US Patent 8156057 - Adaptive neural network utilizing nanoconnections

http://www.freepatentsonline.com/8156057.html

This patent is the latest in a series of continuations from KnowmTech LLC and discloses ways in which nanoparticles can be used to create physical neural networks. Claim 1 reads:

1. A method for strengthening nanoconnections of a electromechanical neural network, said method comprising:

providing an electromechanical neural network comprising a plurality of neurons formed from a plurality of nanoconnections disposed within a dielectric solution in association with at least one pre-synaptic electrode and at least one post-synaptic electrode;

activating said subsequent neuron in response to firing an initial neuron of said plurality of neurons, thereby increasing a voltage of a pre-synaptic electrode of said neuron, which causes a refractory pulse thereof to decrease a voltage of a post-synaptic electrode associated with said neuron and thus provides an increased voltage between said pre-synaptic electrode of said preceding neurons and said post-synaptic electrode of said neuron.

US Patent 7827131 - High density synapse chip using nanoparticles

http://www.freepatentsonline.com/7827131.html

This is one of several patents form Alex Nugent of KnowmTech proposing ways to converge elements of  nanotechnology and A.I. to form a new type of computational neural network. Claim 1 reads:

1. A physical neural network synapse chip, wherein said synapse chip comprises:

an input layer comprising a plurality of input electrodes and an output layer comprising a plurality of output electrodes wherein a gap is formed between said input layer and said output layer such that a direction of said gap is mutually perpendicular to said plurality of input electrodes and said plurality of output electrodes; and

a solution comprising a plurality of nanoconductors and a dielectric solvent, wherein said solution is located within said gap, wherein an electric field is applied across said gap from said input layer to said output layer to form nanoconnections of a physical neural network implemented by said synapse chip.

US Patent 7502769 - Nanoparticle fractal memory

http://www.freepatentsonline.com/7502769.html

This patent from Knowmtech teaches an interesting architecture for a nanoparticle based memory using a fractal tree organization. Claim 1 reads:

1. A fractal memory system, comprising:

a fractal tree comprising at least one fractal trunk;

at least one recognition trigger electrode that routes signals in said fractal tree; and

at least one object circuit associated with said fractal tree, wherein said object circuit is configured from a plurality of nanotechnology-based components to provide a scalable distributed computing architecture.

US Patent 7420396 - Nanoparticle chain universal logic gate

http://www.freepatentsonline.com/7420396.html

Knowmtech is a company exploring the possibilities of nanoparticle based materials to form neural networks and computational systems. This latest patent teaches a new type of reconfigurable computing logic based on self-assembling nanoparticle chains. Claim 1 reads:

1. A universal logic gate apparatus, comprising:

a plurality of self-assembling chains of nanoparticles having a plurality of resistive connections, wherein said plurality of self-assembling chains of nanoparticles comprise resistive connects utilized to create a universal, reconfigurable logic gate thereof; and

a plasticity mechanism based on a plasticity rule for creating stable connections from said plurality of self-assembling chains of nanoparticles for use with said universal, reconfigurable logic gate, wherein said plasticity mechanism is based on an input data stream, wherein said plasticity rule comprises a reproducible modification of a connection resistance in response to input and output electrode activity.

US Patent 7412428 - Nanotechnology based neural network for applying Hebbian learning

http://www.freepatentsonline.com/7412428.html

This patent is one in a series of patents from Alex Nugent who has come up with a variety of techniques to use nanoparticle based interconnections to simulate physical neural networks. One of the limitations of current artificial intelligence approaches is the reliance on software solutions which have an intrinsic delay required for the transfer of information between memory and a processor. On the other hand physical neural networks have the potential to integrate memory with processing. This latest patent teaches a system for applying a Hebbian learning process to a physical neutral network formed from nanoparticles, nanowires, or nanotubes.

1. A system, comprising:

a physical neural network configured utilizing nanotechnology and integrated with feedback circuitry, wherein said physical neural network comprises a plurality of nanoconductors comprising at least one of nanotubes, nanowires, or nanoparticles, suspended and free to move about in a dielectric medium and which form neural connections between pre-synaptic and post-synaptic components of said physical neural network; and

a learning mechanism for applying Hebbian learning to said physical neural network.

US Patent 7409375 - Nanoparticle neural interconnections for independent component analysis

http://www.freepatentsonline.com/7409375.html

Independent component analysis is a methodology for extracting distinct signals from a mixed signals such as being able to ascertain a single voice in a crowded party. This patent from Knowmtech teaches a system for using nanoparticles in a neural network interconnection system to facilitate such analysis. Claim 1 reads:

1. A system for independent component analysis, comprising:

a feedback mechanism based on a plasticity rule; and

an electro-kinetic induced particle chain forming a neural network, wherein said feedback mechanism and said electro-kinetic induced particle chain is utilized to extract independent components from a data set.