For artificial entities to achieve high degrees of autonomy they will need to display appropriate adaptability. In this sense adaptability includes representational flexibility gu...
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
Abstract— Automatic pattern classifiers that allow for incremental learning can adapt internal class models efficiently in response to new information, without having to retrai...
Device mismatch in VLSI degrades the accuracy of analog arithmetic circuits and lowers the learning performance of large-scale neural networks implemented in this technology. We s...
Abstract. This paper introduces the notion of the variadic neural network (VNN). The inputs to a variadic network are an arbitrary-length list of n-tuples of real numbers, where n ...