Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a student neural network. In one aspect, there is provided a method comprising: processing a training input using the student neural network to generate a student neural network output comprising a respective score for each of a plurality of classes; processing the training input using a brain emulation neural network to generate a brain emulation neural network output comprising a respective score for each of the plurality of classes; and adjusting current values of the student neural network parameters using gradients of an objective function that characterizes a similarity between: (i) the student neural network output for the training input, and (ii) the brain emulation neural network output for the training input.

Abstract: An intelligent tracking system generally includes one or more tracking devices, some of which may be passive tracking devices. Each passive tracking device includes one or more transceivers and is energized by an energizing signal. Some of these passive tracking devices may operate in a first communication mode or a second communication mode based on the energizing signal. Some tracking devices may include encryption modules or authentication modules. Some of these devices may incorporate a bulk acoustic wave oscillator.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for predicting object pose. In one aspect, a method includes receiving an image of an object having one or more feature points; providing the image as an input to a neural network subsystem trained to receive images of objects and to generate an output including a heat map for each feature point; applying a differentiable transformation on each heat map to generate respective one or more feature coordinates for each feature point; providing the feature coordinates for each feature point as input to an object pose solver configured to compute a predicted object pose for the object, wherein the predicted object pose for the object specifies a position and an orientation of an object; and receiving, at the output of the object pose solver, a predicted object pose for the object in the image.

Abstract: Methods, systems, and computer-readable media that implement autonomous seagoing power replenishment watercraft. An example system includes a plurality of marine vessels; a plurality of watercraft, each watercraft of the plurality of watercraft including a rechargeable electrical power supply and being configured to operate in: a first mode in which the watercraft awaits an assignment to provide electrical energy to a marine vessel of the plurality of marine vessels; a second mode in which the watercraft performs operations including keeping station with an assigned marine vessel and providing electrical energy to the assigned marine vessel from the power supply; and a third mode in which the watercraft recharges the power supply from a charging station. The system includes a controller configured to perform operations comprising: transmitting, to a first watercraft, an instruction indicating an assignment of the first watercraft to provide electrical energy to a first marine vessel.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a student neural network. In one aspect, there is provided a method comprising: processing a training input using the student neural network to generate an output for the training input; processing the student neural network output using a discriminative neural network to generate a discriminative score for the student neural network output, wherein the discriminative score characterizes a prediction for whether the network input was generated using: (i) the student neural network, or (ii) a brain emulation neural network; and adjusting current values of the student neural network parameters using gradients of an objective function that depends on the discriminative score for the student neural network output.

Abstract: Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.

Abstract: A system, including an optical imaging assembly configured to image a sample at an object plane to an image plane; an image sensor arranged at the image plane and configured to capture images of the sample for a field of view of the system; a light source configured to emit light having a wavelength, ?; a spatial light modulator (SLM) arranged to receive the light emitted from the light source and to provide a spatially modulated light pattern; one or more optical elements arranged to receive the spatially modulated light pattern from the SLM and to direct the spatially modulated light pattern to the image plane; and an electronic controller in communication with the image sensor and the spatial light modulator, the electronic controller being programmed to identify one or more targets in the field of view of the optical imaging assembly and to control the spatial light modulator to selectively direct light from the light source to the one or more targets identified by the electronic controller.

Abstract: A photonic integrated circuit comprises an optical deinterleaver, including an input region, a dispersive region, and at least two output regions. The input region is adapted to receive an input optical signal including a plurality of channels. The dispersive region is optically coupled to the input region to receive the input optical signal. The dispersive region includes an inhomogeneous arrangement of a first material and a second material to structure the dispersive region to separate the input optical signal into a plurality of multi-channel optical signals, including a first multi-channel optical signal and a second multi-channel optical signal. The at least two output regions, include a first out region and a second output region optically coupled to the dispersive region. The first output region is positioned to receive the first multi-channel optical signal and the second output region is positioned to receive the second multi-channel optical signal.

Abstract: A method includes receiving sensor data from a plurality of robot sensors on a robot. The method includes generating a depth map that includes a plurality of pixel depths. The method includes determining, for each respective pixel depth, based on the at least one robot sensor associated with the respective pixel depth, a pixelwise confidence level indicative of a likelihood that the respective pixel depth accurately represents a distance between the robot and a feature of the environment. The method includes generating a pixelwise filterable depth map for a control system of the robot. The pixelwise filterable depth map is filterable to produce a robot operation specific depth map. The robot operation specific depth map is determined based on a comparison of each respective pixelwise confidence level with a confidence threshold corresponding to at least one operation of the robot controlled by the control system of the robot.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting a neural network architecture for performing a machine learning task. In one aspect, a method comprises: obtaining data defining a synaptic connectivity graph representing synaptic connectivity between neurons in a brain of a biological organism; generating data defining a plurality of candidate graphs based on the synaptic connectivity graph; determining, for each candidate graph, a performance measure on a machine learning task of a neural network having a neural network architecture that is specified by the candidate graph; and selecting a final neural network architecture for performing the machine learning task based on the performance measures.

Abstract: The present disclosure relates to in vitro experiments and in silico computation and machine-learning based techniques to iteratively improve a process for identifying binders that can bind a target. Particularly, aspects of the present disclosure are directed to obtaining initial sequence data, identifying, by a first machine-learning model having model parameters learned from the initial sequence data, a first set of aptamer sequences, obtaining, using an in vitro binding selection process, subsequent sequence data including sequences from the first set of aptamer sequences, identifying, by a second machine-learning model having model parameters learned from the subsequent sequence data, a second set of aptamer sequences, determining, using one or more in vitro assays, analytical data for aptamers synthesized from the second set of aptamer sequences, and identifying a final set of aptamer sequences from the second set of aptamer sequences based on the analytical data associated with each aptamer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for fish weight estimation based on fish tracks identified in images. In some implementations, a method includes obtaining images of fish enclosed in a fish enclosure, identifying fish tracks shown in the images of the fish, determining a quality score for each of the fish tracks, selecting a subset of the fish tracks based on the quality scores, determining a representative weight of the fish in the fish enclosure based on weights of the fish shown in the subset of the fish tracks, and outputting the representative weight for display or storage at a device connected to the one or more processors.

Abstract: Methods, apparatus, and computer readable media related to combining and/or training one or more neural network modules based on version identifier(s) assigned to the neural network module(s). Some implementations are directed to using version identifiers of neural network modules in determining whether and/or how to combine multiple neural network modules to generate a combined neural network model for use by a robot and/or other apparatus. Some implementations are additionally or alternatively directed to assigning a version identifier to an endpoint of a neural network module based on one or more other neural network modules to which the neural network module is joined during training of the neural network module.

Abstract: A communication device is provided that estimates one or more disturbance values associated with one or more components of the communication device, and adjusts the communication device to change a received power of the output signal. The communication device includes a transmitter having a seed laser configured to provide an amount of bandwidth for an output signal, an Erbium-doped fiber amplifier (EDFA) configured to increase an amplitude of the output signal, and a single mode variable optical attenuator (SMVOA) configured to decrease the amplitude of the output signal.

Abstract: The optical tracking module includes an optical phased array (OPA), an analog drive, an integrated photodetector, and one or more processors. The OPA includes a plurality of array elements, and a plurality of phase shifters. The analog drive is configured to adjust the plurality of phase shifters. The integrated photodetector is configured to receive light from the OPA. The one or more processors is configured to extract signal information of an incoming beam via the OPA, and control an outgoing beam using the analog drive based on the signal information. The OPA, the analog drive, the integrated photodetector and the one or more processors are in an integrated circuit.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a synthesized signal. In some implementations, a computer-implemented system obtains generator input data including at least an input signal having one or more first characteristics, processes the generator input data to generate output data including a synthesized signal having one or more second characteristics using a generator neural network, and outputs the synthesized signal to a device. The generator neural network is trained, based on a plurality of training examples, with a discriminator neural network.

Abstract: A photonic coupler includes an input coupling section, an output coupling section, and a multimode interference (MMI) waveguide section. The input coupling section is adapted to receive an input optical signal along an input waveguide channel. The output coupling section is adapted to output a pair of output optical signals along output waveguide channels. The output optical signals having output optical powers split from the input optical signal. The MMI waveguide section is optically coupled between the input and output coupling sections. Notched waveguide sections may each be disposed between the MMI waveguide section and a corresponding one of the input or output coupling sections and/or the MMI waveguide section may include curvilinear sidewalls.

Abstract: Training and/or use of a machine learning model for placement of an object secured by an end effector of a robot. A trained machine learning model can be used to process: (1) a current image, captured by a vision component of a robot, that captures an end effector securing an object; (2) a candidate end effector action that defines a candidate motion of the end effector; and (3) a target placement input that indicates a target placement location for the object. Based on the processing, a prediction can be generated that indicates likelihood of successful placement of the object in the target placement location with application of the motion defined by the candidate end effector action. At many iterations, the candidate end effector action with the highest probability is selected and control commands provided to cause the end effector to move in conformance with the corresponding end effector action.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that provides an enhanced synchronization framework. One of the methods includes a primary and a second device that receive configuration information which identifies one or more actions to be performed by the secondary device when it receives specified pulses of a sequence of pulses from the primary device. The primary device transmits a sequence of pulses. The primary and the secondary device receive a particular pulse from the sequence of pulses. The secondary device determines whether the particular pulse satisfies one or more predetermined criteria and generates an instruction based on the determination.

Abstract: An optical communication system includes an optical transmitter and one or more processors. The optical transmitter is configured to output an optical signal, and includes an average-power-limited optical amplifier, such as an erbium-doped fiber amplifier (EDFA). The one or more processors are configured to receive optical signal data related to a received power for a communication link from a remote communication system and determine that the optical signal data is likely to fall below a minimum received power within a time interval. In response to the determination, the one or more processors are configured to determine a duty cycle of the optical transmitter based on a minimum on-cycle length and a predicted EDFA output power and operate the optical transmitter using the determined duty cycle to transmit an on-cycle power that is no less than the minimum required receiver power for error-free operation of the communication link.