Physical neural network design incorporating nanotechnology
AssigneeKnowm Tech, LLC
InventorAlex Nugent
Life of this patent
Estimating the term…
Abstract
A physical neural network based on nanotechnology, including methods thereof. Such a physical neural network generally includes one or more neuron-like nodes, which are formed from a plurality of interconnected nanoconnections formed from nanoconductors. Each neuron-like node sums one or more input signals and generates one or more output signals based on a threshold associated with the input signal. The physical neural network also includes a connection network formed from the interconnected nanoconnections, such that the interconnected nanoconnections used thereof by one or more of the neuron-like nodes are strengthened or weakened according to an application of an electric field.
Claims52
A physical neural network based on nanotechnology, said physical neural network comprising:
- at least one neuron-like node that sums at least one input signal and generates at least one output signal based on a threshold associated with said at least one input signal;
- and
- at least one connection network associated with said at least one neuron-like node wherein said at least one connection network comprises a plurality of interconnected nanoconnections, such that each nanoconnection of said plurality of interconnected nanoconnections is strengthened or weakened according to an application of an electric field.
A physical neural network apparatus based on nanotechnology, said physical neural apparatus comprising:
- at least one connection network associated with at least one neuron-like node wherein said at least one connection network comprises a plurality of interconnected nanoconductors, such that each nanoconductor of said plurality of interconnected nanoconductors is strengthened or weakened according to an application of an electric field;
- wherein each nanoconductor of said plurality of interconnected nanoconductors experiences an increase in alignment in accordance with an increase in said electric field;
- wherein nanoconductors of said plurality of interconnected nanoconductors that are utilized most frequently by said at least one neuron-like node became stronger with each use thereof;
- and
- wherein nanoconductors of said plurality of interconnected nanoconductors that are utilized least frequently become increasingly weak and eventually become unaligned.
A method for assembling a physical neural network based on nanotechnology, said method comprising the steps of:
- forming at least one neuron-like node that sums at least one input signal and generates at least one output signal based on a threshold associated with said at least one input signal;
- and
- configuring at least one connection network associated with said at least one neuron-like node wherein said at least one connection network comprises a plurality of interconnected nanoconnections, such that each nanoconnection of said plurality of interconnected nanoconnections is strengthened or weakened according to an application of an electric field.
A method for assembling a physical neural network apparatus based on nanotechnology, said method comprising the steps of:
- forming at least one connection network associated with at least one neuron-like node wherein said at least one connection network comprises a plurality of interconnected nanoconductors, such that each nanoconductor of said plurality of interconnected nanoconductors is strengthened or weakened according to an application of an electric field;
- wherein each nanoconductor of said plurality of interconnected nanoconductors experiences an increase in alignment in accordance with an increase in said electric field;
- wherein nanoconductors of said plurality of interconnected nanoconductors that are utilized most frequently by said at least one neuron-like node become stronger with each use thereof;
- and
- wherein nanoconductors of said plurality of interconnected nanoconductors that are utilized least frequently become increasingly weak and eventually become unaligned.
Dependencies are inferred from the claim text.