A Pulse-Coupled Neural Network Simulator Using a Programmable Gate Array Technique
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we propose a novel pulse-coupled neural network (PCNN) simulator using a programmable gate array (PGA) technique. The simulator is composed of modified phase-locked loops (PLLs) and a programmable gate array (PGA). The PLL, which is modified by the addition of multiple inputs and multiple feedbacks, works as a neuron. The PGA, which controls the network connection, works as nodes of dendritic trees. This simulator, which has 16 neurons and 32 × 32 network connections, is designed on a chip (4.73 mm × 4.73 mm), and its basic operations such as synchronization, an oscillatory associative memory, and FM interactions are confirmed using circuit simulator SPICE.
- 2003-05-01
著者
-
Iwata Atsushi
Graduate School Of Advanced Sciences Of Matter Hiroshima University
-
Katayama Kousuke
Graduate School Of Engineering Hiroshima University
関連論文
- Image Segmentation/Extraction Using Nonlinear Cellular Networks and Their VLSI Implementation Using Pulse-Modulation Techniques(Special Section on Analog Circuit Techniques and Relate)
- A 1-D CMOS PWM Cellular Neural Network Circuit and Resistive-Fuse Network Operation
- A VLSI Spiking Feedback Neural Network with Negative Thresholding and Its Application to Associative Memory(Novel Device Architectures and System Integration Technologies)
- Pulse Modulation Techniques for Nonlinear Dynamical Systems and a CMOS Chaos Circuit with Arbitrary 1-D Maps(New System Paradigms for Integrated Electronics)
- An Hadamard Transform Chip Using the PWM Circuit Technique and Its Application to Image Processing(Special Issue on High-Performance Analog Integrated Circuits)
- Bio-Inspired VLSIs Based on Analog/Digital Merged Technologies
- New Non-Volatile Analog Memory Circuits Using PWM Methods (Special Issue on Integrated Electronics and New System Paradigms)
- Low-Voltage, Low-Phase-Noise Ring-VCO using 1/f-Noise Reduction Techniques
- A 0.6V Supply CMOS Amplifier Using Noise Reduction Technique of Autozeroing and Chopper Stabilization
- A 1V Low-Noise CMOS Amplifier Using Autozeroing and Chopper Stabilization Technique(Analog Circuit and Device Technologies)
- A Design of Neural Signal Sensing LSI with Multi-Input-Channels(Analog Circuit Techniques and Related Topics)
- A Neural Recording Amplifier with Low-Frequency Noise Suppression
- A 2.0Vpp Input, 0.5V Supply Delta Amplifier with A-to-D Conversion
- A Low Noise Amplifier Using Chopper Stabilization for a Neural Sensor LSI
- A stochastic computing chip for measurement of Manhattan distance
- Chip-Level Substrate Coupling Analysis with Reference Structures for Verification(Physical Design,VLSI Design and CAD Algorithms)
- Evaluation of Isolation Structures against High-Frequency Substrate Coupling in Analog/Mixed-Signal Integrated Circuits(Analog Circuit Techniques and Related Topics)
- A 2.7 Gcps and 7-Multiplexing CDMA Serial Communication Chip Using Two-Step Synchronization Technique(Optical, PLL, Analog Circuit and Device Technologies)
- A Pulse-Coupled Neural Network Simulator Using a Programmable Gate Array Technique
- Low-Voltage and Low-Noise CMOS Analog Circuits Using Scaled Devices(Analog Circuits and Related SoC Integration Technologies)
- A High-Resolution CMOS Image Sensor with Hadamard Transform Function
- A Pulse-Coupled Neural Network Simulator Using a Programmable Gate Array Technique
- PCA-based Object Detection/Recognition Chip for Wireless Interconnected 3-D Integration
- Low-Voltage, Low-Phase-Noise Ring Voltage-Controlled Oscillator Using $1/ f$-Noise Reduction Techniques
- Stochastic Computing Chip for Measurement of Manhattan Distance
- 0.6 V Supply Complementary Metal Oxide Semiconductor Amplifier Using Noise Reduction Technique of Autozeroing and Chopper Stabilization
- Evaluation of Digital Crosstalk Noise on Differential Input Voltage Controlled Oscillator