Abstract: The present disclosure discloses a multi-agent coordination method. The method includes: performing multiple data collections on N agents to collect E sets of data, where N and E are integers greater than 1; and optimizing neural networks of the N agents using reinforcement learning based on the E sets of data. Each data collection includes: randomly selecting a first coordination pattern from multiple predetermined coordination patterns; obtaining N observations after the N agents act on an environment in the first coordination pattern; determining a first probability and a second probability that a current coordination pattern is the first coordination pattern based on the N observations; and determining a pseudo reward based on the first probability and the second probability. The E sets of data include: a first coordination pattern label indicating the first coordination pattern, the N observations, and the pseudo reward.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: collecting location data of users and identifying candidates for an impromptu interaction amongst the users based on converging locations of the candidates. A topic of the impromptu interaction is determined by common work interests amongst the candidates. Notification of the impromptu interaction is sent to the candidates to inform the topic and the other candidate, also with resources relevant to the topic.

Abstract: Media and method for a user interface for training an artificial intelligence system. Many artificial intelligence systems require large volumes of labeled training data before they can accurately classify previously unseen data items. However, for some problem domains, no pre-labeled training data set may be available. Manually labeling training data sets by a subject-matter expert is a laborious process. An interface to enable such a subject-matter expert to accurately, consistently, and quickly label training data sets is disclosed herein. By allowing the subject-matter expert to easily navigate between training data items and select the applicable labels, operation of the computer is improved.

Abstract: Briefly, example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to facilitate and/or support one or more operations and/or techniques for machine learning (ML) classification of digital content for mobile communication devices, such as implemented in connection with one or more computing and/or communication networks and/or protocols.

Abstract: An optical pulse stretcher includes a first delay optical system including a plurality of concave toroidal mirrors; and a beam splitter including a first surface and a second surface, causing a part of pulse laser light incident on the first surface to be transmitted in a first direction and output as a first beam and another part thereof to be reflected in a second direction and enter the first delay optical system, and causing a part of pulse laser light incident on the second surface from the first delay optical system to be reflected in the first direction and output as a second beam.

Abstract: The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment.

Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving data, the data comprising a plurality of examples, each of the plurality of examples comprising an input object and a desired output value, at least some of the plurality of examples being based upon feedback from a user; performing a machine learning operation on the data, the machine learning operation comprising performing an augmented gamma belief network operation, the augmented gamma belief network operation producing an inferred function based upon the data; and, generating a cognitive insight based upon the cognitive profile generated using the inferred function generated by the augmented gamma belief network operation.

Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving information regarding a temporal sequence of events; performing a temporal topic machine learning operation on the temporal sequence of events; generating a cognitive profile based upon the information generated by performing the temporal topic machine learning operation; and, generating a cognitive insight based upon the cognitive profile generated using the temporal topic machine learning operation.

Abstract: A photoresist baking apparatus is provided. The photoresist baking apparatus includes a baking chamber, a hot plate disposed in the baking chamber, and a cover plate disposed over the hot plate. The cover plate has a plurality of exhaust holes. The exhaust holes include a first exhaust hole and a second exhaust hole arranged in a first direction. The first exhaust hole and the second exhaust hole have different sizes.

Abstract: Embodiments provide systems and methods which facilitate optimization of a convolutional neural network (CNN). One embodiment provides for a non-transitory machine-readable medium storing instructions that cause one or more processors to perform operations comprising processing a trained convolutional neural network (CNN) to generate a processed CNN, the trained CNN having weights in a floating-point format. Processing the trained CNN includes quantizing the weights in the floating-point format to generate weights in an integer format. Quantizing the weights includes generating a quantization table to enable non-uniform quantization of the weights and quantizing the weights from the floating-point format to the integer format using the quantization table. The operations additionally comprise performing an inference operation utilizing the processed CNN with the integer format weights.

Abstract: A device manufacturing method including: performing a first exposure on a substrate using a first lithographic apparatus to form a first patterned layer including first features; processing the substrate to transfer the first features into the substrate; and performing a second exposure on the substrate using a second lithographic apparatus to form a second patterned layer including second features, wherein: the first lithographic apparatus has first and second control inputs effective to control first and second parameters of the first features at least partly independently; the second lithographic apparatus has a third control input effective to control the first and second parameters of the second features together; and the first exposure is performed with the first and/or second control input set to pre-bias the first and/or second parameter.

Abstract: A control apparatus for controlling a controlled object includes a measuring device configured to measure a state of the controlled object, and a controller configured to generate a manipulated variable corresponding to an output of the measuring device and a target value. The controller includes a compensator configured to output an index corresponding to the output of the measuring device and the target value, and a converter configured to convert the index into the manipulated variable such that a probability at which a predetermined manipulated variable is generated is a target probability.

Abstract: A method and system are disclosed for training a model that implements a machine-learning algorithm. The technique utilizes latent descriptor vectors to change a multiple-valued output problem into a single-valued output problem and includes the steps of receiving a set of training data, processing, by a model, the set of training data to generate a set of output vectors, and adjusting a set of model parameters and component values for at least one latent descriptor vector in the plurality of latent descriptor vectors based on the set of output vectors. The set of training data includes a plurality of input vectors and a plurality of desired output vectors, and each input vector in the plurality of input vectors is associated with a particular latent descriptor vector in a plurality of latent descriptor vectors. Each latent descriptor vector comprises a plurality of scalar values that are initialized prior to training the model.

Abstract: One or more embodiments of a content naming system provide machine-learned name suggestions to a user for naming content items. Specifically, an online content management system can train a machine-learning model to identify a naming pattern from previously stored content items corresponding to a user account of the user. The online content management system uses the machine-learning model to determine a plurality of name suggestions for naming a content item associated with the user account. One or more embodiments provide graphical elements corresponding to the name suggestions within a graphical user interface. The user can select one or more graphical elements to add the corresponding name suggestion(s) to the name of the content item.

Abstract: A photolithography device includes: a fixed slot, configured to install and fix the light source; a sensing module, configured to sense the distance information between the light source and the fixed slot; a prompt module, configured to send prompt information according to the distance information; and a determination module, configured to determine the installation status of the light source according to the prompt information.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

Abstract: Systems, methods, and non-transitory computer readable media are configured to train a machine learning model. The training can be based on a training set of embeddings of a first type and a training set of embeddings of a second type. The machine learning model can be trained to receive an embedding of a second type and to output a corresponding embedding of the first type. A given embedding of the second type can be provided as input to the machine learning model. An embedding of the first type can be obtained from the machine learning model. The embedding of the first type can correspond to the given embedding of the second type.

Abstract: A learning apparatus includes: an update unit which updates a dictionary used by a classifier; a calculation unit which calculates, by using a dictionary updated and one or more samples with labeling being samples assigned with labels, a ratio to a number of the samples with labeling as a loss with respect to all the samples with labeling; and a determination unit which determines whether to update the dictionary, by using the loss, wherein, when the determination unit determines to update the dictionary, the update unit updates the dictionary by using the samples with labeling added with a new sample with labeling, and wherein the determination unit determines whether to update the dictionary, by using a loss calculated by using the updated dictionary and a loss calculated by using the dictionary before updating with respect to all the samples with labeling before adding the new sample with labeling.

Abstract: Embodiments of the present disclosure generally relate to apparatus and methods for verification and re-use of process fluids. The apparatus generally includes a tool for performing lithography, and a recirculation path coupled to the tool. The recirculation path generally includes a collection unit coupled at first end to a first end of the tool, and a probe coupled at a first end to a second end of the collection unit, the probe for determining one or more characteristics of a fluid flowing from the tool. The recirculation path of the apparatus further generally includes a purification unit coupled at a first end to a third end of the collection unit, the purification unit further coupled at a second end to a second end of the probe, the purification unit for changing a characteristic of the fluid.

Abstract: A computer-implemented method for learning a policy for selection of an associative topic, which can be used in a dialog system, is described. The method includes obtaining a policy base that indicates a topic transition from a source topic to a destination topic and a short-term reward for the topic transition, by analyzing data from a corpus. The short-term reward may be defined as probability of associating a positive response. The method also includes calculating an expected long-term reward for the topic transition using the short-term reward for the topic transition with taking into account a discounted reward for a subsequent topic transition. The method further includes generating a policy using the policy base and the expected long-term reward for the topic transition. The policy indicates selection of the destination topic for the source topic as an associative topic for a current topic.