A feedforward neural network based on multi-valued neurons is considered in the paper. It is shown that using a traditional feedforward architecture and a high functionality multi-...
Learning to solve small instances of a problem should help in solving large instances. Unfortunately, most neural network architectures do not exhibit this form of scalability. Our...
Frequently, sequences of state transitions are triggered by specific signals. Learning these triggered sequences with recurrent neural networks implies storing them as different at...
Despite a large body of literature and methods devoted to the Traffic Matrix (TM) estimation problem, the inference of traffic flows volume from aggregated data still represents a ...
Abstract. In the philosophy of behavior-based robotics, design of complex behavior needs the interaction of basic behaviors that are easily implemented. Action selection mechanism ...