Learning of Simple Dynamic Binary Neural Networks
スポンサーリンク
概要
- 論文の詳細を見る
This paper studies the simple dynamic binary neural network characterized by the signum activation function, ternary weighting parameters and integer threshold parameters. The network can be regarded as a digital version of the recurrent neural network and can output a variety of binary periodic orbits. The network dynamics can be simplified into a return map, from a set of lattice points, to itself. In order to store a desired periodic orbit, we present two learning algorithms based on the correlation learning and the genetic algorithm. The algorithms are applied to three examples: a periodic orbit corresponding to the switching signal of the dc-ac inverter and artificial periodic orbit. Using the return map, we have investigated the storage of the periodic orbits and stability of the stored periodic orbits.
著者
関連論文
- Artificial Spiking Neurons and Analog-to-Digital-to-Analog Conversion
- Analysis of Simple Single/Parallel Switched Dynamical Systems Based on Two Switching Strategies
- Synchronization and Hyperchaos in Switched Dynamical Systems Based on Parallel Buck Converters
- Chaotic Spike-Train with Line-Like Spectrum
- Special Section of Selected Papers from the 9th Karuizawa Workshop on Circuits and Systems
- A Simple Nonautonomous Chaotic Spiking Circuit with a Refractory Threshold(Nonlinear Problems)
- Growing Particle Swarm Optimizers for Multi-Objective Problems in Design of DC-AC Inverters
- An Approach to Collaboration of Growing Self-Organizing Maps and Adaptive Resonance Theory Maps(Neural Networks and Bioengineering)
- Consistency in a Chaotic Spiking Oscillator
- A Switched-Capacitor Boost Converter including Voltage-Mode Threshold Switching
- Basic Dynamics of Simple Delay-Coupled Bifurcating Neurons
- A Trade-Off between the Maximum Power Point and Stability
- Self-Organizing Digital Spike Maps for Learning of Spike-Trains
- A Simple Class of Binary Neural Networks and Logical Synthesis
- Learning of Simple Dynamic Binary Neural Networks
- Basic Dynamics of the Digital Logistic Map
- Basic Bifurcation of Artificial Spiking Neurons with Triangular Base Signal