Abstract: A device, system, and method is provided for training a new neural network to mimic a target neural network without access to the target neural network or its original training dataset. The target neural network and the new neural network may be probed with input data to generate corresponding target and new output data. Input data may be detected that generate a maximum or above threshold difference between the corresponding target and new output data. A divergent probe training dataset may be generated comprising the input data that generate the maximum or above threshold difference and the corresponding target output data. The new neural network may be trained using the divergent probe training dataset to generate the target output data. The new neural network may be iteratively trained using an updated divergent probe training dataset dynamically adjusted as the new neural network changes during training.

Abstract: The disclosure relates to structures of, and methods for forming electromagnetic band gap (EBG) element. Specifically, the disclosure is directed to methods for additively manufacturing electronic mushroom-type EBG elements having a periodic cell structure enabling a reduced footprint and increased band gap range for a very wide range of frequencies, for example between 500 MHz to about 30 GHz, by altering both the EBG structure's superstrate as well as the ground plane.

Abstract: A device, system, and method is provided to mimic a pre-trained target model without access to the pre-trained target model or its original training dataset. A set of random or semi-random input data may be sent to randomly probe the pre-trained target model at a remote device. A set of corresponding output data may be received from the remote device that is generated by applying the pre-trained target model to the set of random or semi-random input data. A random probe training dataset may be generated comprising the set of random or semi-random input data and corresponding output data generated by randomly probing the pre-trained target model. A new model may be trained with the random probe training dataset so that the new model generates substantially the same corresponding output data in response to said input data to mimic the pre-trained target model.

Abstract: An efficient technique of machine learning is provided for training a plurality of convolutional neural networks (CNNs) with increased speed and accuracy using a genetic evolutionary model. A plurality of artificial chromosomes may be stored representing weights of artificial neuron connections of the plurality of respective CNNs. A plurality of pairs of the chromosomes may be recombined to generate, for each pair, a new chromosome (with a different set of weights than in either chromosome of the pair) by selecting entire filters as inseparable groups of a plurality of weights from each of the pair of chromosomes (e.g., “filter-by-filter” recombination). A plurality of weights of each of the new or original plurality of chromosomes may be mutated by propagating recursive error corrections incrementally throughout the CNN. A small random sampling of weights may optionally be further mutated to zero, random values, or a sum of current and random values.

Abstract: An efficient technique of machine learning is provided for training a plurality of convolutional neural networks (CNNs) with increased speed and accuracy using a genetic evolutionary model. A plurality of artificial chromosomes may be stored representing weights of artificial neuron connections of the plurality of respective CNNs. A plurality of pairs of the chromosomes may be recombined to generate, for each pair, a new chromosome (with a different set of weights than in either chromosome of the pair) by selecting entire filters as inseparable groups of a plurality of weights from each of the pair of chromosomes (e.g., “filter-by-filter” recombination). A plurality of weights of each of the new or original plurality of chromosomes may be mutated by propagating recursive error corrections incrementally throughout the CNN. A small random sampling of weights may optionally be further mutated to zero, random values, or a sum of current and random values.

Abstract: The disclosure relates to methods for fabricating coreless printed circuit board (PCB) based transformers and/or coreless PCB-based circuits containing one or more coil inductor(s). More specifically, the disclosure relates to methods for fabricating coreless PCB-based transformers and/or inductors having concatenated helix architecture of their primary and secondary windings using layer-by-layer printing of dielectric and conductive patterns.

Abstract: A device, system, and method is provided for storing a sparse neural network. A plurality of weights of the sparse neural network may be obtained. Each weight may represent a unique connection between a pair of a plurality of artificial neurons in different layers of a plurality of neuron layers. A minority of pairs of neurons in adjacent neuron layers are connected in the sparse neural network. Each of the plurality of weights of the sparse neural network may be stored with an association to a unique index. The unique index may uniquely identify a pair of artificial neurons that have a connection represented by the weight. Only non-zero weights may be stored that represent connections between pairs of neurons (and zero weights may not be stored that represent no connections between pairs of neurons).

Abstract: The disclosure relates to systems, methods and compositions for fabricating additive manufactured electronics having conductive and dielectric constituents comprising voids, using additive manufacturing. Specifically, the disclosure is directed to the fabrication of three-dimensional component having conductive and dielectric constituents comprising voids by using water soluble support ink, capable of undergoing all processing steps for fabricating the dielectric and conductive constituents.

Abstract: A device, system, and method is provided for storing a sparse neural network. A plurality of weights of the sparse neural network may be obtained. Each weight may represent a unique connection between a pair of a plurality of artificial neurons in different layers of a plurality of neuron layers. A minority of pairs of neurons in adjacent neuron layers are connected in the sparse neural network. Each of the plurality of weights of the sparse neural network may be stored with an association to a unique index. The unique index may uniquely identify a pair of artificial neurons that have a connection represented by the weight. Only non-zero weights may be stored that represent connections between pairs of neurons (and zero weights may not be stored that represent no connections between pairs of neurons).

Abstract: The disclosure relates to systems, methods and compositions for fabricating composite component using additive manufacturing (AM). Specifically, the disclosure is directed to methods, systems and compositions for the fabrication of composite components having improved or modulated thermo-mechanical properties, as well as derivative dielectric strength, using for example, inkjet printing.

Abstract: The disclosure relates to systems and methods for using additive manufacturing techniques for fabricating ball grid array (BGA) surface mounting pads (SMP), and surface mounted technology devices (SMT) package sockets. More specifically, the disclosure relates to additive manufacturing methods for additively manufactured electronic (AME) circuits such as a printed circuit board (PCB), and/or flexible printed circuit (FPC), and/or high-density interconnect printed circuit board (HDIPCB) each having integrated raised and/or sunk BGA SMP, and or surface mounting sockets for SMT device(s) defined therein, and methods of coupling surface mounted devices such as BGA and/or SMT thereto.

Abstract: The disclosure relates to methods and compositions for direct printing of composite components. Specifically, the disclosure relates to the continuous printing of colored resin and metallic composite components using inkjet printing.

Abstract: The disclosure relates to a portable system for cleaning ink jet print heads. Specifically, the disclosure relates to external, portable systems and jig assemblies for cleaning clogged nozzles of ink jet print head under controlled pressure. The jig assembly can be self-contained and detachable, and can be programmed to operate upon receiving various signals indicating clogged nozzle plate or portion thereof, and/or as a routine maintenance operating procedure.

Abstract: The disclosure relates to systems and methods for photonic sintering of conductive ink compositions with metal nanoparticles. Specifically, the disclosure relates to methods and systems for sintering ink compositions with metal nanoparticles using an illumination source comprising an array of pulsed light emitting diodes (LEDs).

Abstract: The disclosure relates to methods, kits and compositions for direct printing of double-sided and/or multilayered printed circuit boards. Specifically, the disclosure relates to the printing of conductive leads and insulating portions of printed circuit boards using inkjet printing.

Abstract: The disclosure relates to systems, methods and compositions for direct printing of printed circuit boards with embedded integrated chips. Specifically, the disclosure relates to systems methods and compositions for the direct, top-down inkjet printing of printed circuit board with embedded chip and/or chip packages using a combination of print heads with conductive and dielectric ink compositions, creating predetermined dedicated compartments for locating the chips and/or chip packages and covering these with an encapsulating layer while maintaining interconnectedness among the embedded chips. Placing of the chips can be done automatically using robotic arms.

Abstract: The disclosure relates to systems, methods and compositions for inkjet printing of ceramic dielectric portions. Specifically, the disclosure relates to systems, methods and compositions for the inkjet printing of three dimensional patterns formed from pre-ceramic polymer derived interpenetrated networks that are comprised of at least two phases, or bi-continuous phases, one formed by free radical polymerization and the other by sol-gel polymerization.

Abstract: The disclosure relates to methods and compositions for direct printing of circuit boards having an electromagnetically-shielded tracks and/or components. Specifically, the disclosure relates to the direct, uninterrupted and continuous 3D printing of insulation-jacketed tracks and/or components with metallic shielding sleeves or capsule.

Abstract: The disclosure relates to methods and compositions for direct printing of rigid flexible electronic objects. Specifically, the disclosure relates to methods, systems and compositions for the direct, optionally simultaneous inkjet printing of rigid-flexible electronics, for example, rigid-flexible PCBs, FPCs, TFTs, antennae solar cells, RFIDs and the like, using a combination of print heads with flexible and rigid conductive and dielectric ink compositions.

Abstract: The disclosure relates to systems and methods for photonic sintering of conductive ink compositions with metal nanoparticles.