Transform for a neurosynaptic core circuit
AssigneeInternational Business Machines Corporation
InventorsRathinakumar Appuswamy, Myron D. Flickner, Dharmendra S. Modha
Life of this patent
Estimating the term…
Abstract
Embodiments of the present invention provide a method for feature extraction comprising generating synaptic connectivity information for a neurosynaptic core circuit. The core circuit comprises one or more electronic neurons, one or more electronic axons, and an interconnect fabric including a plurality of synapse devices for interconnecting the neurons with the axons. The method further comprises initializing the interconnect fabric based on the synaptic connectivity information generated, and extracting a set of features from input received via the electronic axons. The set of features extracted comprises a set of features with reduced correlation.
Claims20
A method comprising:
- receiving, at a core circuit, multi-dimensional data, wherein the core circuit comprises a plurality of synapses interconnecting a plurality of axons to a plurality of neurons;
- and
- processing, learning, and associating the multi-dimensional data by extracting, via the core circuit, a set of features with reduced correlation from the multi-dimensional data.
A system comprising a computer processor, a computer-readable hardware storage medium, and program code embodied with the computer-readable hardware storage medium for execution by the computer processor to implement a method comprising:
- receiving, at a core circuit, multi-dimensional data, wherein the core circuit comprises a plurality of synapses interconnecting a plurality of axons to a plurality of neurons;
- and
- processing, learning, and associating the multi-dimensional data by extracting, via the core circuit, a set of features with reduced correlation from the multi-dimensional data.
A computer program product comprising a computer-readable hardware storage medium having program code embodied therewith, the program code being executable by a computer to implement a method comprising:
- receiving, at a core circuit, multi-dimensional data, wherein the core circuit comprises a plurality of synapses interconnecting a plurality of axons to a plurality of neurons;
- and
- processing, learning, and associating the multi-dimensional data by extracting, via the core circuit, a set of features with reduced correlation from the multi-dimensional data.
Dependencies are inferred from the claim text.