• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.113-117
• /
• 1998

We propose a way to show the inherent learning complexity for the multilayer perceptron. We display the solution space and the error surfaces on the input space of a single neuron with two inputs. The evolution of its weights will follow one of the two error surfaces. We observe that when we use the back-propagation(BP) learning algorithm (1), the wight cam not jump to the lower error surface due to the implicit continuity constraint on the changes of weight. The self-relaxation approach is to explicity find out the best combination of all neurons' two error surfaces. The time complexity of training a multilayer perceptron by self-relaxationis exponential to the number of neurons.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.155-157
• /
• 2005

We propose a new category of hybrid multi-layer neural networks with hetero nodes such as Fuzzy Set based Polynomial Neurons (FSPNs) and Polynomial Neurons (PNs). These networks are based on a genetically optimized multi-layer perceptron. We develop a comprehensive design methodology involving mechanisms of genetic optimization and genetic algorithms, in particular. The augmented genetically optimized HFPNN (namely gHFPNN) results in a structurally optimized structure and comes with a higher level of flexibility in comparison to the one we encounter in the conventional HFPNN. The GA-based design procedure being applied at each layer of HFPNN leads to the selection of preferred nodes (FPNs or PNs) available within the HFPNN. In the sequel, two general optimization mechanisms are explored. First, the structural optimization is realized via GAs whereas the ensuing detailed parametric optimization is carried out in the setting of a standard least square method-based learning. The performance of the gHFPNNs quantified through experimentation where we use a number of modeling benchmarks-synthetic and experimental data already experimented with in fuzzy or neurofuzzy modeling.

• Animal cells and systems
• /
• 제9권3호
• /
• pp.145-152
• /
• 2005

A retrograde tracer, WGA-apo-HRP-gold, was injected into midline thalamic nuclei and subsequently orexin-A immunostaining was performed on the tuberal region of the hypothalamus in order to investigate orexinergic projections to the midline thalamus. Injection site was targeted within one specific region, i.e., paraventricular, centromedian, rhomboid, reuniens, or intermediodorsal nucleus, but it proved to be either one or a combination of these thalamic nuclei. The distribution of WG/orexin-double-labeled neurons exhibited a general pattern in that the majority of labeled cells were observed within the ventral portion of the lateral hypothalamus as well as the perifornical nucleus (PeF). A small number of double-labeled cells were also observed at the dorsomedial nucleus, the area dorsal to the PeF, dorsal portion of the lateral hypothalamus, and the posterior hypothalamus. These orexin-immunoreactive neurons might have wake-related influences over a variety of functions related with midline thalamic nuclei, which include autonomic control, associative cortical functions, and limbic regulation.

• 전자공학회논문지B
• /
• 제29B권4호
• /
• pp.58-65
• /
• 1992

In this paper new back propagation algorithm which adds neurons to hidden layer is proposed. this proposed algorithm is applied to the pattern recognition of written number coupled with back propagation algorithm through omitting redundant learning. Learning rate and recognition rate of the proposed algorithm are compared with those of the conventional back propagation algorithm and the back propagation through omitting redundant learning. The learning rate of proposed algorithm is 4 times as fast as the conventional back propagation algorithm and 2 times as fast as the back propagation through omitting redundant learning. The recognition rate is 96.2% in case of the conventional back propagation algorithm, 96.5% in case of the back propagation through omitting redundant learning and 97.4% in the proposed algorithm.

• 산업경영시스템학회지
• /
• 제23권61호
• /
• pp.127-135
• /
• 2000

This paper provides a new method of initializing neurons used in self-organizing neural networks and sequencing input nodes for applying to Euclidean traveling salesman problem. We use a general property that in any optimal solution for Euclidean traveling salesman problem, vertices located on the convex hull are visited in the order in which they appear on the convex hull boundary. We composite input nodes as number of convex hulls and initialize neurons as shape of the external convex hull. And then adapt input nodes as the convex hull unit and all convex hulls are adapted as same pattern, clockwise or counterclockwise. As a result of our experiments, we obtain l∼3 % improved solutions and these solutions can be used for initial solutions of any global search algorithms.

• 전자공학회논문지B
• /
• 제33B권2호
• /
• pp.159-167
• /
• 1996

In this paper, a new competitive learning algorithm called dynamic competitive learning (DCL) is presented. DCL is a supervised learning mehtod that dynamically generates output neuraons and nitializes weight vectors from training patterns. It introduces a new parameter called LOG (limit of garde) to decide whether or not an output neuron is created. In other words, if there exist some neurons in the province of LOG that classify the input vector correctly, then DCL adjusts the weight vector for the neuraon which has the minimum grade. Otherwise, it produces a new output neuron using the given input vector. It is largely learning is not limited only to the winner and the output neurons are dynamically generated int he trining process. In addition, the proposed algorithm has a small number of parameters. Which are easy to be determined and applied to the real problems. Experimental results for patterns recognition of remote sensing data and handwritten numeral data indicate the superiority of dCL in comparison to the conventional competitive learning methods.

• 제어로봇시스템학회논문지
• /
• 제12권5호
• /
• pp.473-479
• /
• 2006

A global path planning algorithm using modified self-organizing feature map(SOFM) which is a method among a number of neural network is presented. The SOFM uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors of the 2-dimensional mesh, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the opposite direction of input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.817-822
• /
• 2004

This paper provides a global path planning method using self-organizing feature map which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• BMB Reports
• /
• 제56권2호
• /
• pp.90-95
• /
• 2023

Mitochondria are important organelles that regulate adenosine triphosphate production, intracellular calcium buffering, cell survival, and apoptosis. They play therapeutic roles in injured cells via transcellular transfer through extracellular vesicles, gap junctions, and tunneling nanotubes. Astrocytes can secrete numerous factors known to promote neuronal survival, synaptic formation, and plasticity. Recent studies have demonstrated that astrocytes can transfer mitochondria to damaged neurons to enhance their viability and recovery. In this study, we observed that treatment with mitochondria isolated from rat primary astrocytes enhanced cell viability and ameliorated hydrogen peroxide-damaged neurons. Interestingly, isolated astrocytic mitochondria increased the number of cells under damaged neuronal conditions, but not under normal conditions, although the mitochondrial transfer efficiency did not differ between the two conditions. This effect was also observed after transplanting astrocytic mitochondria in a rat middle cerebral artery occlusion model. These findings suggest that mitochondria transfer therapy can be used to treat acute ischemic stroke and other diseases.

• 한국정밀공학회지
• /
• 제23권3호
• /
• pp.94-101
• /
• 2006

A global path planning method using self-organizing feature map which is a method among a number of neural network is presented. The self-organizing feature map uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are moved toward the input vector On the other hand, the modified method in this research uses a predetermined initial weight vectors of 1-dimensional string and 2-dimensional mesh, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are moved toward the input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.