Abstract: A method of training a learning network is described. The method includes generating a first estimate of a gradient for the learning network and generating subsequent estimates of the gradient using a feedback network. The feedback network generates improved perturbations for the subsequent gradient estimates. Gradient estimates include the first estimate of the gradient and the subsequent estimates of the gradient. The method also includes using the gradient estimates to determine weights in the learning network. The improved perturbations may include lower variance perturbations.

Abstract: A system includes inputs, outputs, and nodes between the inputs and the outputs. The nodes include hidden nodes. Connections between the nodes are determined based on a gradient computable using symmetric solution submatrices.

Abstract: An air chuck includes a body and a valve core interface. The body includes output, interface, and input ports. The body defines a first passageway that extends between the output and interface ports. The input port defines a second passageway that is in fluid communication with the first passageway. The valve core interface is slidably coupled with the body and is slidable between extended and retracted positions. The valve core interface includes a shaft and a knob. The shaft includes proximal and distal ends. The distal end is at least partially disposed in the first passageway. The knob is coupled with the proximal end of the shaft. The shaft is rotatably coupled with the body and is selectively rotatable in either tightening or loosening directions via the knob. The distal end of the shaft comprises a grasping feature that is configured to grasp a valve core of a valve stem.

Abstract: A grommet assembly is configured to be installed within an opening and includes a grommet, a primary seal, and a lock ring. The grommet includes a platform, a panel portion extending from a first surface, and a ring portion extending from a second surface. The ring portion defines a passageway extending through the grommet and includes a plurality of grommet clamping features arranged around the ring portion. The primary seal extends around a periphery of the grommet. The lock ring includes a central hub having a plurality of ring clamping features arranged around the central hub. The displacement of the lock ring relative to the grommet engages each one of the plurality of ring clamping features with a corresponding one of the plurality of grommet clamping features to fasten the lock ring to the grommet to form a secondary seal between the grommet and the lock ring.

Abstract: A method for performing learning is described. A free inference is performed on a learning network for input signals. The input signals correspond to target output signals. The learning network includes inputs that receive the input signals, neurons, weights interconnecting the neurons, and outputs. The learning network is described by an energy for the free inference. The energy includes an interaction term corresponding to interactions consisting of neuron pair interactions. The free inference results in output signals. A first portion of the plurality of weights corresponding to data flow for the free inference. A biased inference is performed on the learning network by providing the input signals to the inputs and bias signals to the outputs. The bias signals are based on the target output signals and the output signals. The bias signals are fedback to the learning network through a second portion of the weights corresponding to a transpose of the first portion of the weights.

Abstract: A memristive device is described. The memristive device includes a first layer having a first plurality of conductive lines, a second layer having a second plurality of conductive lines, and memristive interlayer connectors. The first and second layers differ. The first and second pluralities of conductive lines are each lithographically defined. The first and second pluralities of conductive lines are insulated from each other. The memristive interlayer connectors are memristively coupled with a first portion of the first plurality of conductive lines and memristively coupled with a second portion of the second plurality of conductive lines. The memristive interlayer connectors are thus sparsely coupled with the first and second pluralities of conductive lines. Each memristive interlayer connector includes a conductive portion and a memristive portion.

Abstract: A method for performing learning is described. A free inference is performed on a learning network for input signals. The input signals correspond to target output signals. The learning network includes inputs that receive the input signals, neurons, weights interconnecting the neurons, and outputs. The learning network is described by an energy for the free inference. The energy includes an interaction term corresponding to interactions consisting of neuron pair interactions. The free inference results in output signals. A first portion of the plurality of weights corresponding to data flow for the free inference. A biased inference is performed on the learning network by providing the input signals to the inputs and bias signals to the outputs. The bias signals are based on the target output signals and the output signals. The bias signals are fedback to the learning network through a second portion of the weights corresponding to a transpose of the first portion of the weights.

Abstract: A method for performing learning in a dissipative learning network is described. The method includes determining a trajectory for the dissipative learning network and determining a perturbed trajectory for the dissipative learning network based on a plurality of target outputs. Gradients for a portion of the dissipative learning network are determined based on the trajectory and the perturbed trajectory. The portion of the dissipative learning network is adjusted based on the gradients.

Abstract: A caption encoder system is provided that can include a computer system and a caption encoder card. The caption encoder card can include a caption encoder module having at least one of: an input component, a field programmable gate array (FPGA), a microcontroller unit (MCU), a peripheral component interconnect express (PCIe) bridge, and a plurality of output components. The input component can be configured to receive an input SDI stream. The FPGA can be in communication with the input component and can be configured to compile an output SDI stream with embedded closed captions. The MCU can be in communication with the FPGA. The PCIe bridge can be in communication with the microcontroller unit and a plurality of universal serial bus to serial devices. The plurality of output components can be communication with the field programmable gate array.

Abstract: A method of training a learning network is described. The method includes generating a first estimate of a gradient for the learning network and generating subsequent estimates of the gradient using a feedback network. The feedback network generates improved perturbations for the subsequent gradient estimates. Gradient estimates include the first estimate of the gradient and the subsequent estimates of the gradient. The method also includes using the gradient estimates to determine weights in the learning network. The improved perturbations may include lower variance perturbations.

Abstract: A memristive device is described. The memristive device includes a first layer having a first plurality of conductive lines, a second layer having a second plurality of conductive lines, and memristive interlayer connectors. The first and second layers differ. The first and second pluralities of conductive lines are each lithographically defined. The first and second pluralities of conductive lines are insulated from each other. The memristive interlayer connectors are memristively coupled with a first portion of the first plurality of conductive lines and memristively coupled with a second portion of the second plurality of conductive lines. The memristive interlayer connectors are thus sparsely coupled with the first and second pluralities of conductive lines. Each memristive interlayer connector includes a conductive portion and a memristive portion.

Abstract: Provided are 2-aminoimidazole-phenyl derivative compounds of Formula (I): which compounds are useful in methods of controlling microbial growth, such as by enhancing the effects of an antibiotic administered in combination with the compound. Compositions including these compounds, devices including these compounds, and methods of using the same are also provided.

Abstract: A system includes inputs, outputs, and nodes between the inputs and the outputs. The nodes include hidden nodes. Connections between the nodes are determined based on a gradient computable using symmetric solution submatrices.

Abstract: A memristive device and mechanisms for providing and using the memristive device are described. The memristive device includes a nanowire, a plurality of memristive plugs and a plurality of electrodes. The nanowire has a conductive core and an insulator coating at least a portion of the conductive core. The insulator has a plurality of apertures therein. The memristive plugs are for the apertures. At least a portion of each of the memristive plugs resides in each of the apertures. The memristive plugs are between the conductive core and the electrodes.

Abstract: A method for performing learning in a dissipative learning network is described. The method includes determining a trajectory for the dissipative learning network and determining a perturbed trajectory for the dissipative learning network based on a plurality of target outputs. Gradients for a portion of the dissipative learning network are determined based on the trajectory and the perturbed trajectory. The portion of the dissipative learning network is adjusted based on the gradients.

Abstract: A memristive device and mechanisms for providing and using the memristive device are described. The memristive device includes a nanowire, a plurality of memristive plugs and a plurality of electrodes. The nanowire has a conductive core and an insulator coating at least a portion of the conductive core. The insulator has a plurality of apertures therein. The memristive plugs are for the apertures. At least a portion of each of the memristive plugs resides in each of the apertures. The memristive plugs are between the conductive core and the electrodes.

Abstract: A method for performing learning in a dissipative learning network is described. The method includes determining a trajectory for the dissipative learning network and determining a perturbed trajectory for the dissipative learning network based on a plurality of target outputs. Gradients for a portion of the dissipative learning network are determined based on the trajectory and the perturbed trajectory. The portion of the dissipative learning network is adjusted based on the gradients.

Abstract: The invention encompasses methods of increasing the rate of genetic progress or generating inbred lines in a non-human mammalian species comprising the use of nuclear transfer eggs or gametes derived from embryos of the non-human mammalian species.