Abstract: A system comprises a network of computers comprising a master computer and slave computers. For a machine learning problem that is partitioned into a number of correlated sub-problems, each master computer is configured to store tasks associated with the machine learning problem, and each of the slave computers is assigned one of the correlated sub-problems. Each slave computer is configured to store variables or parameters or both associated with the assigned one of the correlated sub-problems; obtain information about one or more tasks stored by the master computer without causing conflict with other slave computers with regard to the information; perform computations to update the obtained information and the variables or parameters or both of the assigned sub-problem; send the updated information to the master computer to update the information stored at the master computer; and store the updated variables or parameters or both of the assigned sub-problem.

Abstract: A model building device and a loading disaggregation system are provided. The model building device disaggregates total aggregated data outputted from a total electricity meter and measured during a unit processing period. The model building device includes a usage pattern-analyzing module, an information mapping module, and a time series-analyzing module. After receiving the total aggregated data, the usage pattern-analyzing module analyzes the total aggregated data based on detection conditions and generates usage pattern information accordingly. The information mapping module maps the usage pattern information to form encoded data. The time series-analyzing module analyzes time correlation of the encoded data to generate synthesized simulation data.

Abstract: A “Content Optimizer” applies a machine-learned relevancy model to predict levels of interest for segments of arbitrary content. Arbitrary content includes, but is not limited to, any combination of documents including text, charts, images, speech, etc. Various automated reports and suggestions for “reformatting” segments to modify the predicted levels of interest may then be presented. Similarly, the Content Optimizer applies a machine-learned comprehension model to predict what a human audience is likely to understand (e.g., a “comprehension prediction”) from the arbitrary content. Various automated reports and suggestions for “reformatting” segments to modify the comprehension prediction may then be presented.

Abstract: Aspects of the present disclosure provide techniques for FAQ retrieval. Embodiments include receiving, via a user interface of a computing application, a query related to a subject. Embodiments include generating a first multi-dimensional representation of the query. Embodiments include obtaining a plurality of question and answer pairs related to the subject and, for a given question and answer pair comprising a given question and a given answer, generating a second multi-dimensional representation of the given question and a third multi-dimensional representation of the given answer. Embodiments include providing input to a model based on the first multi-dimensional representation, the second multi-dimensional representation, and the third multi-dimensional representation and determining a match score for the query and the given question and answer pair based on an output of the model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural programming. One of the methods includes processing a current neural network input using a core recurrent neural network to generate a neural network output; determining, from the neural network output, whether or not to end a currently invoked program and to return to a calling program from the set of programs; determining, from the neural network output, a next program to be called; determining, from the neural network output, contents of arguments to the next program to be called; receiving a representation of a current state of the environment; and generating a next neural network input from an embedding for the next program to be called and the representation of the current state of the environment.

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating data items. A method includes reading a glimpse from a data item using a decoder hidden state vector of a decoder for a preceding time step, providing, as input to a encoder, the glimpse and decoder hidden state vector for the preceding time step for processing, receiving, as output from the encoder, a generated encoder hidden state vector for the time step, generating a decoder input from the generated encoder hidden state vector, providing the decoder input to the decoder for processing, receiving, as output from the decoder, a generated a decoder hidden state vector for the time step, generating a neural network output update from the decoder hidden state vector for the time step, and combining the neural network output update with a current neural network output to generate an updated neural network output.

Abstract: A processing unit can train a model as a joint multi-domain recurrent neural network (JRNN), such as a bi-directional recurrent neural network (bRNN) and/or a recurrent neural network with long-short term memory (RNN-LSTM) for spoken language understanding (SLU). The processing unit can use the trained model to, e.g., jointly model slot filling, intent determination, and domain classification. The joint multi-domain model described herein can estimate a complete semantic frame per query, and the joint multi-domain model enables multi-task deep learning leveraging the data from multiple domains. The joint multi-domain recurrent neural network (JRNN) can leverage semantic intents (such as, finding or identifying, e.g., a domain specific goal) and slots (such as, dates, times, locations, subjects, etc.) across multiple domains.

Abstract: A system includes a memory having instructions therein and at least one processor in communication with the memory. The at least one processor is configured to execute the instructions to acquire phytomorphological field data via a sensor component of a mobile robot, generate, based on the phytomorphological field data and via a machine learning agent, a predicted likelihood of whether a hypothetical action by the mobile robot against a found plant would be directed against a true Toxicodendron plant, conduct a non-phytomorphological assessment of the found plant via the mobile robot and based on the predicted likelihood being below a first threshold and above a second threshold, and, via the mobile robot and based on the non-phytomorphological assessment, attack the found plant, mark a site of the found plant, and/or document a context of the site.

Abstract: Anomaly detection in computing environments is disclosed herein. An example method includes receiving an unstructured input stream of data instances from the computing environment, the unstructured input stream being time stamped; categorizing the data instances of the unstructured input stream of data instances, the data instances comprising at least one principle value and a set of categorical attributes determined through machine learning; generating anomaly scores for each of the data instances collected over a period of time; and detecting a change in the categorical attribute that is indicative of an anomaly.

Abstract: A convolution operation method and a processing device for performing the same are provided. The method is performed by a processing device. The processing device includes a main processing circuit and a plurality of basic processing circuits. The basic processing circuits are configured to perform convolution operation in parallel. The technical solutions disclosed by the present disclosure can provide short operation time and low energy consumption.

Abstract: In an example embodiment, a single machine learned model that allows for ranking of entities across all of the different combinations of node types and edge types is provided. The solution calibrates the scores from Edge-FPR models to a single scale. Additionally, the solution may utilize a per-edge type multiplicative factor dictated by the true importance of an edge type, which is learned through a counterfactual experimentation process. The solution may additionally optimize on a single, common downstream metric, specifically downstream interactions that can be compared against each other across all combinations of node types and edge types.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for balanced-weight sparse convolution processing. An exemplary method comprises: obtaining an input tensor and a plurality of filters at a layer within a neural network; segmenting the input tensor into a plurality of sub-tensors; dividing a channel dimension of each of the plurality of filters into a plurality of channel groups; pruning each of the plurality of filters so that each of the plurality of channel groups of each filter comprises a same number of non-zero weights; segmenting each of the plurality of filters into a plurality of the sub-filters according to the plurality of channel groups; and assigning the plurality of sub-tensors and the plurality of sub-filters to a plurality of processors for parallel convolution processing.

Abstract: The systems, methods, and computer program products for determining bins for a data model are provided. Variables in a training data set are binned into bins up to a configurable number of bins. Variables in the validation data set are also binned using the bins from the training data set. A first decision tree is generated using the bins and the binned variables from the training data set and is pruned. A second decision tree is generated using the structure of the first decision tree and the binned variables from the validation data set. The first and second decision tree are merged into a third decision tree. Leaf nodes of the third decision tree are sorted and merged until weights of evidence associated with the training data set and the validation data set are monotonic. The bins for the data model are determined from the merged leaf nodes.

Abstract: Systems and methods for automated evaluation system routing are described herein. The system can include a memory, which can include a model database and a correlation database. The system can include a first user device and a second user device. The system can include at least one server. The at least one server can: receive a response communication from the user device; generate an initial evaluation value according to an AI model; determine a correlation between the initial evaluation value and evaluation range data; accept the initial evaluation value when the correlation exceeds a threshold value; and route the response communication to the second user device for generation of an elevated evaluation value when the correlation does not exceed the threshold value.

Abstract: A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

Abstract: A resistive processing unit (RPU) that includes a pair of transistors connected in series providing an update function for a weight of a training methodology to the RPU, and a read transistor for reading the weight of the training methodology. In some embodiments, the resistive processing unit (RPU) further includes a capacitor connecting a gate of the read transistor to the air of transistors providing the update function for the resistive processing unit (RPU). The capacitor stores said weight of training methodology for the RPU.

Abstract: A system includes a processor for performing one or more autonomous driving or assisted driving tasks based on a neural network. The neural network includes a base portion for performing feature extraction simultaneously for a plurality of tasks on a single set of input data. The neural network includes a plurality of subtask portions for performing the plurality of tasks based on feature extraction output from the base portion. Each of the plurality of subtask portions comprise nodes or layers of a neutral network trained on different sets of training data, and the base portion comprises nodes or layers of a neural network trained using each of the different sets of training data constrained by elastic weight consolidation to limit the base portion from forgetting a previously learned task.

Abstract: A method includes generating a base model by training with a first dataset of data pairs and generating an adapted model by training the base model on a second dataset of data pairs. The method also includes determining a contrastive score for each data pair of a third dataset of data pairs using the base model and the adapted model. The contrastive score is indicative of a probability of quality of the respective data pair. The method also includes training a target model using the data pairs of the third dataset and the contrastive scores.

Abstract: Certain aspects involve optimizing neural networks or other models for assessing risks and generating explanatory data regarding predictor variables used in the model. In one example, a system identifies predictor variables. The system generates a neural network for determining a relationship between each predictor variable and a risk indicator. The system performs a factor analysis on the predictor variables to determine common factors. The system iteratively adjusts the neural network so that (i) a monotonic relationship exists between each common factor and the risk indicator and (ii) a respective variance inflation factor for each common factor is sufficiently low. Each variance inflation factor indicates multicollinearity among the common factors. The adjusted neural network can be used to generate explanatory indicating relationships between (i) changes in the risk indicator and (ii) changes in at least some common factors.

Abstract: Neuromorphic methods, systems and devices are provided. The embodiment may include a neuromorphic device which may comprise a crossbar array structure and an analog circuit. The crossbar array structure may include N input lines and M output lines interconnected at junctions via N×M electronic devices, which, in preferred embodiments, include, each, a memristive device. The input lines may comprise N1 first input lines and N2 second input lines. The first input lines may be connected to the M output lines via N1×M first devices of said electronic devices. Similarly, the second input lines may be connected to the M output lines via N2×M second devices of said electronic devices. The analog circuit may be configured to program the electronic devices so as for the first devices to store synaptic weights and the second devices to store neuronal states.