Loading patent…
AssigneeUniversity of Tennessee Research Foundation
InventorsJ. Douglas Birdwell, Mark E. Dean, Catherine Schuman
Estimating the term…
A circuit element of a multi-dimensional dynamic adaptive neural network array (DANNA) may comprise a neuron/synapse select input functional to select the circuit element to function as one of a neuron and a synapse. In one embodiment of a DANNA array of such circuit elements, (wherein a circuit element or component thereof may be analog or digital), a destination neuron may be connected to a first neuron by a first synapse in one dimension, a second destination neuron may be connected to the first neuron by a second synapse in a second dimension and, optionally, a third destination neuron may be connected to the first neuron by a third synapse. The DANNA may thus form multiple levels of neuron and synapse circuit elements. In one embodiment, multiples of eight inputs may be selectively received by the circuit element selectively functioning as one of a neuron and a synapse. The dynamic adaptive neural network array (DANNA) may comprise a special purpose processor for performing one of a control, anomaly detection and classification application and may comprise a first structure connected to a neuroscience-inspired dynamic artificial neural network (NIDA), comprise substructures thereof or be combined with other neural networks.
Apparatus for a neuromorphic network comprising an artificial neural network, the artificial neural network comprising a multi-dimensional array of interconnected circuit elements, each circuit element having similar components to one another selectively representing, under special purpose program control, one of a neuron and a synapse, at least one circuit element of the array selectively representing an input neuron, at least one circuit element of the array selectively representing an output synapse and under program control one to multiple circuit elements of the array selectively representing a neuron or a synapse connected between the input neuron and the output synapse.
A circuit element for use in a multi-dimensional artificial neural network array, the circuit element comprising a neuron/synapse select input for selecting one of a neuron and synapse function of the circuit element, an accumulator, a comparator, a refractory period input and a threshold input, the accumulator accumulating charge from a plurality of selectable inputs for comparison at the comparator with the threshold, and, if a refractory period has lapsed and the accumulated charge is greater than the threshold, the comparator causing a fire output of the circuit element of the neural network array when the circuit element selectively performs a neuron function.
A method for constructing a neuromorphic network comprising at least one artificial neural network, the artificial neural network comprising a multi-dimensional array of interconnected circuit elements, each circuit element having similar components to one another selectively representing, under special purpose program control, one at a neuron and a synapse, at least one circuit element of the array selectively representing an input neuron, at least one circuit element of the array selectively representing an output synapse and under program control one to multiple circuit elements of the array selectively representing a neuron or a synapse connected between the input neuron and the output synapse.
A method for use in a circuit element of an artificial neural network, the circuit element having a neuron/synapse select input for selecting one of a neuron and synapse function of the Circuit element, an accumulator, a comparator, a refractory period input and a threshold input, the accumulator accumulating charge from a plurality of selectable inputs for comparison at the comparator with the threshold, and, if a refractory period has lapsed and the accumulated charge is greater than the threshold, the comparator causing a fire output of the circuit element when the circuit element selectively performs a neuron function.
Dependencies are inferred from the claim text.