United States of America As Represented by the Secretary of the Air Force

University of Central Florida Research Foundation Inc

Dilia E Rodriguez

Joseph E Van Nostrand

Alvaro Velasquez

Sumit Kumar Jha

Systems and associated methods for constructing neural networks (NN) without the benefit of predefined output spike times or predefined network architecture. Functions are constructed from other functions determined from an input construction training set of output variable type. Method aspects of the neural network modeler may comprise partitioning the construction training set, representing the partitions, restricting the representations, constructing subfunctions from the restrictions, and combining the subfunctions to model the target function. Specifically, subfunctions represented from partition-specific neural networks of output value type are created using two fundamental composition operations: same-constant composition and different-constants composition. Different choices of weights and delays lead to different NNs with different output spikes that implement the same function.

System, apparatus and method for spiking neural network

Memristor-based nano-crossbar computing is a revolutionary computing paradigm that does away with the traditional Von Neumann architectural separation of memory and computation units. The computation of Boolean formulas using memristor circuits has been a subject of several recent investigations. Crossbar computing, in general, has also been a topic of active interest, but sneak paths have posed a hurdle in the design of pervasive general-purpose crossbar computing paradigms. Various embodiments are disclosed which demonstrate that sneak paths in nano-crossbar computing can be exploited to design a Boolean-formula evaluation strategy. Such nano-crossbar designs are also an effective approach for synthesizing high performance customized arithmetic and logic circuits.

Growing community of inventors

Fayetteville, NY, United States of America

Dilia E Rodriguez