and a great deal of time and effort goes into refining and tuning them. This paper presents an automatic knowledge-based method for generating features for evaluation functions. The feature set is developed iteratively: features are generated, then evaluated, and this information is used to develop new features in turn. Both the contribution of a feature and its computational expense are considered in determining whether and how to develop it further.
This method has been applied to two problem-solving domains: the Othello board game and the domain of telecommunications network management. Empirical results show that the method is able to generate many known features and several novel features and to improve concept accuracy in both domains.     

Deterministic learning of completely resonant nonlinear wave systems with Dirichlet boundary conditions

In this paper, we investigate the approximation of completely resonant nonlinear wave systems via deterministic learning. The plants are distributed parameter systems (DPS) describing homogeneous and isotropic elastic vibrating strings with fixed endpoints. The purpose of the paper is to approximate the infinite-dimensional dynamics, rather than the parameters of the wave systems. To solve the problem, the wave systems are first transformed into finite-dimensional dynamical systems described by ordinary differential equation (ODE). The properties of the finite-dimensional systems, including the convergence of the solution, as well as the dominance of partial system dynamics according to point-wise measurements, are analyzed. Based on the properties, second, by using the deterministic learning algorithm, an approximately accurate neural network (NN) approximation of the the finite-dimensional system dynamics is achieved in a local region along the recurrent trajectories. Simulation studies are included to demonstrate the effectiveness of the proposed approach.     

无线ILC系统测控信号延时效应补偿方法

针对通过无线信道进行测控信号传输的远程迭代学习控制( ILC)系统,研究信号传输延时对控制系统性能的影响.分析了测控信号延时情况下ILC系统的收敛性问题,通过引入预控制向量,提出了ILC系统信道延时效应补偿的向量更新方法.数值仿真结果表明了所提方法的有效性.     

Negative effects of sufficiently small initial weights on back-propagation neural networks

In the training of feedforward neural networks,it is usually suggested that the initial weights should be small in magnitude in order to prevent premature saturation.The aim of this paper is to point out the other side of the story:In some cases,the gradient of the error functions is zero not only for infinitely large weights but also for zero weights.Slow convergence in the beginning of the training procedure is often the result of sufficiently small initial weights.Therefore,we suggest that,in these cases,the initial values of the weights should be neither too large,nor too small.For instance,a typical range of choices of the initial weights might be something like(0.4,0.1) ∪(0.1,0.4),rather than(0.1,0.1) as suggested by the usual strategy.Our theory that medium size weights should be used has also been extended to a few commonly used transfer functions and error functions.Numerical experiments are carried out to support our theoretical findings.