다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Most current Artificial Neural Network (ANN) models are based on highly simplified brain dynamics. They have been used as powerful computational tools to solve complex pattern recognition, function estimation, and classification problems. ANNs have been evolving towards more powerful and more biologically realistic models. In the past decade, Spiking Neural Networks (SNNs) have been developed which comprise of spiking neurons. Information transfer in these neurons mimics the information transfer in biological neurons, i.e., via the precise timing of spikes or a sequence of spikes. To facilitate learning in such networks, new learning algorithms based on varying degrees of biological plausibility have also been developed recently. Addition of the temporal dimension for information encoding in SNNs yields new insight into the dynamics of the human brain and could result in compact representations of large neural networks. As such, SNNs have great potential for solving complicated time-dependent pattern recognition problems because of their inherent dynamic representation. This article presents a state-of-the-art review of the development of spiking neurons and SNNs, and provides insight into their evolution as the third generation neural networks.

Spiking neural networks.

dix A. Even if you don’t choose to memorize them this system aids in reference and retreival of important formulas. The book was compiled from notes developed during eight years of teaching a graduate course on the subject and was used as a text. Thus it has been student tested. Appendix F contains a number of problems, grouped to be used on a chapter by chapter basis The problems are designed to illustrate practical applications of the text material. The parts of this book of most interest and value to the EMC engineer will be the chapters on Thermal Noise, Antennas, Propagation and Transmission Lines, and  Reflection and Refraction. This is not  to downpade the chapters on Statistics and Its Applications, Signal Processing and Detection, and Some System Characteristics which also contain much potentially useful materials. Additional plus values for the book include a list of 40 references, a table of symbols used throughout the book, and a subject index. Some readers may find the condensed type and close line spacing hard to read. It was apparently set up by typewriter using an elite type face with single line spacing. When reduced down to a 6 by 9 5 inch size page it is too crowded for easy reading. In spite of this shortcoming your reviewer recommends this book as a worthwhile reference in this field of interest.

http://ieeexplore.ieee.org/iel5/5/31269/01455368.pdf

Signal analysis

Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier

Since the last decade, several complex-valued neural networks have been developed and applied in various research areas. As an extension of real-valued recurrent neural networks, complex-valued recurrent neural networks use complex-valued states, connection weights, or activation functions with much more complicated properties than real-valued ones. This paper presents several sufficient conditions derived to ascertain the existence of unique equilibrium, global asymptotic stability, and global exponential stability of delayed complex-valued recurrent neural networks with two classes of complex-valued activation functions. Simulation results of three numerical examples are also delineated to substantiate the effectiveness of the theoretical results.

Global Stability of Complex-Valued Recurrent Neural Networks With Time-Delays

In recent years, several neural networks using Clifford algebra have been studied. Clifford algebra is also called geometric algebra. Complex-valued Hopfield neural networks (CHNNs) are the most popular neural networks using Clifford algebra. The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs. Hyperbolic algebra is a Clifford algebra based on Lorentzian geometry. In this brief, a hyperbolic neuron is defined in a manner analogous to a phasor neuron, which is a typical complex-valued neuron model. HHNNs share common concepts with CHNNs, such as the angle and energy. However, HHNNs and CHNNs are different in several aspects. The states of hyperbolic neurons do not form a circle, and, therefore, the start and end states are not identical. In the quantized version, unlike complex-valued neurons, hyperbolic neurons have an infinite number of states.

Hyperbolic Hopfield Neural Networks

We have studied the electronic structure of Zn$_{0.9}$Fe$_{0.1}$O nano-particles, which have been reported to show ferromagnetism at room temperature, by x-ray photoemission spectroscopy (XPS), resonant photoemission spectroscopy (RPES), x-ray absorption spectroscopy (XAS) and x-ray magnetic circular dichroism (XMCD). From the experimental and cluster-model calculation results, we find that Fe atoms are predominantly in the Fe$^{3+}$ ionic state with mixture of a small amount of Fe$^{2+}$ and that Fe$^{3+}$ ions are dominant in the surface region of the nano-particles. It is shown that the room temperature ferromagnetism in the Zn$_{0.9}$Fe$_{0.1}$O nano-particles is primarily originated from the antiferromagnetic coupling between unequal amounts of Fe$^{3+}$ ions occupying two sets of nonequivalent positions in the region of the XMCD probing depth of $\sim$ 2-3 nm.

Electronic structure and magnetism of the diluted magnetic semiconductor Fe-doped ZnO nano-particles

Quaternionic Hopfield neural networks with twin-multistate activation function

Twin-multistate commutative quaternion Hopfield neural networks

A rotor Hopfield neural network (RHNN) is an extension of a complex-valued Hopfield neural network (CHNN). RHNNs have some excellent properties. For example, the storage capacity of an RHNN is twice that of a CHNN. The most important property of an RHNN is that it does not store rotated patterns of training patterns, unlike CHNNs, which have less noise robustness because they store rotated patterns. However, conventional learning methods for RHNNs, such as Hebbian learning rule and gradient descent learning rules, present difficulties with regard to, for example, storage capacity, noise robustness, and learning time. In this paper, we propose a projection rule for RHNN and demonstrate that the noise robustness of RHNN is better than that of CHNN. The proposed algorithm improves the noise robustness of RHNN. As the number of training patterns increases, the noise robustness of CHNN rapidly deteriorates. On the other hand, the noise robustness of RHNN reduces less rapidly for the same case. Moreover, RHNN can easily recover from rotated patterns, unlike CHNN. We show this ability by computer simulation.

Masaki Kobayashi

Papers

Hyperbolic Hopfield Neural Networks

Electronic structure and magnetism of the diluted magnetic semiconductor Fe-doped ZnO nano-particles

Quaternionic Hopfield neural networks with twin-multistate activation function

Twin-multistate commutative quaternion Hopfield neural networks

Projection Rule for Rotor Hopfield Neural Networks