Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for modeling agents in multi-agent systems as reinforcement learning (RL) agents and training control policies that cause the agents to cooperate towards a common goal. A method can include generating, for each of a group of simulated local agents in an agent network in which the simulated local agents share resources, information, or both, experience tuples having a state for the simulated local agent, an action taken by the simulated local agent, and a local result for the action taken, updating each local policy of each simulated local agent according to the respective local result, providing, to each of the simulated local agents, information representing a global state of the agent network, and updating each local policy of each simulated local agent according to the global state of the agent network.

Abstract: Implementations are directed to improving network anti-fragility. In some aspects, a method includes receiving parameter data from a network of nodes, the parameter data comprising attributes, policies, and action spaces for each node in the network of nodes; configuring one or more interruptive events on one or more nodes included in the network of nodes; determining a first action of each node in the network of nodes in response to the one or more interruptive events; determining a first performance metric, for each node, that corresponds to the first action, wherein the first performance matric is determined based on at least a first reward value associated with the first action; continuously updating the first action in an iterative process to obtain a final action, wherein a performance metric corresponding to the final action satisfies a performance threshold, and transmitting the final action for each node to the network of nodes.

Abstract: In one aspect, there is provided a method performed by one or more data processing apparatus for training a neural network, the method including: obtaining a set of training examples, where each training example includes: (i) a training input, and (ii) a target output, and training the neural network on the set of training examples. Training the neural network can include, for each training example: processing the training input using the neural network to generate a corresponding training output, updating current values of at least a set of encoder sub-network parameters and a set of decoder sub-network parameters by a supervised update, and updating current values of at least a set of brain emulation sub-network parameters by an unsupervised update based on correlations between activation values generated by artificial neurons of the neural network during processing of the training input by the neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing defect detection using brain emulation neural networks.

Abstract: In one aspect, there is provided a method performed by one or more data processing apparatus, the method includes: obtaining a network input including a respective data element at each input position in a sequence of input positions, and processing the network input using a neural network to generate a network output that defines a prediction related to the network input, where the neural network includes a sequence of encoder blocks and a decoder block, where each encoder block has a respective set of encoder block parameters, and where the set of encoder block parameters includes multiple brain emulation parameters that, when initialized, represent biological connectivity between multiple biological neuronal elements in a brain of a biological organism.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing remote sensing data using brain emulation neural networks. One of the methods includes obtaining an aerial image of a plurality of agricultural plots; processing the aerial image using an encoder subnetwork of a segmentation neural network to generate an encoder subnetwork output; processing the encoder subnetwork output using a brain emulation subnetwork of the segmentation neural network to generate a brain emulation subnetwork output; processing the brain emulation subnetwork output using a decoder subnetwork of the segmentation neural network to generate a network output that defines a segmentation of the aerial image into a plurality of categories including at least one agricultural plot category; and identifying at least one of the plurality of agricultural plots in the aerial image from the segmentation of the aerial image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing brain emulation neural networks using compressed matrix representations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing connectivity neural network layers. One of the methods includes processing a network input using a neural network to generate a network output, comprising: generating a layer input to a connectivity layer of the neural network based on the network input, wherein the layer input to the connectivity layer comprises a plurality of input values arranged in a plurality of input channels; processing the layer input using the connectivity layer to generate a layer output comprising a plurality of output values arranged in a plurality of output channels; processing the plurality of output channels of the connectivity layer using a brain emulation subnetwork of the neural network to generate a brain emulation subnetwork output; and generating the network output based on the brain emulation subnetwork output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining network architectures based on synaptic connectivity. One of the methods includes processing a network input using a neural network to generate a network output, comprising: processing the network input using an encoder subnetwork of the neural network to generate an embedding of the network input; processing the embedding of the network input using a first connectivity layer of the neural network to generate a first connectivity layer output; processing the first connectivity layer output using a brain emulation subnetwork of the neural network to generate a brain emulation subnetwork output; processing the brain emulation subnetwork output using a second connectivity layer of the neural network to generate a second connectivity layer output; and processing the second connectivity layer output using a decoder subnetwork of the neural network to generate the network output.

Abstract: In one aspect, there is provided a method performed by one or more data processing apparatus that includes obtaining a point cloud dataset representing a brain of a biological organism. The point cloud dataset includes a collection of brain points that each define a respective spatial location in the brain. The method further includes identifying multiple brain points from the point cloud dataset as being located on a surface of the brain by repeatedly performing operations including initializing a current value of a position parameter and iteratively adjusting the current value of the position parameter until a termination criterion is satisfied. The termination criterion is satisfied if at least one brain point from the point cloud dataset is included in an interior of a shape parameterized by the current value of the position parameter.

Abstract: A coating for pelletized thermoplastic road marking material is provided in which at least one of waxes, silica compounds, and inorganic compounds is provided on the surface of the thermoplastic pellet. The pellet is formed by mixing a binder mixture with a filler mixture, heating the mixed ingredients while mixing into a homogenous molten mixture and then extruding the molten mixture. The extruded material is cooled, cut into individual pellets and then coated. The coating prevents clumping of the pellets and also imparts improved flowability and lower melting point properties. Preferred coatings include micronized polyethylene wax, silicates, silanes, silicones, siliconates, fluoropolymers, calcium carbonate and zeolite.

Abstract: A coating for pelletized thermoplastic road marking material is provided in which at least one of waxes, silica compounds, and inorganic compounds is provided on the surface of the thermoplastic pellet. The pellet is formed by mixing a binder mixture with a filler mixture, heating the mixed ingredients while mixing into a homogenous molten mixture and then extruding the molten mixture. The extruded material is cooled, cut into individual pellets and then coated. The coating prevents clumping of the pellets and also imparts improved flowability and lower melting point properties. Preferred coatings include micronized polyethylene wax, silicates, silanes, silicones, siliconates, fluoropoymers, calcium carbonate and zeolite.

Abstract: A composition of matter suitable for use as a road marking substance and a method thereof provides for the steps of mixing a binder mixture with a filler mixture, heating the mixed ingredients while mixing into a homogenous molten mixture and then extruding the molten mixture. The extruded material is cooled, cut into individual pellets, coated with an anti-clumping coating and packaged for use in making a road marking substance in situ. The binder can be alkyd-based or hydrocarbon based. The binder includes rosin resins, wax and a plasticizer, and a hydrocarbon resin is added for the hydrocarbon-based binder. The filler contains titanium dioxide, a pigment (if necessary) and ground calcium carbonate.

Abstract: A composition of matter suitable for use as a road marking substance and a method thereof provides for the steps of mixing a binder mixture with a filler mixture, heating the mixed ingredients while mixing into a homogenous molten mixture and then extruding the molten mixture. The extruded material is cooled, cut into individual pellets, coated with an anti-clumping coating and packaged for use in making a road marking substance in situ. The binder can be alkyd-based or hydrocarbon based. The binder includes rosin resins, wax and a plasticizer, and a hydrocarbon resin is added for the hydrocarbon-based binder. The filler contains titanium dioxide, a pigment (if necessary) and ground calcium carbonate.

Abstract: The invention relates to pelletizing thermoplastic road marking substance containing light-reflective agents, such as glass beads. A dry formulation of the ingredients is transported to a heating station, where the dry mix is heated to a molten state. The melted mix is extruded into form pockets of a moving conveyor. As the conveyor moves through a cooling station, the molten substance in the form pockets solidifies forming individual pellets. The pellets are then removed from the form pockets, packaged and shipped to customers.

Abstract: A coating for pelletized thermoplastic road marking material is provided in which at least one of waxes, silica compounds, and inorganic compounds is provided on the surface of the thermoplastic pellet. The pellet is formed by mixing a binder mixture with a filler mixture, heating the mixed ingredients while mixing into a homogenous molten mixture and then extruding the molten mixture. The extruded material is cooled, cut into individual pellets and then coated. The coating prevents clumping of the pellets and also imparts improved flowability and lower melting point properties. Preferred coatings include micronized polyethylene wax, silicates, silanes, silicones, siliconates, fluoropoymers, calcium carbonate and zeolite.

Abstract: A composition of matter suitable for use as a road marking substance and a method thereof provides for the steps of mixing a binder mixture with a filler mixture, heating the mixed ingredients while mixing into a homogenous molten mixture and then extruding the molten mixture. The extruded material is cooled, cut into individual pellets, coated with an anti-clumping coating and packaged for use in making a road marking substance in situ. The binder can be alkyd-based or hydrocarbon based. The binder includes rosin resins, wax and a plasticizer, and a hydrocarbon resin is added for the hydrocarbon-based binder. The filler contains titanium dioxide, a pigment (if necessary) and ground calcium carbonate.

Abstract: A composition of matter suitable for use as a road marking substance and a method thereof provides for the steps of mixing a binder mixture with a filler mixture, heating the mixed ingredients while mixing into a homogenous molten mixture and then extruding the molten mixture. The extruded material is cooled, cut into individual pellets, coated with an anti-clumping coating and packaged for use in making a road marking substance in situ. The binder can be alkyd-based or hydrocarbon based. The binder includes rosin resins, wax and a plasticizer, and a hydrocarbon resin is added for the hydrocarbon-based binder. The filler contains titanium dioxide, a pigment (if necessary) and ground calcium carbonate.