Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.

Abstract: Systems and methods are provided for adding a heated stream of light hydrocarbons to a fluidized coking environment to improve liquid product yield and/or reduce coke production. The light hydrocarbons can correspond to C1-C10 hydrocarbons and/or hydrogen. The light hydrocarbons can be heated so that the light hydrocarbons are exposed to an activation temperature of 535° C. to 950° C. and/or an activation temperature higher than the temperature in the coking zone by 50° C. or more for an activation time prior to entering the fluidized coking reactor and/or the coking zone in the fluidized coking environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating document vector representations. One of the methods includes obtaining a new document; and determining a vector representation for the new document using a trained neural network system, wherein the trained neural network system has been trained to receive an input document and a sequence of words from the input document and to generate a respective word score for each word in a set of words, wherein each of the respective word scores represents a predicted likelihood that the corresponding word follows a last word in the sequence in the input document, and wherein determining the vector representation for the new document using the trained neural network system comprises iteratively providing each of the plurality of sequences of words to the trained neural network system to determine the vector representation for the new document using gradient descent.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing sequential data. In one aspect, a computer-implemented method includes receiving a request to generate a system output for an input data sequence, the input data sequence including a plurality of tokens. One or more tokens may be designated as tokens to be skipped. When a token has not been designated as a token to be skipped, the token is processed using a recurrent neural network to update a current internal state of the recurrent neural network. The system output is generated from the final internal state of the recurrent neural network.

Abstract: Scales are prevented or inhibited from forming in a well or in a formation penetrated by a well by pumping into the well a fluid comprising a hydratable polymer, a crosslinking agent, such as an organometallic crosslinking agent containing a polyvalent metal and a scale inhibitor selected from the group consisting of polyvinyl sulfonates, a polyacrylamidomethylpropane sulfonic acid, carboxymethyl inulin and sulfonated polyacrylates and mixtures thereof.

Abstract: An FI having an in-situ particle detector and a method for particle detection therein are provided. In one aspect, the FI includes a fan, a substrate support, a particle detector, and an exhaust outlet. The fan, substrate support, and particle detector are arranged such that, in operation, the fan directs air towards the exhaust outlet and over a substrate on the substrate support to create laminar flow. The particle detector, positioned downstream from the substrate support and upstream from the exhaust outlet, analyzes the air and detects particle concentration before the particles are exhausted. The collected particle detection data may be combined with data from other sensors in the FI and used to identify the source of particle contamination. The particle detector may also be incorporated into other system components, including but not limited to, a load-lock or buffer chamber to detect particle concentration therein.

Abstract: Systems and techniques are disclosed for labeling objects within an image. The objects may be labeled by selecting an option from a plurality of options such that each option is a potential label for the object. An option may have an option score associated with. Additionally, a relation score may be calculated for a first option and a second option corresponding to a second object in an image. The relation score may be based on a frequency, probability, or observance corresponding to the co-occurrence of text associated with the first option and the second option in a text corpus such as the World Wide Web. An option may be selected as a label for an object based on a global score calculated based at least on an option score and relation score associated with the option.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices includes receiving data specifying machine learning operations, and determining a placement that assigns each of the operations specified by the data to a respective device from the multiple hardware devices.

Abstract: A method for determining a placement for machine learning model operations across multiple hardware devices is described.

Abstract: Systems and methods are provided for integrating a fluidized coking process, optionally a coke gasification process, and processes for production of additional liquid products from the coking and/or gasification process. In some aspects, the integrated processes can allow for conversion of olefins generated during a fluidized coking process to form additional liquid products. Additionally or alternately, in some aspects the integrated processes can allow for separation of syngas from the flue gas/fuel gas generated by a gasifier integrated with a fluidized coking process. This syngas can then be used to form methanol, which can then be converted in a methanol conversion process to form heavier products. In such aspects, olefins generated during the fluidized coking process can be added to the methanol conversion process to improve the yield.

Abstract: Scales are prevented or inhibited from forming in a well or in a formation penetrated by a well by pumping into the well a fluid comprising a hydratable polymer, a crosslinking agent, such as an organometallic crosslinking agent containing a polyvalent metal and a scale inhibitor selected from the group consisting of polyvinyl sulfonates, a polyacrylamidomethylpropane sulfonic acid, carboxymethyl inulin and sulfonated polyacrylates and mixtures thereof.

Abstract: A seal assembly includes a seal body, a spring disposed adjacent to the seal body, and a seal ring disposed adjacent to the seal body. The seal body and the seal ring can include a plastic polymer material. The seal assembly can be a subcomponent of hydraulic strut in the landing gear of an aircraft.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model. An exemplary system applying implicit bridging for machine learning tasks, as described in this specification, trains a machine learning model to perform certain types of machine learning tasks without requiring explicit training data for the certain types of machine learning tasks to be used during training.

Abstract: Tetrahydrothiophene and related heterocyclic analogs and related methods for GABA aminotransferase inactivation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch defining a respective architecture of a child neural network that is configured to perform a particular neural network task; for each output sequence in the batch: training a respective instance of the child neural network having the architecture defined by the output sequence; evaluating a performance of the trained instance of the child neural network on the particular neural network task to determine a performance metric for the trained instance of the child neural network on the particular neural network task; and using the performance metrics for the trained instances of the child neural network to adjust the current values of the controller parameters of the controller neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for structuring and training a recurrent neural network. This describes a technique that improves the ability to capture long term dependencies in recurrent neural networks by adding an unsupervised auxiliary loss at one or more anchor points to the original objective. This auxiliary loss forces the network to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences and also improving full backpropagation through time.

Abstract: A network function optimization method, system, and computer program product, include optimizing network function chain components by modifying a structure of the network function chain components by removing one of the functions of the network function chain components in response to a constraint according to a policy requirement.

Abstract: An FI having an in-situ particle detector and a method for particle detection therein are provided. In one aspect, the FI includes a fan, a substrate support, a particle detector, and an exhaust outlet. The fan, substrate support, and particle detector are arranged such that, in operation, the fan directs air towards the exhaust outlet and over a substrate on the substrate support to create laminar flow. The particle detector, positioned downstream from the substrate support and upstream from the exhaust outlet, analyzes the air and detects particle concentration before the particles are exhausted. The collected particle detection data may be combined with data from other sensors in the FI and used to identify the source of particle contamination. The particle detector may also be incorporated into other system components, including but not limited to, a load-lock or buffer chamber to detect particle concentration therein.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating document vector representations. One of the methods includes obtaining a new document; and determining a vector representation for the new document using a trained neural network system, wherein the trained neural network system has been trained to receive an input document and a sequence of words from the input document and to generate a respective word score for each word in a set of words, wherein each of the respective word scores represents a predicted likelihood that the corresponding word follows a last word in the sequence in the input document, and wherein determining the vector representation for the new document using the trained neural network system comprises iteratively providing each of the plurality of sequences of words to the trained neural network system to determine the vector representation for the new document using gradient descent.