Abstract: Systems and methods of the present disclosure are directed to a method for generating a machine-learned multitask model configured to perform tasks. The method can include obtaining a machine-learned multitask search model comprising candidate nodes. The method can include obtaining tasks and machine-learned task controller models associated with the tasks. As an example, for a task, the method can include using the task controller model to route a subset of the candidate nodes in a machine-learned task submodel for the corresponding task. The method can include inputting task input data to the task submodel to obtain a task output. The method can include generating, using the task output, a feedback value based on an objective function. The method can include adjusting parameters of the task controller model based on the feedback value.

Abstract: Quantum generative models for sampling many-body spectral functions are provided. Quantum approximate Bayesian computation is provided for NMR model inference.

Abstract: A computer-implemented method includes: receiving, by a computing device, data comprising a labeled dataset and an unlabeled dataset; generating, by the computing device, a set of heuristics using the labeled dataset; generating, by the computing device, a vector of initial labels by labeling each point in the unlabeled dataset using the set of heuristics; generating, by the computing device, a refined set of heuristics using data-driven active learning; generating, by the computing device, a vector of training labels by automatically labeling each point in the unlabeled dataset using the refined set of heuristics; and outputting, by the computing device, the vector of training labels to a client device or a data repository.

Abstract: In some aspects, the disclosure is directed to methods and systems for machine learning-based document classification using multiple classifiers. Various classifiers may be employed during different iterations of the method to advance the classification of a document. The document may be classified and labeled in response to a predetermined number of classifiers agreeing upon a meaningful label. Further, the meaningful label may only be applied to the document in the event that the classifiers predicted the document label with a confidence score in excess of a threshold value.

Abstract: A graph neural network for average power estimation of netlists is trained with register toggle rates over a power window from an RTL simulation and gate level netlists as input features. Combinational gate toggle rates are applied as labels. The trained graph neural network is then applied to infer combinational gate toggle rates over a different power window of interest and/or different netlist.

Abstract: The computing system includes a neural network system configured to drive an artificial neural network (ANN); and a quantization system configured to quantize the ANN, wherein the quantization system is further configured to quantize parameters of the ANN to generate the quantized parameters of the ANN, generate a quantization error of the parameters of the ANN based on the parameters of the ANN and the quantized parameters, generate a compensation bias based on the quantized parameters and the quantization error of the parameters of the ANN, and transmit the generated quantized parameters and the compensation bias to the neural network system.

Abstract: A classification system is provided for efficient machine-learning-based classification using a large set of possible classes (e.g., millions or hundreds of millions of distinct classes). A two-step process may be used whereby the large set of classes is segmented into reasonably-sized segments, and a separate classification model is generated for each of the different segments of classes.

Abstract: When a molecule is lost from a site of a qubit array, the site can be identified as a “target” site. A target site can be reloaded by transporting a molecule from a reservoir at least two millimeters to the target site. Alternatively, in response to the identifying, a molecule that has been transferred from the reservoir to a qubit-array region including the qubit array can be transferred to the target site. Quantum-logic language (QLL) programs can continue qubit operations on the array during transfers from the reservoir to the qubit region. Such operations can also continue during transfer from within the qubit region to a target site; in some cases, these latter operations are limited to sections of the qubit array not including a target site.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating prediction outputs characterizing a set of entities. In one aspect, a method comprises: obtaining data defining a graph, comprising: (i) a set of nodes, wherein each node represents a respective entity from the set of entities, (ii) a current set of edges, wherein each edge connects a pair of nodes, and (iii) a respective current embedding of each node; at each of a plurality of time steps: updating the respective current embedding of each node, comprising processing data defining the graph using a graph neural network; and updating the current set of edges based at least in part on the updated embeddings of the nodes; and at one or more of the plurality of time steps: generating a prediction output characterizing the set of entities based on the current embeddings of the nodes.

Abstract: A computer system displays paths based on processing of at least one series of input data including a list of time-stamped tasks. The tasks include an identifier of an object, an identifier of an action and a piece of time information. The system includes a piece of connected user computer equipment executing a display application and at least one remote server executing an application for calculating a path model from tables.

Abstract: A method includes using a first procedure of discretizing a user specified nano-device structure for at least one quantum method with open boundary conditions. Additionally, the first procedure includes solving the at least one quantum method with open boundary conditions, thereby having a solution of the at least one quantum method with open boundary conditions. Moreover, the first procedure includes extracting a parameter out of the solution of the at least one quantum method with open boundary conditions. Furthermore, the first procedure includes discretizing at least one quantum method with closed boundary conditions to the user-specified nano-device structure using the parameter. Next, the first procedure includes solving the at least one quantum method with closed boundary conditions to the user-specified nano-device structure using the parameter. Further, the first procedure includes extracting the device behavior of the user-specified nano-device structure.

Abstract: A method and system may operate a neural network (NN), e.g. during inference or training, by executing a first tensor column comprising task instruction code representing at least one computation spanning a number of layers of the NN, the execution producing an output, and compressing that output. In order to execute a next tensor column, the output may be uncompressed to produce uncompressed output; and the second tensor column may be executed, the second tensor column including task instruction code representing at least one computation spanning a number of layers of the NN. The second tensor column may take as input the uncompressed output.

Abstract: Example aspects of the present disclosure provide systems and methods to learn machine-learned model parameters for models of quantum computing systems. In particular, example aspects of the present disclosure are directed to systems and methods to learn a deep neural network configured to predict parameter values for a physical model that models quantum dynamics of interactions between one or more qubits of a quantum gate and one or more two-level-system (TLS) defects during operation of the quantum gate through use of an evolutionary algorithm.

Abstract: A data stream is received. Data elements of the data stream are analyzed using one or more machine learning models and one or more machine learning prediction explanation implementations. Different candidate presentations are tested. The different candidate presentations are associated with machine learning results provided to different reviewers in a group of human-in-the-loop reviewers that review predictions of the one or more machine learning models. The different candidate presentations include different explanations generated by the one or more machine learning prediction explanation implementations and at least one control candidate presentation corresponding to an absent explanation. Different aspects of the testing are monitored. Results of the monitoring are used to make a selection among the different candidate presentations.

Abstract: One or more computing devices, systems, and/or methods for implementing an automated model update pipeline are provided. User behavior data associated with content provided to users may be collected. An automatic model training is invoked to train a new model to output a set of model parameters based upon a configuration specifying a target audience, features extracted from user behavior data, and training model parameters. In response to determining that the new model will outperform a deployed model on a content serving platform, an automatic model updater is invoked to update the content serving platform with the new model and a ranking profile of the new model for serving content requests.

Abstract: Conventionally, applying analytics on dataset is the scarcity of labelled data. With increase of data there is cost fact effecting nature of servicing required for data (e.g., cost in terms of resource and time and effort is high for data annotation). Though data is analysed, it may be prone to error. Present disclosure provides systems/methods for reducing volume of data to be annotated for time series data thereby reducing time and effort of resources, thus resulting in effective utilization of system's resources (e.g., memory, processor, etc.). More specifically, the method of the present disclosure adaptively modifies the volume of the data to be annotated based on the performance of the unsupervised learning method applied in the system. Moreover, in the absence of an annotation mechanism for clusters of time series data, meta data associated with the time series data is utilized for annotation and validation of dataset.

Abstract: A system and a method of training a Neural network (NN) model may include, receiving a pretrained NN model, that may include a plurality of layers, each associated with an activation matrix; selecting at least one, and performing an iterative training process on the layer. The iterative training process may include, applying an activation threshold to the activation matrix of the layer; measuring an accuracy value of the NN model; retraining the layer, while using a bimodal regularization function of one or more activation matrices of the NN model; and repeating the applying, measuring and retraining, while each repetition uses different activation threshold values. This repetition may be repeated until a maximal value of the activation threshold, where the NN model still converges, is found.

Abstract: A control engine is trained to operate a robotic camera according to a variety of different cinematographic techniques. The control engine may reconfigure the robotic camera to respond to a set of cues, to enforce a set of constraints, or to apply one or more characteristic styles. A training engine trains a network within the control engine based on training data that exemplifies cue responses, enforced constraints, and characteristic styles.

Abstract: Systems, computer-implemented methods, and/or computer program products to facilitate updating, such as averaging and/or training, of one or more statistical sets are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a computing component that updates a first statistical set with an additional statistical set from an additional system. The additional statistical set can have been generated from a parent statistical set that is based on underlying data. To update the first statistical set, the additional statistical set can be obtained by the system without obtaining the parent statistical set and without obtaining the underlying data. According to an embodiment, the first statistical set can be a model parameter set generated from a first parent statistical set that is an analytical model.

Abstract: Embodiments described herein provide safe policy improvement (SPI) in a batch reinforcement learning framework for a task-oriented dialogue. Specifically, a batch reinforcement learning framework for dialogue policy learning is provided, which improves the performance of the dialogue and learns to shape a reward that reasons the invention behind human response rather than just imitating the human demonstration.