Toward Unified Hybrid Simulation Techniques for Spiking Neural Networks
Autor: | Benjamin Schrauwen, Michiel D'Haene, Michiel Hermans |
---|---|
Rok vydání: | 2014 |
Předmět: |
Time Factors
Computer science Cognitive Neuroscience Models Neurological Action Potentials Machine learning computer.software_genre Synaptic Transmission Neural Network Simulation Field (computer science) Arts and Humanities (miscellaneous) Animals Humans Computer Simulation Neurons Alternative methods Spiking neural network Ideal (set theory) business.industry Hybrid approach Key (cryptography) Artificial intelligence Nerve Net business computer Software |
Zdroj: | Neural Computation. 26:1055-1079 |
ISSN: | 1530-888X 0899-7667 |
Popis: | In the field of neural network simulation techniques, the common conception is that spiking neural network simulators can be divided in two categories: time-step-based and event-driven methods. In this letter, we look at state-of-the art simulation techniques in both categories and show that a clear distinction between both methods is increasingly difficult to define. In an attempt to improve the weak points of each simulation method, ideas of the alternative method are, sometimes unknowingly, incorporated in the simulation engine. Clearly the ideal simulation method is a mix of both methods. We formulate the key properties of such an efficient and generally applicable hybrid approach. |
Databáze: | OpenAIRE |
Externí odkaz: |