Distributed Neural Networks Microcontroller Implementation and Applications
Ioan Șușnea · Studies in Informatics and Control · 2012
In this paper it is argued that, for any three-layer perceptron, it is always possible to design an equivalent distributed ANN, wherein the neurons are implemented on the nodes of a communication network, and the synapses between them are established in the communication process.In this approach, neurons are seen as processing and communication entities.Since both local and distributed implementations of a specific ANN are perfectly equivalent, they can use the same set of synapse weights, i.e. a distributed ANN can be trained on a local, equivalent software implementation.Two use cases are presented to demonstrate the validity of the idea.