Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a reservoir computing neural network. In one aspect there is provided a reservoir computing neural network comprising: (i) a brain emulation sub-network, and (ii) a prediction sub-network. The brain emulation sub-network is configured to process the network input in accordance with values of a plurality of brain emulation sub-network parameters to generate an alternative representation of the network input. The prediction sub-network is configured to process the alternative representation of the network input in accordance with values of a plurality of prediction sub-network parameters to generate the network output. The values of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusting during training of the reservoir computing neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an artificial neural network architecture based on a synaptic connectivity graph. According to one aspect, there is provided a method comprising: obtaining a synaptic resolution image of at least a portion of a brain of a biological organism; processing the image to identify: (i) a plurality of neurons in the brain, and (ii) a plurality of synaptic connections between pairs of neurons in the brain; generating data defining a graph representing synaptic connectivity between the neurons in the brain; determining an artificial neural network architecture corresponding to the graph representing the synaptic connectivity between the neurons in the brain; and processing a network input using an artificial neural network having the artificial neural network architecture to generate a network output.

Abstract: A sensor device includes a sensor housing defining a channel extending along a channel axis through the housing from a first side of the sensor housing to a second side of the sensor housing opposite the first side, at least one contact electrode extending from the first side of the housing, an electrically-conducting lead attached to the housing in electrical communication with the at least one contact electrode, and a locking mechanism located in the channel permitting one-way axial motion of a thread threaded through the channel from the first side to the second side.

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: 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, 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: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a reservoir computing neural network. In one aspect there is provided a reservoir computing neural network comprising: (i) a brain emulation sub-network, and (ii) a prediction sub-network. The brain emulation sub-network is configured to process the network input in accordance with values of a plurality of brain emulation sub-network parameters to generate an alternative representation of the network input. The prediction sub-network is configured to process the alternative representation of the network input in accordance with values of a plurality of prediction sub-network parameters to generate the network output. The values of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusting during training of the reservoir computing neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an artificial neural network architecture based on a synaptic connectivity graph. According to one aspect, there is provided a method comprising: obtaining a synaptic resolution image of at least a portion of a brain of a biological organism; processing the image to identify: (i) a plurality of neurons in the brain, and (ii) a plurality of synaptic connections between pairs of neurons in the brain; generating data defining a graph representing synaptic connectivity between the neurons in the brain; determining an artificial neural network architecture corresponding to the graph representing the synaptic connectivity between the neurons in the brain; and processing a network input using an artificial neural network having the artificial neural network architecture to generate a network output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining an artificial neural network architecture corresponding to a sub-graph of a synaptic connectivity graph. In one aspect, there is provided a method comprising: obtaining data defining a graph representing synaptic connectivity between neurons in a brain of a biological organism; determining, for each node in the graph, a respective set of one or more node features characterizing a structure of the graph relative to the node; identifying a sub-graph of the graph, comprising selecting a proper subset of the nodes in the graph for inclusion in the sub-graph based on the node features of the nodes in the graph; and determining an artificial neural network architecture corresponding to the sub-graph of the graph.

Abstract: An example method may include receiving, from a client computing device, an indication of a target drop-off spot for an object within a first virtual model of a first region of a delivery destination. A second virtual model of a second region of the delivery destination may be determined based on sensor data received from one or more sensors on a delivery vehicle. A mapping may be determined between physical features represented in the first virtual model and physical features represented in the second virtual model to determine an overlapping region between the first and second virtual models. A position of the target drop-off spot within the second virtual model may be determined based on the overlapping region. Based on the position of the target drop-off spot within the second virtual model, the delivery vehicle may be navigated to the target drop-off spot to drop off the object.

Abstract: The subject matter of this specification generally relates to modular vehicles including separable pod and base units. In some implementations, a computing system installed in a vehicle base identifies a vehicle pod that is detachably connected to a chassis on the vehicle base. In response to identifying that the vehicle pod is detachably connected to the chassis on the vehicle base, a communications link can be established between the computing system installed in the vehicle base and a computing system installed in the vehicle pod. Based on information obtained through the communications link, the computing system installed in the vehicle base can determine a particular configuration of the vehicle pod that is detachably connected to the chassis. The computing system can then verify that the vehicle base can safely transport the vehicle pod while the vehicle pod is detachably connected.

Abstract: An example method may include receiving, from a client computing device, an indication of a target drop-off spot for an object within a first virtual model of a first region of a delivery destination. A second virtual model of a second region of the delivery destination may be determined based on sensor data received from one or more sensors on a delivery vehicle. A mapping may be determined between physical features represented in the first virtual model and physical features represented in the second virtual model to determine an overlapping region between the first and second virtual models. A position of the target drop-off spot within the second virtual model may be determined based on the overlapping region. Based on the position of the target drop-off spot within the second virtual model, the delivery vehicle may be navigated to the target drop-off spot to drop off the object.

Abstract: A method of delivering air to a user includes receiving, by a controller and from a sensor, motion information of the user. The motion information represents motion of a portion of a head of the user below eyes of the user. The sensor and the controller are coupled to a portable article of the user. The method also includes determining, by the controller, based on the motion information, a position of the head of the user. The method further includes controlling, by the controller based on the determined position, a fluid outlet of a fluid conduit fluidly coupled to and configured to receive air from a fan.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an artificial neural network architecture based on a synaptic connectivity graph. According to one aspect, there is provided a method comprising: obtaining a synaptic resolution image of at least a portion of a brain of a biological organism; processing the image to identify: (i) a plurality of neurons in the brain, and (ii) a plurality of synaptic connections between pairs of neurons in the brain; generating data defining a graph representing synaptic connectivity between the neurons in the brain; determining an artificial neural network architecture corresponding to the graph representing the synaptic connectivity between the neurons in the brain; and processing a network input using an artificial neural network having the artificial neural network architecture to generate a network output.

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: 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: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a reservoir computing neural network. In one aspect there is provided a reservoir computing neural network comprising: (i) a brain emulation sub-network, and (ii) a prediction sub-network. The brain emulation sub-network is configured to process the network input in accordance with values of a plurality of brain emulation sub-network parameters to generate an alternative representation of the network input. The prediction sub-network is configured to process the alternative representation of the network input in accordance with values of a plurality of prediction sub-network parameters to generate the network output. The values of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusting during training of the reservoir computing neural network.

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, and apparatus, including computer programs encoded on a computer storage medium, for determining an artificial neural network architecture corresponding to a sub-graph of a synaptic connectivity graph. In one aspect, there is provided a method comprising: obtaining data defining a graph representing synaptic connectivity between neurons in a brain of a biological organism; determining, for each node in the graph, a respective set of one or more node features characterizing a structure of the graph relative to the node; identifying a sub-graph of the graph, comprising selecting a proper subset of the nodes in the graph for inclusion in the sub-graph based on the node features of the nodes in the graph; and determining an artificial neural network architecture corresponding to the sub-graph of the graph.

Abstract: A bioamplifier for analyzing electroencephalogram (EEG) signals is disclosed. The bioamplifier includes an input terminal for receiving an EEG signal from a plurality of sensors coupled to a user. The bioamplifier also includes an analogue-to-digital converter arranged to receive the EEG signal from the input terminal and convert the EEG signal to a digital EEG signal. A data processing apparatus within the bioamplifier is arranged to receive the digital EEG signal from the analogue-to-digital converter and programmed to process, in real time the digital EEG signal using a first machine learning model to generate a cleaned EEG signal having a higher signal-to-noise ratio than the digital EEG signal. The bioamplifier further includes a power source to provide electrical power to the analogue-to-digital converter and the data processing apparatus. The bioamplifier includes a housing that contains the analogue-to-digital converter, the data processing apparatus, the power source, and the sensor input.