Abstract: Systems, methods, and apparatuses for providing dynamic, prioritized spectrum utilization management. The system includes at least one monitoring sensor, at least one data analysis engine, at least one application, a semantic engine, a programmable rules and policy editor, a tip and cue server, and/or a control panel. The tip and cue server is operable utilize the environmental awareness from the data processed by the at least one data analysis engine in combination with additional information to create actionable data.

Abstract: Systems, methods, and computer program products for predicting user preference of items in an image process image data associated with a single image with a first branch of a neural network to produce an image embedding, the single image including a set of multiple items; process a user identifier of a user with a second branch of the neural network to produce a user embedding; concatenate the image embedding with the user embedding to produce a concatenated embedding; process the concatenated embedding with the neural network to produce a joint embedding; and generate a user preference score for the set of multiple items from the neural network based on the joint embedding, the user preference score including a prediction of whether the user prefers the set of multiple items.

Abstract: A copy of a model comprising a plurality of trees is received, as is a copy of training set data comprising a plurality of training set examples. For each tree included in the plurality of trees, the training set data is used to determine which training set examples are classified as a given leaf. A blame forest is generated at least in part by mapping each training set item to the respective leaves at which it arrives.

Abstract: Embodiments of a method are disclosed. The method includes performing distributed deep learning training on multiple batches of training data using corresponding learners. Additionally, the method includes determining training times wherein the learners perform the distributed deep learning training on the batches of training data. The method also includes modifying a processing aspect of the straggler to reduce a future training time of the straggler for performing the distributed deep learning training on a new batch of training data in response to identifying a straggler of the learners by a centralized control.

Abstract: In order to facilitate the entity resolution and entity activity tracking and indexing, systems and methods include receiving first source records from a first database and second source records from a record database. A candidate set of second source records is determined by a heuristic search in the set of second source records. A candidate pair feature vector associated with each candidate pair of first and second source records is generated. An entity matching machine learning model predicts matching first source records for each candidate second source record based on the respective candidate pair feature vector. An aggregate quantity associated with the matching first source records is aggregated from a quantity associated with each first source record, and a quantity index for each candidate second source record is determined based the aggregate quantities. Each quantity index is displayed to a user.

Abstract: A system and method may partition and/or execute a NN, by, for a graph including nodes and hyper edges, each node representing a data item in the NN and each hyper edge representing an operation in the NN, identifying a deep tensor column comprising a subset of the nodes and a subset of the hyper edges, such that the operations in the deep tensor column, when executed, use only data which fits within a preselected cache.

Abstract: A method for accelerating machine learning on a computing device is described. The method includes hosting a neural network in a first inference accelerator and a second inference accelerator. The neural network split between the first inference accelerator and the second inference accelerator. The method also includes routing intermediate inference request results directly between the first inference accelerator and the second inference accelerator. The method further includes generating a final inference request result from the intermediate inference request results.

Abstract: Embodiments are directed to a composite binary decomposition network. An embodiment of a computer-readable storage medium includes executable computer program instructions for transforming a pre-trained first neural network into a binary neural network by processing layers of the first neural network in a composite binary decomposition process, where the first neural network having floating point values representing weights of various layers of the first neural network. The composite binary decomposition process includes a composite operation to expand real matrices or tensors into a plurality of binary matrices or tensors, and a decompose operation to decompose one or more binary matrices or tensors of the plurality of binary matrices or tensors into multiple lower rank binary matrices or tensors.

Abstract: Systems and methods are described for facilitating operation of a plurality of computing devices. Data indicative of enumerated resources of a computing device is collected. The data is collected without dependency on write permissions to a file system of the one computing device. A condition of the computing device is determined based on historical data associated with enumerated resources of other computing devices. The identified condition can be updated as updated historical data becomes available. A communication to the computing device may be sent based on the identified condition.

Abstract: The present disclosure is directed to an automated neural architecture search approach for designing new neural network architectures such as, for example, resource-constrained mobile CNN models. In particular, the present disclosure provides systems and methods to perform neural architecture search using a novel factorized hierarchical search space that permits layer diversity throughout the network, thereby striking the right balance between flexibility and search space size. The resulting neural architectures are able to be run relatively faster and using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art mobile-optimized models.

Abstract: Systems, methods, and apparatuses for providing dynamic, prioritized spectrum utilization management. The system includes at least one monitoring sensor, at least one data analysis engine, at least one application, a semantic engine, a programmable rules and policy editor, a tip and cue server, and/or a control panel. The tip and cue server is operable utilize the environmental awareness from the data processed by the at least one data analysis engine in combination with additional information to create actionable data.

Abstract: Embodiments described herein disclose methods and systems for using more than one Recurrent Neural Network (RNN) to analyze a user input and to predict a request being made by the user as the user is inputting the request. In an embodiment, a first RNN and a second RNN can simultaneously or near simultaneously process the user requested information by separating and analyzing the characters and words in the user's request. A third RNN can process the output vectors generated by the first and second RNNs to identify one or more solutions that predict the user's request.

Abstract: Systems and methods are described for training a machine learning model using intelligently selected multiclass vectors. According to an embodiment, a set of un-labeled feature vectors are received. The set of feature vectors are grouped into clusters within a vector space having fewer dimensions than the first set of feature vectors by applying a homomorphic dimensionality reduction algorithm to the set of feature vectors and performing centroid-based clustering. An optimal set of clusters among the clusters is identified by performing a convex optimization process on the clusters. Vector labeling is minimized by selecting ground truth representative vectors including a representative vector from each cluster of the optimal set of clusters. A set of labeled feature vectors is created based on labels received from an oracle for each of the representative vectors. A machine-learning model is trained for multiclass classification based on the set of labeled feature vectors.

Abstract: Certain aspects of the present disclosure provide techniques for predicting activity within a software application using a machine learning model. An example method generally includes generating a multidimensional time-series data set from time-series data associated with activity within a software application. The multidimensional time-series data set generally includes the time-series data organized based on a plurality of time granularities. Using a machine learning model and the generated multidimensional time-series data set, activity within the software application is predicted for one or more time granularities of the plurality of time granularities. Computing resources are allocated to execute operations using the software application based on the predicted activity within the software application.

Abstract: In one embodiment, a computing device includes an input sensor providing an input data; a programmable logic device (PLD) implementing a convolutional neural network (CNN), wherein: each compute block of the PLD corresponds to one of a multiple of convolutional layers of the CNN, each compute block of the PLD is placed in proximity to at least two memory blocks, a first one of the memory blocks serves as a buffer for the corresponding layer of the CNN, and a second one of the memory blocks stores model-specific parameters for the corresponding layer of the CNN.

Abstract: An apparatus for an apparatus for modular completion of a pecuniary-related activity is disclosed. The apparatus includes at least a processor; and a memory communicatively connected to the at least a processor. The memory containing instructions configuring the at least a processor to receive a user profile from a user for a pecuniary-related activity, the user profile having at least a user target, obtain a plurality of pecuniary approach blocks, select at least one pecuniary approach block from the plurality of pecuniary approach blocks as a function of the user profile and generate at least one pecuniary plan as a function of the at least one pecuniary approach block and the user profile. Apparatus further includes a user interface communicatively connected to the processor, the user interface configured to display the at least one pecuniary plan.

Abstract: Methods, apparatus, and processor-readable storage media for correlating data center resources in a multi-tenant execution environment using machine learning techniques are provided herein. An example computer-implemented method includes obtaining multiple data streams pertaining to one or more data center resources in at least one multi-tenant executing environment; correlating one or more portions of the multiple data streams by processing at least a portion of the multiple data streams using at least one multi-tenant-capable search engine; determining one or more anomalies within the multiple data streams by processing the one or more correlated portions of the multiple data streams using a machine learning-based anomaly detection engine; and performing at least one automated action based at least in part on the one or more determined anomalies.

Abstract: Data for processing by a machine learning model may be prepared by encoding a first portion of the data including a spatial data. The spatial data may include a spatial coordinate including one or more values identifying a geographical location. The encoding of the first portion of the data may include mapping, to a cell in a grid system, the spatial coordinate such that the spatial coordinate is represented by an identifier of the cell instead of the one or more values. The data may be further prepared by embedding a second portion of the data including textual data, preparing a third portion of the data including hierarchical data, and/or preparing a fourth portion of the data including numerical data. The machine learning model may be applied to the prepared data in order to train, validate, test, and/or deploy the machine learning model to perform a cognitive task.

Abstract: Embodiments of the present disclosure include systems and methods for reducing hardware resource utilization by residual neural networks. In some embodiments, a first matrix is received at a layer included in a neural network. The first matrix is compressed to produce a second matrix. The second matrix has a reduced dimensionality relative to a dimensionality of the first matrix. The second matrix is processed through a network block in the layer included in the neural network. The processed second matrix is expanded to produce a third matrix. The third matrix has a dimensionality that is equal to a dimensionality of the first matrix. The third matrix is added to the first matrix to produce a fourth matrix.

Abstract: The invention proposes a method of training a convolutional neural network in which, at each convolution layer, weights for one seed convolutional filter per layer are updated during each training iteration. All other convolutional filters are polynomial transformations of the seed filter, or, alternatively, all response maps are polynomial transformations of the response map generated by the seed filter.