On asynchronous dynamic neural field computation
Wahiba Taouali, Thierry Viéville, Rougier, Nicolas, P., Frédéric Alexandre · HAL (Le Centre pour la Communication Scientifique Directe) · 2010
The hallmark of most artificial neural networks is their supposed intrinsic parallelism where each unit is evaluated concurrently to other units in a distributed way. However, if one gives a closer look under the hood, one can soon realize that such a parallelism is an illusion since most implementations use what is referred to as synchronous evaluation. The present article propose to consider different evaluation methods (namely asynchronous evaluation methods) and to study their properties in some restricted but illustrative cases.