Adaptive weighted outer-product learning associative memory

Associative-memory neural networks with adaptive weighted outer-product learning are proposed in this paper. For the correct recall of a fundamental memory (FM), a corresponding learning weight is attached and a parameter called signal-to-noise-ratio-gain (SNRG) is devised. The sufficient conditions for the learning weights and the SNRG's are derived. It is found both empirically and theoretically that the SNRG's have their own threshold values for correct recalls of the corresponding FM's. Based on the gradient-descent approach, several algorithms are constructed to adaptively find the optimal learning weights with reference to global- or local-error measure.     

Enhanced recognition memory following glycine transporter 1 deletion in forebrain neurons.

Selective deletion of glycine transporter 1 (GlyT1) in forebrain neurons enhances N-methyl-D-aspartate receptor (NMDAR)-dependent neurotransmission and facilitates associative learning. These effects are attributable to increases in extracellular glycine availability in forebrain neurons due to reduced glycine re-uptake. Using a forebrain- and neuron-specific GlyT1-knockout mouse line (CamKIIαCre; GlyT1tm1.2fl/fI), the authors investigated whether this molecular intervention can affect recognition memory. In a spontaneous object recognition memory test, enhanced preference for a novel object was demonstrated in mutant mice relative to littermate control subjects at a retention interval of 2 hr, but not at 2 min. Furthermore, mutants were responsive to a switch in the relative spatial positions of objects, whereas control subjects were not. These potential procognitive effects were demonstrated against a lack of difference in contextual novelty detection: Mutant and control subjects showed equivalent preference for a novel over a familiar context. Results therefore extend the possible range of potential promnesic effects of specific forebrain neuronal GlyT1 deletion from associative learning to recognition memory and further support the possibility that mnemonic functions can be enhanced by reducing GlyT1 function. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Linear response algorithms for approximate inference in graphical models

Belief propagation (BP) on cyclic graphs is an efficient algorithm for computing approximate marginal probability distributions over single nodes and neighboring nodes in the graph. However, it does not prescribe a way to compute joint distributions over pairs of distant nodes in the graph. In this article, we propose two new algorithms for approximating these pairwise probabilities, based on the linear response theorem. The first is a propagation algorithm that is shown to converge if BP converges to a stable fixed point. The second algorithm is based on matrix inversion. Applying these ideas to gaussian random fields, we derive a propagation algorithm for computing the inverse of a matrix.     

Determination Of The Phase Current Waveform For A Disc‐Type Axial‐Flux Wheel Motor

An optimal design of the driving current pattern for a disc‐type axial‐flux brushless DC wheel motor of an electric vehicle is proposed in this paper. The electro‐magnetic dynamic model of the motor is established with magnetic circuits, describing the relationship between the output torque and excitation current. The optimal current pattern, in terms of magnitude and phase angle, is then obtained by maximizing the output torque with respect to the rotor shift. Compared with the traditional three‐phase‐on current pattern of fixed 120–degree phase shift, both the average torque and efficiency with the driving current of an optimal advanced switching angle are seen to be improved under various loading conditions. The motor performance with the optimal driving waveform is simulated and verified by experiments.     

Development of a web-based system for engineering change management

Engineering changes (ECs) are changes and/or modifications in forms, fits, functions, materials, dimensions, etc., of products and constituent components. ECs usually induce a series of downstream changes. Multiple disciplines and responsibilities are therefore involved in managing ECs. Previous investigations conducted by the authors and other researchers have shown that paper-based and standalone computerised EC management (ECM) systems have limited support for such intensive teamwork and close communication. This paper proposes to establish a web-based framework that supports ECM procedures and activities. A web-based ECM system is able to provide better information sharing, simultaneous data access and processing and more prompt communication and feedback. The amount of paperwork and the throughput time of managing ECs are significantly reduced while the effectiveness and the efficiency are substantially improved. This paper focuses on discussing the issues of design, development, and implementation of this prototype web-based ECM system.     

An Upper Bound on the Loss from Approximate Optimal-Value Functions

Many reinforcement learning approaches can be formulated using the theory of Markov decision processes and the associated method of dynamic programming (DP). The value of this theoretical understanding, however, is tempered by many practical concerns. One important question is whether DP-based approaches that use function approximation rather than lookup tables can avoid catastrophic effects on performance. This note presents a result of Bertsekas (1987) which guarantees that small errors in the approximation of a task's optimal value function cannot produce arbitrarily bad performance when actions are selected by a greedy policy. We derive an upper bound on performance loss that is slightly tighter than that in Bertsekas (1987), and we show the extension of the bound to Q-learning (Watkins, 1989). These results provide a partial theoretical rationale for the approximation of value functions, an issue of great practical importance in reinforcement learning.     

基于视觉系统的聚类算法

人类对于结构的感知方式和产生数据的物理系统原理对于聚类分析而言具有同等的重要性。因此,在聚类算法的设计和分析中,模拟人类的主要器官－视觉系统将帮助我们解决这一领域的一些基本问题。从这一观点出发,文中提出一类基于初级视觉系统尺度空间理论的聚类算法,并通过引入显著性假设,将生物物理学中的Weber定律与聚类结构的有效性联系起来。由此产生的聚类算法简洁有效,并可部分地回答那些与人类感知数据结构相关联的聚类有效性问题。我们的数值试验表明这一方法具有广泛的应用前景。     

Efficient Low Dissipative High Order Schemes for Multiscale MHD Flows, II: Minimization of ∇·B Numerical Error

An adaptive numerical dissipation control in a class of high order filter methods for compressible MHD equations is systematically discussed. The filter schemes consist of a divergence-free preserving high order spatial base scheme with a filter approach which can be divergence-free preserving depending on the type of filter operator being used, the method of applying the filter step, and the type of flow problem to be considered. Some of these filter variants provide a natural and efficient way for the minimization of the divergence of the magnetic field (∇·B) numerical error in the sense that commonly used divergence cleaning is not required. Numerical experiments presented emphasize the performance of the ∇·B numerical error. Many levels of grid refinement and detailed comparison of the filter methods with several commonly used compressible MHD shock-capturing schemes will be illustratedA condensed version appears in the Proceedings of the International Conference on High Performance Scientific Computing, March 10-14, 2003, Hanoi, Vietnam. This is a revised version of a longer internal report, Feb. 19, 2004. The longer internal report was published as a RIACS Technical Report TR03.10, July 2003, NASA Ames Research Center     

针对环状流形数据的非线性降维

近年来出现了多种新型的非线性降维方法,且在一些应用中体现出良好的效果.然而,当面对球体、柱体等环状流形产生的非线性流形数据时,这些方法往往会失效.针对这一问题,提出了针对环状流形数据的环结构检测算法与非线性降维方法.理论上,基于目前极受关注的Isomap降维方法的运行原理,给出了一个判断环状流形的充要条件;算法上利用所得的判断定理,制订了基于数据的环状流形检测算法:最后基于所找到的环结构,利用极坐标展开的思想设计了针对环状流形数据的非线性降维策略.针对一系列典型环状流形数据集的仿真实验结果表明,与其他流形学习降维方法相比,该方法对环状流形数据进行降维具有显著优势.