• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.5
• /
• pp.277-282
• /
• 2003

In this paper we propose Using Higher Order Neuron on the Supervised Learning Machine of the Kohonen Feature Map. The architecture of proposed model adopts the higher order neuron in the input layer of Kohonen Feature Map as a Supervised Learning Machine. It is able to estimate boundary on input pattern space because or the higher order neuron. However, it suffers from a problem that the number of neuron weight increases because of the higher order neuron in the input layer. In this time, we solved this problem by placing the second order neuron among the higher order neuron. The feature of the higher order neuron can be mapped similar inputs on the Kohonen Feature Map. It also is the network with topological mapping. We have simulated the proposed model in respect of the recognition rate by XOR problem, discrimination of 20 alphabet patterns, Mirror Symmetry problem, and numerical letters Pattern Problem.

• Annals of Clinical Neurophysiology
• /
• v.2 no.2
• /
• pp.107-113
• /
• 2000

Background & Objectives : Motor evoked potentials(MEPs) to magnetic trans cranial stimulation were performed to evaluate upper motor neuron involvement and relationship to lower motor neuron involvement in motor neuron disease patients. Method : MEPs were obtained in the 17 consecutive patients with motor neuron disease. These patients were divided into three group based on clinical evidence of upper and lower motor neuron involvement, bulbar symptom; amyotrophic lateral sclerosis(ALS), progressive muscular atrophy(PMA), progressive bulbar palsy(PBP). MEPs were recorded from abductor pollicis brevis and abductor hallucis muscles. Abnormal MEPs were defined by delayed central motor conduction time or absent MEP. Results : MEPs were abnormal in 64%(11/17) of patients; 100%(7/7) in ALS, 64%(4/7) in PMA, 0%(0/3) in PBP respectively. In 68 total recording muscles, 34 muscles had evidence of motor weakness and showed abnormal responses in 59%(20/34). Whereas 34 muscles with normal strength, only 3%(1/34) of muscles showed abnormal response. Conclusion : MEPs are well correlated with upper motor neuron signs in ALS and may detect masking upper motor neuron signs in PMA. The muscles with lower motor neuron sign(weakness) usually relate with abnormal MEPs reponses.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.14 no.4
• /
• pp.383-390
• /
• 2014

This paper presents an excitatory CMOS neuron oscillator circuit design, which can synchronize two neuron-bursting patterns. The excitatory CMOS neuron oscillator is composed of CMOS neurons and CMOS excitatory synapses. And the neurons and synapses are connected into a close loop. The CMOS neuron is based on the Hindmarsh-Rose (HR) neuron model and excitatory synapse is based on the chemical synapse model. In order to fabricate using a 0.18 um CMOS standard process technology with 1.8V compatible transistors, both time and amplitude scaling of HR neuron model is adopted. This full-chip integration minimizes the power consumption and circuit size, which is ideal for motion control unit of the proposed bio-mimetic micro-robot. The experimental results demonstrate that the proposed excitatory CMOS neuron oscillator performs the expected waveforms with scaled time and amplitude. The active silicon area of the fabricated chip is $1.1mm^2$ including I/O pads.

• Journal of IKEEE
• /
• v.3 no.2 s.5
• /
• pp.161-167
• /
• 1999

3-input neuron-MOSFET inverters and 3-bit D/A converters using enhancement type device have been designed and fabricated by using standard 2-poly CMOS process. The voltage transfer curve and the noise margin of neuron-MOSFET inverters have been measured and characterized as the same method in normal CMOS inverters. From the theoretical calculation of the effects of coupling ratio on the voltage transfer curve and noise margin, we set up the design guideline for the gate oxide thickness and input gate layout in neuron-MOSFET inverters. BT using one of input gates as a control gate, we can design and fabricate the neuron-MOSFET D/A converter without offset voltage.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.15 no.3
• /
• pp.365-373
• /
• 2015

We propose a simple and compact thyristor-based neuron circuit. The thyristor exhibits bi-stable characteristics that can mimic the action potential of the biological neuron, when it is switched between its OFF-state and ON-state with the help of assist circuit. In addition, a method of inter-neuron connection with synaptic devices is proposed, using double current mirror circuit. The circuit utilizes both short-term and long-term plasticity of the synaptic devices by flowing current through them and transferring it to the post-synaptic neuron. The double current mirror circuit is capable of shielding the pre-synaptic neuron from the post synaptic-neuron while transferring the signal through it, maintaining the synaptic conductance unaffected by the change in the input voltage of the post-synaptic neuron.

• Proceedings of the IEEK Conference
• /
• 2000.11c
• /
• pp.5-8
• /
• 2000

Voltage mode chaotic neuron has been designed in integrated circuit and fabricated by using 0.8$\mu\textrm{m}$ single poly CMOS technology. The fabricated CMOS chaotic neuron consist of chaotic signal generator and sigmoid output function. This paper presents an analysis of the chaotic behavior in the voltage mode CMOS chaotic neuron. From empirical equations of the chaotic neuron, the dynamical responses such as time series, bifurcation, and average firing rate are calculated. And, results of experiments in the single chaotic neuron and chaotic neural networks by two neurons are shown and compared with the simulated results.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.149.6-149
• /
• 2001

We propose a neuron model that has the interactions between excitation and inhibition. By adopting the knowledge of the physiology, the neuron model by imitating structure of a neuron, has the system resemble a neuron. We considered a neuron system based on the arguments, and wished to examine whether the system had reasonable function Koch, Poggio and Torre believed that inhibition signal would shunt excitation signal on the dendrites. They believed that excitation signal operated input signals and inhibition did as delayed ones. Thus, they were sure that function for directional selectivity was arisen by the shunting. We construct the neuron system with Koch's concept. Our neuron model has 3-layer structure and ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.516-516
• /
• 2000

We propose a neuron model that is possible to learn three-dimensional movement. The neuron model by imitating structure of a neuron, has the system resemble a neuron. We considered a neuron system based on the arguments, and wished to examine whether the system had reasonable function. Koch, Poggio and Torre believed that inhibition signal would shunt excitation signal on the dendrites. They believed that excitation signal operated input-signals and inhibition did as delayed ones. Thus, they were sure that function for directional selectivity was arisen by the shunting. Koch's concept is so important; therefore, we construct the neuron system with their concept. The neuron system makes the shunting function; thus, the model may have a function for directional selectivity. We initialized the connections and the dendrites by random data, and trained them by the back-propagation algorithm for three-dimensional movement. We made sure the defection of three-dimensional movement in the system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.496-496
• /
• 2000

We propose a neuron computer for tracking motion of particles in multi-dimensional space. The neuron computer is constructed of neural networks and their connections, which is a simplified model of the brain. The neuron computer is assemblage of neural networks, it includes a control unit, and the actions of the unit are represented by instructions. We designed a neuron computer to recognize and predict motion of particles. The recognition unit is constructed of neuron-array, encoder, and control part. The neuron-array is a model of the retina, and particles crease an image on the array, where the image is binary. The encoder picks one particle from the array, and translates the particle's location to Cartesian coordinates, which is scaled in [0, 1] intervals. Next, the encoder picks another particle, and does same process. The ordering and reduction of complex processes are executed by instructions. The instructions are held in the control part. The prediction unit is constructed of a multi-layer neural network and a feedback loop, where real time learning is executed. The particles' future locations are forecasted by coordinate values. The neuron computer can chase maximum 100 particles that take evasions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.427-430
• /
• 2007

기존의 LVQ(Learning Vector Quantization) 방법을 이용하여 물체를 분류하면 데이터의 학습이 빠르고 연산량이 적어 실시간으로 물체를 분류할 수 있는 장점이 있다. 하지만 데이터의 훈련시 output neuron의 개수를 정확히 예측할 수 없고 output neuron의 개수에 따라 물체를 분류하는 정확도가 매우 달라질 수 있다. 그러므로 본 논문에서는 output neuron의 개수를 데이터의 특성에 맞게 결정해주는 알고리즘을 제시한다. DLVQ(Dynamic Learning Vector Quantization) 알고리즘은 승자로 결정된 가중치 벡터의 부류가 샘플 데이터의 부류와 같으면 업데이트하고 다르면 새로운 가중치 벡터로 생성한다. 제한한 알고리즘의 가장 다른 부분은 미리 output neuron의 개수를 정하는 것이 아니라 훈련 과정에서 동적으로 output neuron의 개수를 생성하는 것이다. 그리고 클러터의 구분 방법을 제시하여 사람, 차, 클러터를 구분할 수 있다.