Abstract: One embodiment provides a method, comprising: training, using deep imitation learning, a neural network associated with a predetermined ghosting model to predict player movements for at least one player during at least one sequence in a game; receiving, at an information handling device, tracking data associated with a player movement path for at least one player during the at least one sequence; analyzing, using a processor, the tracking data to determine at least one feature associated with the at least one player at a plurality of predetermined time points during the at least one sequence; and determining, using the predetermined ghosting model and the at least one feature, a ghosted movement path for the at least one player beginning from one of the plurality of predetermined time points. Other aspects are described and claimed.

Abstract: An example system and method facilitate enabling precise answers to technical support questions pertaining to a given computing environment, e.g., a cloud-based enterprise computing environment. The example method includes using an overtrained recurrent neural network employing Long Short-Term Memory (LSTM) cells to selectively answer specific questions by providing precise answers to technical support questions. A second neural network that is not overtrained can provide more generalized answers when a confidence measurement of an answer of the first neural network falls below a predetermined threshold. Furthermore, expert staff, e.g., developers and/or engineers that may be able to more precisely answer a specific question may be shown the answer. Subsequent expert answers or modifications to existing answers may be used to further refine the neural networks, e.g., via periodic supervised learning.

Abstract: Systems and methods for assessment of user price sensitivity using a predictive model are disclosed.

Abstract: An approach for training a recurrent neural network to create a model for anomaly detection in the topology of a network is disclosed. The approach comprises, creating an embedding vector for each resource in the network based on applying an embedding algorithm to each resource of the network. A feature vector is then created for each change to a resource in the network based on one or more properties of the change. A recurrent neural network can thus be trained with the embedding vectors and the feature vectors to create a model for anomaly detection in the topology of the network.

Abstract: A one-shot neural architecture search method referred to as MergeNAS by merging different types of convolutions into a single operation. This mergence approach reduces the search cost to roughly half a GPU-day as well as alleviates the over-fitting problem caused by a traditional differentiable architecture search (DARTS) approach by reducing the number of redundant parameters.

Abstract: A method includes receiving historical time-series data and generating training data comprising a plurality of randomized data points associated with the historical time-series data. The historical time-series data was generated by one or more sensors during one or more processes. The method further includes training a logistic regression classifier based on the training data to generate a trained logistic regression classifier. The trained logistic regression classifier is associated with a logistic regression that indicates a location of a transition pattern from a first data point to a second data point. The transition pattern reflects about a reflection point located on the transition pattern. The trained logistic regression classifier is capable of indicating a probability that new time-series data generated during a new execution of the one or more processes matches the historical time-series data.

Abstract: An optimization method comprises determining jump ratios of embedding layer parameters of a trained quantization model in a predetermined time range. The quantization model comprises a neural network model obtained after quantization processing on the embedding layer parameters. The method also comprises determining a jump curve in the predetermined time range according to the jump ratios, and fitting the jump curve to obtain a corresponding time scaling parameter. The method also comprises optimizing an initial algorithm of the quantization model based on the time scaling parameter to obtain an optimized target optimization algorithm, and training the quantization model based on the target optimization algorithm.

Abstract: A live model of a deep learning algorithm may be used to generate predictions of features of interest in an instance of training data. If the predictions correspond to actual features of interest, the predictions may be converted to qualitative labels, the instance may be designated as being acceptably labeled, and the live model may be trained on all instances of training data designated as acceptably labeled to update the live model. If the predictions do not correspond, a repetitive process of applying qualitative labels to features of interest in the instance of training data, quantitatively training on the qualitatively labeled instance of training data and all instances of training data designated as acceptably labeled, and generating predictions of features of interest until the predictions correspond to the actual features of interest.

Abstract: Disclosed is a disentangled personalized federated learning method via consensus representation extraction and diversity propagation provided by embodiments of the present application. The method includes: receiving, by a current node, local consensus representation extraction models and unique representation extraction models corresponding to other nodes, respectively; extracting, by the current node, the representations of the data of the current node by using the unique representation extraction models of other nodes respectively, and calculating first mutual information between different sets of representation distributions, determining similarity of the data distributions between the nodes based on the size of the first mutual information, and determining aggregation weights corresponding to the other nodes based on the first mutual information; the current node obtains the global consensus representation aggregation model corresponding to the current node.

Abstract: Aspects of the present invention disclose a method, computer program product, and system for optimizing a result for a combinatorial optimization problem. The method includes one or more processors receiving a black-box model. The method further includes one or more processors learning a multilinear polynomial surrogate model employing an exponential weight update rule. The method further includes one or more processors optimizing the learnt multilinear polynomial surrogate model. The method further includes one or more processors applying the black-box model to the optimized solution found by the multilinear polynomial surrogate model. In an additional aspect, the method of learning an optimized multilinear polynomial surrogate model employing an exponential weight update rule further includes one or more processors calculating utilizing data from the black-box model, an update of the coefficients of the multilinear polynomial surrogate model.

Abstract: Mixed signal multipliers and methods for operating the same include a sampling capacitor and an accumulate capacitor. A sampling switch is configured to store an analog value on the sampling capacitor when a digital bit value of a digital signal is one and to store a zero when the digital bit value of the digital signal is a zero. An accumulate switch is configured to store an average of the stored value of the sampling capacitor and a previous stored value of the accumulate capacitor. A processor is configured to alternately trigger the sampling capacitor and the sampling capacitor for each bit value in the digital signal.

Abstract: Systems, methods, and computer program products for multi-domain ensemble learning based on multivariate time sequence data are provided. A method may include receiving multivariate sequence data. At least a portion of the multivariate sequence data may be inputted into a plurality of anomaly detection models to generate a plurality of scores. The multivariate sequence data may be combined with the plurality of scores to generate combined intermediate data. The combined intermediate data may be inputted into a combined ensemble model to generate an output score. In response to determining that the output score satisfies a threshold, at least one of an alert may be communicated to a user device, the multivariate sequence data may be inputted into the feature-domain ensemble model to generate a feature importance vector, or at least one of a model-domain, a time-domain, a feature-domain, or the combined ensemble model may be updated.

Abstract: A machine learning environment utilizing training data generated by customer networks. A reinforcement learning machine learning environment receives and processes training data generated by simulated hosted, or integrated, customer networks. The reinforcement learning machine learning environment corresponds to machine learning clusters that receive and process training data sets provided by the integrated customer networks. The customer networks include an agent process that collects training data and forwards the training data to the machine learning clusters. The machine learning clusters can be configured in a manner to automatically process the training data without requiring additional user inputs or controls to configure the application of the reinforcement learning machine learning processes.

Abstract: Features related to systems and methods for reinforcement learning are described. The environment includes one or more agents for automating the training of reinforcement learning (RL) models. The environment may include a simulator or real-world observations. The features described identify key training parameters, resource configurations, virtual network configurations, and simulators based on historical training data.

Abstract: Systems and methods for analyzing the usage of a set of workloads in a hyper-converged infrastructure are disclosed. A neural network model is trained based upon historical usage data of the set of workloads. The neural network model can make usage predictions of future demands on the set of workloads to minimize over-allocation or under-allocation of resources to the workloads.

Abstract: The present disclosure is directed to methods and apparatus for validating and authenticating use of machine learning models. For example, various techniques are described herein to limit the vulnerability of machine learning models to attack and/or exploitation of the model for malicious use, and for detecting when such attack/exploitation has occurred. Additionally, various embodiments described herein promote the protection of sensitive and/or valuable data, for example by ensuring only licensed use is permissible. Moreover, techniques are described for version tracking, usage tracking, permission tracking, and evolution of machine learning models.

Abstract: A computer-implemented method for detecting an operation tendency is disclosed. The method includes preparing a general model for generating a general anomaly score. The method also includes preparing a specific model, for generating a specific anomaly score, trained with a set of a plurality of operation data related to operation by a target operator. The method further includes receiving input operation data. The method includes also calculating a detection score related to the operation tendency by using a general anomaly score and a specific anomaly score generated for the input operation data. Further the method includes outputting a result based on the detection score.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating candidate output sequences using language model neural networks. In particular, an auto-regressive language model neural network is used to generate a candidate output sequence. The same auto-regressive language model neural network is used to evaluate the candidate output sequence to determine rating scores for each of one or more criteria. The rating score(s) are then used to determine whether to provide the candidate output sequence.

Abstract: A system for training a multi-task model includes a processor and a memory in communication with the processor. The memory has a multi-task training module having instructions that, when executed by the processor, causes the processor to provide simulation training data having a plurality of samples to a multi-task model capable of performing at least a first task and a second task using at least one shared. The training module further causes the processor to determine a first value (gradience or loss) for the first task and a second value (gradience or loss) for a second task using the simulation training data and the at least one shared parameter, determine a task induced variance between the first value and the second value, and iteratively adjust the at least one shared parameter to reduce the task induced variance.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network used to select actions performed by a reinforcement learning agent interacting with an environment. In one aspect, a method includes maintaining a replay memory, where the replay memory stores pieces of experience data generated as a result of the reinforcement learning agent interacting with the environment. Each piece of experience data is associated with a respective expected learning progress measure that is a measure of an expected amount of progress made in the training of the neural network if the neural network is trained on the piece of experience data. The method further includes selecting a piece of experience data from the replay memory by prioritizing for selection pieces of experience data having relatively higher expected learning progress measures and training the neural network on the selected piece of experience data.