Hyperparameter on-line learning of stochastic resonance based threshold networks

Aiming at training the feed-forward threshold neural network consisting of nondifferentiable activation functions, the approach of noise injection forms a stochastic resonance based threshold network that can be optimized by various gradient-based optimizers. The introduction of injected noise extends the noise level into the parameter space of the designed threshold network, but leads to a highly non-convex optimization landscape of the loss function. Thus, the hyperparameter on-line learning procedure with respective to network weights and noise levels becomes of challenge. It is shown that the Adam optimizer, as an adaptive variant of stochastic gradient descent, manifests its superior learning ability in training the stochastic resonance based threshold network effectively. Experimental results demonstrate the significant improvement of performance of the designed threshold network trained by the Adam optimizer for function approximation and image classification.     

Additive Hermitian idempotent preservers between operator algebras

Let L be an additive map between (real or complex) matrix algebras sending $n\times n$ Hermitian idempotent matrices to $m\times m$ Hermitian idempotent matrices. We show that there are nonnegative integers $p,q$ with $n(p+q)=r\le m$ and an $m\times m$ unitary matrix U such that$L(A)=U[(I_p?A)\oplus (I_q?A^t)\oplus 0_{m?r}]U^{?},\text{for any}n\times n\text{Hermitian}A\text{with rational trace}.$ We also extend this result to the (complex) von Neumann algebra setting, and provide a supplement to the Dye-Bunce-Wright Theorem asserting that every additive map of Hermitian idempotents extends to a Jordan ?-homomorphism.     

Patterns and Symmetries in the Visual Cortex and in Natural Images

As borders between different entities, lines are an important element of natural images. Indeed, the neurons of the mammalian visual cortex are tuned to respond best to lines of a given orientation. This preferred orientation varies continuously across most of the cortex, but also has vortex-like singularities known as pinwheels. In attempting to describe such patterns of orientation preference, we are led to consider underlying rotation symmetries: Oriented segments in natural images tend to be collinear; neurons are more likely to be connected if their preferred orientations are aligned to their topographic separation. These are indications of a reduced symmetry requiring joint rotations of both orientation preference and the underlying topography. This is verified by direct statistical tests in both natural images and in cortical maps. Using the statistics of natural scenes we construct filters that are best suited to extracting information from such images, and find qualitative similarities to mammalian vision. PACS84.35+i 89.70.+c 87.57.Nk     

光码分多址系统中光学相关接收机判决阈值的分析

介绍了光码分多址系统中常用地址码（一维扩时码、二维码和三维码）的特点，并对它们各自的互相关均值和方差进行了理论分析。基于非相干光码分多址系统中光学相关接收机的基本原理，结合不同的用户地址码，对系统误码率性能进行了分析，得到了接收机最佳判决阈值与地址码基本特性参数和系统同时用户数间的关系。最后，给出了数值仿真结果。结果表明，对于采用特定地址码的光码分多址系统，只有选择合适的接收机判决阈值，系统的误码率性能才能达到最佳。研究结果对光码分多址系统中接收机判决阈值的选取具有一定的参考作用。     

Toward Fuzzy Optimization without Mathematical Ambiguity

Fuzzy programming has been discussed widely in literature and applied in such various disciplines as operations research, economic management, business administration, and engineering. The main purpose of this paper is to present a brief review on fuzzy programming models, and classify them into three broad classes: expected value model, chance-constrained programming and dependent-chance programming. In order to solve general fuzzy programming models, a hybrid intelligent algorithm is also documented. Finally, some related topics are discussed.     

模糊对向传播网络数据融合目标识别方法

重点研究了模糊对向传播网络 (FCPN)模型。针对数据融合和目标识别的特点 ,提出了基于模糊对向传播网络的融合目标识别方法和改进的模糊对向传播网络 (MFCPN)融合结构。利用仿真数据对网络的训练算法和融合结构进行了实验研究。结果表明 ,模糊对向传播网络较误差后向传播网络 (BPN)能够有效地实现融合识别 ;改进的模糊对向传播网络融合结构是可行的。同时还对FCPN和MFCPN应用于前视红外 (FLIR)和可见光摄像机目标跟踪系统进行了应用研究。     

强流脉冲高斯分布束在磁四极透镜中的非线性传输

用李代数方法分析了高斯分布下强流脉冲束在磁四极透镜中的非线性传输.在高斯分布下,束流的空间电荷势可利用Green函数算出,进而可以得到包含束流自场的粒子运动的Hamilton函数.再施加李变换,就可以得到粒子运动的各级近似解.本文给出二级近似下的结果,根据需要,还可以扩展到更高级近似.计算过程需要进行迭代,即根据每次算出的轨迹值,确定束团在三维实空间中的大小,然后再进行迭代,直到满足精度要求为止.     

Cyclic permutations and evolutionary trees

Given a tree with leaf set X, there are certain ways of arranging the elements of X in a circular order so that can be embedded in the plane and ‘preserve’ this ordering. We investigate some new combinatorial properties of these ‘circular orderings.’ We then use these properties to establish two results concerning dissimilarity maps on X that are induced by edge-weighted trees with leaf set X.     

Regular Balanced Cayley Maps for Cyclic, Dihedral and Generalized Quaternion Groups

A Cayley map is a Cayley graph embedded in an orientable surface such that. the local rotations at every vertex are identical. In this paper, balanced regular Cayley maps for cyclic groups, dihedral groups, and generalized quaternion groups are classified.