Difficult real-time AI problems require a means for expressing multi-dimensional and dynamic goal criteria and a principled model for satisficing to best meet the criteria. In the...
Least-squares estimation has always been the main approach when applying prediction error methods (PEM) in the identification of linear dynamical systems. Regardless of the estim...
In contrast to the conventional send/receive model, the one-way communication model--using Put and Synch--allows the decoupling of message transmission from synchronization. This ...
Mahmut T. Kandemir, U. Nagaraj Shenoy, Prithviraj ...
Abstract. While traditional approaches to machine learning are sensitive to highdimensional state and action spaces, this paper demonstrates how an indirectly encoded neurocontroll...
The dynamics of the learning equation, which describes the evolution of the synaptic weights, is derived in the situation where the network contains recurrent connections. The deri...
Anthony N. Burkitt, Matthieu Gilson, J. Leo van He...