Abstract: In one example, a method includes receiving, by a computing system, context information associated with a computing device; inferring, by the computing system and based on the context information, an action of a user of the computing device, the action associated with at least one entity; determining, by the computing system and based on stored attribute information associated with the at least one entity, and based on a stored set of rules associated with the inferred action, that the inferred action is not advisable; and responsive to determining that the inferred action is not advisable, outputting, by the computing system and for display on the computing device, notification data indicating that the inferred action is not advisable.

Abstract: Disclosed is a system, method, and computer program product for implementing a log analytics method and system that can configure, collect, and analyze log records in an efficient manner. Machine learning-based classification can be performed to classify logs. This approach is used to group logs automatically using a machine learning infrastructure.

Abstract: It is disclosed a method comprising obtaining a target spectrum, obtaining a set of non-target spectra, the set of non-target spectra comprising one or more non-target spectra, summing the target spectrum and the set of non-target spectra to obtain a mixture spectrum, and training an artificial neural network by using the mixture spectrum as input of the neural network and by using a spectrum which is based on the target spectrum as desired output of the artificial neural network.

Abstract: There is a need for more effective and efficient predictive data analysis. Various embodiments of the present invention address one or more of the noted technical challenges. In one example, a method for generating a neutralized prediction model includes accessing an initial prediction model generated using an initial training data object, performing a randomized shuffling of the initial training data object to generate a shuffled training data object, generating randomized predictions by processing the shuffled training data object using the initial prediction model, performing a neutralization of the initial training data object to generate a neutralized training data object, and generating the neutralized prediction model based at least in part on the neutralized training data object and the randomized predictions.

Abstract: A function creation method is disclosed. The method comprises defining one or more database function inputs, defining cluster processing information, defining a deep learning model, and defining one or more database function outputs. A database function is created based at least in part on the one or more database function inputs, the cluster set-up information, the deep learning model, and the one or more database function outputs. In some embodiments, the database function enables a non-technical user to utilize deep learning models.

Abstract: Systems, methods, and apparatuses related to cooperative learning neural networks are described. Cooperative learning neural networks may include neural networks which utilize sensor data received wirelessly from at least one other wireless communication device to train the neural network. For example, cooperative learning neural networks described herein may be used to develop weights which are associated with objects or conditions at one device and which may be transmitted to a second device, where they may be used to train the second device to react to such objects or conditions. The disclosed features may be used in various contexts, including machine-type communication, machine-to-machine communication, device-to-device communication, and the like. The disclosed techniques may be employed in a wireless (e.g., cellular) communication system, which may operate according to various standardized protocols.

Abstract: Systems, methods, and apparatuses related to cooperative learning neural networks are described. Cooperative learning neural networks may include neural networks which utilize sensor data received wirelessly from at least one other wireless communication device to train the neural network. For example, cooperative learning neural networks described herein may be used to develop weights which are associated with objects or conditions at one device and which may be transmitted to a second device, where they may be used to train the second device to react to such objects or conditions. The disclosed features may be used in various contexts, including machine-type communication, machine-to-machine communication, device-to-device communication, and the like. The disclosed techniques may be employed in a wireless (e.g., cellular) communication system, which may operate according to various standardized protocols.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage medium, for training a neural network, wherein the neural network is configured to receive an input data item and to process the input data item to generate a respective score for each label in a predetermined set of multiple labels. The method includes actions of obtaining a set of training data that includes a plurality of training items, wherein each training item is associated with a respective label from the predetermined set of multiple labels; and modifying the training data to generate regularizing training data, comprising: for each training item, determining whether to modify the label associated with the training item, and changing the label associated with the training item to a different label from the predetermined set of labels, and training the neural network on the regularizing data.

Abstract: A method for monitoring performance of a ML system includes receiving a data stream via a processor and generating a first plurality of metrics based on the data stream. The processor also generates input data based on the data stream, and sends the input data to a machine learning (ML) model for generation of intermediate output and model output based on the input data. The processor also generates a second plurality of metrics based on the intermediate output, and a third plurality of metrics based on the model output. An alert is generated based on at least one of the first plurality of metrics, the second plurality of metrics, or the third plurality of metrics, and a signal representing the alert is sent for display to a user via an interface.

Abstract: An automatic seismic facies identification method based on combination of Self-Attention mechanism and U-shape network architecture, including: obtaining and preprocessing post-stack seismic data to construct a sample training and validation dataset; building an encoder through an overlapped patch merging module with down-sampling function and a self-attention transformer module with global modeling function; building a decoder through a patch expanding module with linear upsampling function, the self-attention transformer module, and a skip connection module with multilayer feature fusion function; building a seismic facies identification model using the encoder, the decoder, and a Hypercolumn module, where the seismic facies identification model includes a Hypercolumns-U-Segformer (HUSeg); and building a hybrid loss function; iteratively training the seismic facies identification model with a training and validation set; and inputting test data into a trained identification model to obtain seismic facies co

Abstract: Systems, methods and apparatus for generating music recommendations based on combining song and user influencers with channel rule characterizations are presented. Such systems and methods output a playlist, which may be delivered as an information stream of audio on a user or client device, such as a telephone or smartphone, tablet, computer or MP3 player, or any consumer device with audio play capabilities. The playlist may comprise various individual audio clips of one genre or type, such as songs, or of multiple types, such as music, talk, sports and comedy. The individual audio clips may be ordered by a sequencer, which, using large amounts of data, generates both (i) user independent and (i) user dependent influencer weightings for each clip, and then combines all of such influencer weightings into a combined play weighting W for a given audio clip, for a given user.

Abstract: A system and method for emotion-enhanced natural speech using dilated convolutional neural networks, wherein an audio processing server receives a raw audio waveform from a dilated convolutional artificial neural network, associates text-based emotion content markers with portions of the raw audio waveform to produce an emotion-enhanced audio waveform, and provides the emotion-enhanced audio waveform to the dilated convolutional artificial neural network for use as a new input data set.

Abstract: An electronic device may determine whether a machine-learning model is operating within predefined limits. In particular, the electronic device may receive, from another electronic device, instructions for the machine-learning model, a reference input and a predetermined output of the machine-learning model for the reference input. Note that the instructions may include an architecture of the machine-learning model, weights associated with the machine-learning model and/or a set of pre-processing transformations for use when executing the machine-learning model on images. In response, the electronic device may configure the machine-learning model based on the instructions. Then, the electronic device may calculate an output of the machine-learning model for the reference input. Next, the electronic device may determine whether the machine-learning model is operating within predefined limits based on the output and the predetermined output.

Abstract: In some examples, machine learning based semantic structural hole identification may include mapping each text element of a plurality of text elements of a corpus into an embedding space that includes embeddings that are represented as vectors. A semantic network may be generated based on semantic relatedness between each pair of vectors. A boundary enclosure of the embedding space may be determined, and points to fill the boundary enclosure may be generated. Based on an analysis of voidness for each point within the boundary enclosure, a set of void points and void regions may be identified. Semantic holes may be identified for each void region, and utilized to determine semantic porosity of the corpus. A performance impact may be determined between utilization of the corpus to generate an application by using the text elements without filling the semantic holes and the text elements with the semantic holes filled.

Abstract: A growth transform neural network system is disclosed that includes a computing device with at least one processor and a memory storing a plurality of modules, including a growth transform neural network module, a growth transform module, and a network convergence module. The growth transform neural network module defines a plurality of mirrored neuron pairs that include a plurality of first components and a plurality of second components. Each first and second component is connected by a normalization link. The first components are interconnected according to an interconnection matrix, and the second components are interconnected according to the interconnection matrix. The growth transform module updates each first component of each mirrored neuron pair according to a growth transform neuron model. The network convergence module converges the plurality of mirrored neuron pairs to a steady state condition by solving a system objective function subject to at least one normalization constraint.

Abstract: According to an aspect of the present invention, a computer-implemented method is provided for reinforcement learning. The method includes reading, by a processor device, an action manifold which is described as a n-polytope, at least one physical action limit, and at least one safety constraint. The method further includes updating, by the processor device, the action manifold based on the at least one physical action limit and the at least one safety constraint. The method also includes performing, by the processor device, the reinforcement learning by selecting a constrained action from among a set of constrained actions in the action manifold.

Abstract: Embodiments of the present invention provide an automated image tagging system that can predict a set of tags, along with relevance scores, that can be used for keyword-based image retrieval, image tag proposal, and image tag auto-completion based on user input. Initially, during training, a clustering technique is utilized to reduce cluster imbalance in the data that is input into a convolutional neural network (CNN) for training feature data. In embodiments, the clustering technique can also be utilized to compute data point similarity that can be utilized for tag propagation (to tag untagged images). During testing, a diversity based voting framework is utilized to overcome user tagging biases. In some embodiments, bigram re-weighting can down-weight a keyword that is likely to be part of a bigram based on a predicted tag set.

Abstract: The present disclosure provides computing systems and methods directed to algorithms and the underlying machine learning (ML) models for evaluating similarity between graphs using graph structures and/or attributes. The systems and methods disclosed may provide advantages or improvements for comparing graphs without additional context or input from a person (e.g., the methods are unsupervised). In particular, the systems and methods of the present disclosure can operate to generate respective embeddings for one or more target graphs, where the embedding for each target graph is indicative of a respective similarity of such target graph to each of a set of source graphs, and where a pair of embeddings for a pair of target graphs can be used to assess a similarity between the pair of target graphs.

Abstract: A system and method for training base classifiers in a boosting algorithm includes optimally training base classifiers considering an unreliability model, and then using a scheme with an aggregator decoder that reverse-flips inputs using inter-classifier redundancy introduced in training.

Abstract: A quantum prediction AI system includes a quantum prediction circuit adapted to receive an input vector representing a subset of a time-sequential sequence; encode the input vector as a corresponding qubit register; apply a trained quantum circuit to the qubit register; and measure one or more qubits output from the quantum prediction circuit to infer a next data point in the series following the subset represented by the input vector.