Abstract: A video camera is provided for video-based anomaly detection that includes at least one imaging sensor configured to capture video sequences in a workplace environment having a plurality of machines therein. The video camera further includes a processor. The processor is configured to generate one or more predictions of an impending anomaly affecting at least one item selected from the group consisting of (i) at least one of the plurality of machines and (ii) at least one operator of the at least one of the plurality of machines, using a Deep High-Order Convolutional Neural Network (DHOCNN)-based model applied to the video sequences. The DHOCNN-based model has a one-class SVM as a loss layer of the model. The processor is further configured to generate a signal for initiating an action to the at least one of the plurality of machines to mitigate expected harm to the at least one item.

Abstract: A video monitoring system and method are provided. The video monitoring system includes a camera. The camera is positioned to monitor an area and capture live video to provide a live video stream. The video monitoring system also includes a security processing system. The security processing system includes a processor and memory coupled to the processor. The security processing system is programmed to detect and identify a target action sequence in the live video stream using a multi-layer deep long short-term memory process on are attention factor that is based on an within-frame attention and an between-frame attention. The security processing system is further programmed to trigger an action to alert that a target action sequence has been detected.

Abstract: A method, a computer program product, and a system are provided for video based action recognition. The system includes a processor. One or more frames from one or more video sequences are received. A feature vector for each patch of the one w more frames is generated using a deep convolutional neural network. An attention factor for the feature vectors is generated based on a within-frame attention and a between-frame attention. A target action is identified using a multi-layer deep long short-term memory process applied to the attention factor, said target action representing at least one of the one or more video sequences.

Abstract: A system and method are provided for deep high-order exemplar learning of a data set. Feature vectors and class labels are received. Each of the feature vectors represents a respective one of a plurality of high-dimensional data points of the data set. The class labels represent classes for the high-dimensional data points. Each of the feature vectors are processed, using a deep high-order convolutional neural network, to obtain respective low-dimensional embedding vectors within each class. A minimization operation is performed on high-order embedding parameters of the high-dimensional data points to output a set of synthetic exemplars. A binarizing operation is performed on the low-dimensional embedding vectors and the set of synthetic exemplars to output hash codes representing the data set. The hash codes are utilized as a search key to increase the efficiency of a processor-based machine searching the data set.

Abstract: Mobile phones and methods for mobile phone failure prediction include receiving respective log files from one or more mobile phone components, including at least one user application. The log files have heterogeneous formats. A likelihood of failure of one or more mobile phone components is determined based on the received log files by clustering the plurality of log files according to structural log patterns and determining feature representations of the log files based on the log clusters. A user is alerted to a potential failure if the likelihood of component failure exceeds a first threshold. An automatic system control action is performed if the likelihood of component failure exceeds a second threshold.

Abstract: Methods for system failure prediction include clustering log files according to structural log patterns. Feature representations of the log files are determined based on the log clusters. A likelihood of a system failure is determined based on the feature representations using a neural network. An automatic system control action is performed if the likelihood of system failure exceeds a threshold.

Abstract: A computer-implemented method and system are provided for video-based anomaly detection. The method includes forming, by a processor, a Deep High-Order Convolutional Neural Network (DHOCNN)-based model having a one-class Support Vector Machine (SVM) as a loss layer of the DHOCNN-based model. An objective of the SVM is configured to perform the video-based anomaly detection. The method further includes generating, by the processor, one or more predictions of an impending anomaly based on the high-order deep learning based model applied to an input image. The method also includes initiating, by the processor, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

Abstract: A video camera is provided for video-based anomaly detection that includes at least one imaging sensor configured to capture video sequences in a workplace environment having a plurality of machines therein. The video camera further includes a processor. The processor is configured to generate one or more predictions of an impending anomaly affecting at least one item selected from the group consisting of (i) at least one of the plurality of machines and (ii) at least one operator of the at least one of the plurality of machines, using a Deep High-Order Convolutional Neural Network (DHOCNN)-based model applied to the video sequences. The DHOCNN-based model has a one-class SVM as a loss layer of the model. The processor is further configured to generate a signal for initiating an action to the at least one of the plurality of machines to mitigate expected harm to the at least one item.

Abstract: A computer-implemented method and a system are provided for, in turn, providing driver assistance for a vehicle. The method includes forming, by a processor, a deep High-Order Long Short-Term Memory (HOLSTM)-based model by applying, to a HOLSTM, high-order interactions captured between global pattern distribution probabilities and local feature representations of an input sensor signal vector at each of a plurality of time steps. The input sensor signal vector is formed from multiple time series. Each of the multiple time series corresponds to a different one of a plurality of driving related sensors. The method further includes generating, by the processor, one or more predictions of impending dangerous conditions related to driving the vehicle based on the deep HOLSTM-based model. The method also includes informing, by an operator-perceptable warning device, an operator of the vehicle of the one or more predictions of impending dangerous conditions.

Abstract: A method is provided for scalable supervised high-order parametric embedding for big data visualization. The method is performed by a processor and includes receiving feature vectors and class labels. Each feature vector is representative of a respective one of a plurality of high-dimensional data points. The class labels denote classes for the high-dimensional data points. The method further includes multiplying each feature vector by one or more factorized high-order tensors to obtain respective product vectors. The method also includes performing a maximally collapsing metric learning on the product vectors using learned synthetic exemplars and learned high-order filters. The learned high-order filters represent high-order embedding parameters.

Abstract: Aspects of the present disclosure describe techniques for training a convolutional neural network using an inconsistent stochastic gradient descent (ISGD) algorithm. Training effort for training batches used by the ISGD algorithm are dynamically adjusted according to a determined loss for a given training batch which are classified into two sub states—well-trained or under-trained. The ISGD algorithm provides more iterations for under-trained batches while reducing iterations for well-trained ones.

Abstract: Methods and systems for training a neural network include sampling multiple local sub-networks from a global neural network. The local sub-networks include a subset of neurons from each layer of the global neural network. The plurality of local sub-networks are trained at respective local processing devices to produce trained local parameters. The trained local parameters from each local sub-network are averaged to produce trained global parameters.

Abstract: A network device, system, and method are provided. The network device includes a processor. The processor is configured to store a local estimate and a dual variable maintaining an accumulated subgradient for the network device. The processor is further configured to collect values of the dual variable of neighboring network devices. The processor is also configured to form a convex combination with equal weight from the collected dual variable of neighboring network devices. The processor is additionally configured to add a most recent local subgradient for the network device, scaled by a scaling factor, to the convex combination to obtain an updated dual variable. The processor is further configured to update the local estimate by projecting the updated dual variable to a primal space.

Abstract: Systems and methods are disclosed for operating a Restricted Boltzmann Machine (RBM) by determining a corrected energy function of high-order semi-RBMs (hs-RBMs) without self-interaction; performing distributed pre-training of the hs-RBM; adjusting weights of the hs-RBM using contrastive divergence; generating predictions by Gibbs Sampling or by determining conditional probabilities with hidden units integrated out; and generating predictions.

Abstract: Systems and methods are disclosed for operating a machine, by receiving training data from one or more sensors; training a machine learning module with the training data by: partitioning a data matrix into smaller submatrices to process in parallel and optimized for each processing node; for each submatrix, performing a greedy search for rank-one solutions; using alternating direction method of multipliers (ADMM) to ensure consistency over different data blocks; and controlling one or more actuators using live data and the learned module during operation.

Abstract: An optimization-driven sparse learning framework is disclosed to identify discriminative system components among system input features that are essential for system output prediction. In biomarker discovery, to handle the combinatorial interactions among gene or protein expression measurements for identifying interaction complexes and disease biomarkers, the system uses both single input features and high-order input feature interactions.

Abstract: System and methods are disclosed to perform peptide-MHC interaction prediction by applying a high-order kernel function to determine a similarity between peptide sequences; applying one or more supervised strategies to the kernel to encode relevant physicochemical and interaction information about peptide sequence and MHC molecule; and applying a classifier to the kernel to identify the peptide-MHC interaction of interest in response to a query.

Abstract: Methods and systems for training a neural network include pre-training a bi-linear, tensor-based network, separately pre-training an auto-encoder, and training the bi-linear, tensor-based network and auto-encoder jointly. Pre-training the bi-linear, tensor-based network includes calculating high-order interactions between an input and a transformation to determine a preliminary network output and minimizing a loss function to pre-train network parameters. Pre-training the auto-encoder includes calculating high-order interactions of a corrupted real network output, determining an auto-encoder output using high-order interactions of the corrupted real network output, and minimizing a loss function to pre-train auto-encoder parameters.

Abstract: Systems and methods are provided for identifying combinatorial feature interactions, including capturing statistical dependencies between categorical variables, with the statistical dependencies being stored in a computer readable storage medium. A model is selected based on the statistical dependencies using a neighborhood estimation strategy, with the neighborhood estimation strategy including generating sets of arbitrarily high-order feature interactions using at least one rule forest and optimizing one or more likelihood functions. A damped mean-field approach is applied to the model to obtain parameters of a Markov random field (MRF); a sparse high-order semi-restricted MRF is produced by adding a hidden layer to the MRF; indirect long-range dependencies between feature groups are modeled using the sparse high-order semi-restricted MRF; and a combinatorial dependency structure between variables is output.

Abstract: A method for peptide binding prediction includes receiving a peptide sequence descriptor and descriptors of contacting amino acids on major histocompatibility complex (MHC) protein-peptide interaction structure; generating a model with an ensemble of high order neural network; pre-training the model by high order semi-restricted Boltzmann machine (RBM) or high-order denoising autoencoder; and generating a prediction as a binary output or continuous output with initial model parameters pre-trained using binary output data if available. A systematic learning method for leveraging high-order interactions/associations among items for better collaborative filtering and item recommendation.