Abstract: A false alarm reduction system is provided that includes a processor cropping each input image at randomly chosen positions to form cropped images of a same size at different scales in different contexts. The system further includes a CONDA-GMM, having a first and a second conditional deep autoencoder for respectively (i) taking each cropped image without a respective center block as input for measuring a discrepancy between a reconstructed and a target center block, and (ii) taking an entirety of cropped images with the target center block. The CONDA-GMM constructs density estimates based on reconstruction error features and low-dimensional embedding representations derived from image encodings. The processor determines an anomaly existence based on a prediction of a likelihood of the anomaly existing in a framework of a CGMM, given the context being a representation of the cropped image with the center block removed and having a discrepancy above a threshold.

Abstract: A system is provided for video captioning. The system includes a processor. The processor is configured to apply a three-dimensional Convolutional Neural Network (C3D) to image frames of a video sequence to obtain, for the video sequence, (i) intermediate feature representations across L convolutional layers and (ii) top-layer features. The processor is further configured to produce a first word of an output caption for the video sequence by applying the top-layer features to a Long Short Term Memory (LSTM). The processor is further configured to produce subsequent words of the output caption by (i) dynamically performing spatiotemporal attention and layer attention using the intermediate feature representations to form a context vector, and (ii) applying the LSTM to the context vector, a previous word of the output caption, and a hidden state of the LSTM. The system further includes a display device for displaying the output caption to a user.

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: 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 or 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. An operation of a processor-based machine is controlled to change a state of the processor-based machine, responsive to the at least one of the one or more video sequences including the identified target action.

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 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 for predicting new relationships in the knowledge graph, including embedding a partial triplet including a head entity description and a relationship or a tail entity description to produce a separate vector for each of the head, relationship, and tail. The vectors for the head entity, relationship, and tail entity can be combined into a first matrix, and adaptive kernels generated from the entity descriptions can be applied to the matrix through convolutions to produce a second matrix having a different dimension from the first matrix. An activation function can be applied to the second matrix to obtain non-negative feature maps, and max-pooling can be used over the feature maps to get subsamples. A fixed length vector, Z, flattens the subsampling feature maps into a feature vector, and a linear mapping method is used to map the feature vectors into a prediction score.

Abstract: A computer-implemented method, computer program product, and computer processing system are provided for word embedding. The method includes receiving, by a processor device, a word embedding matrix. The method further includes generating, by a processor device, an average pooling vector and a max pooling vector, based on the word embedding matrix. The method also includes generating, by the processor device, a prediction by applying a Multi-Layer Perceptron (MLP) to the average pooling vector and the max pooling vector.

Abstract: A system for electronic message classification and delivery using a neural network architecture includes one or more computing devices associated with one or more users, and at least one computer processing system in communication with one or more computing devices over at least one network. The at least one computer processing system includes at least one processor operatively coupled to a memory device and configured to execute program code stored on the memory device to receive one or more inputs associated with one or more e-mails corresponding to the one or more users across the at least one network, classify the one or more e-mails by performing natural language processing based on one or more sets of filters conditioned on respective ones of the one or more inputs, and permit the one or more users access to the one or more classified e-mails via the one or more computing devices.

Abstract: A computer-implemented method for employing input-conditioned filters to perform natural language processing tasks using a convolutional neural network architecture includes receiving one or more inputs, generating one or more sets of filters conditioned on respective ones of the one or more inputs by implementing one or more encoders to encode the one or more inputs into one or more respective hidden vectors, and implementing one or more decoders to determine the one or more sets of filters based on the one or more hidden vectors, and performing adaptive convolution by applying the one or more sets of filters to respective ones of the one or more inputs to generate one or more representations.

Abstract: A system is provided for video captioning. The system includes a processor. The processor is configured to apply a three-dimensional Convolutional Neural Network (C3D) to image frames of a video sequence to obtain, for the video sequence, (i) intermediate feature representations across L convolutional layers and (ii) top-layer features. The processor is further configured to produce a first word of an output caption for the video sequence by applying the top-layer features to a Long Short Term Memory (LSTM). The processor is further configured to produce subsequent words of the output caption by (i) dynamically performing spatiotemporal attention and layer attention using the intermediate feature representations to form a context vector, and (ii) applying the LSTM to the context vector, a previous word of the output caption, and a hidden state of the LSTM. The system further includes a display device for displaying the output caption to a user.

Abstract: A surveillance system is provided that includes an image capture device configured to capture a video sequence of a target area that includes objects and is formed from a set of image frames. The system further includes a processor configured to apply a C3D to the image frames to obtain therefor (i) intermediate feature representations across L convolutional layers and (ii) top-layer features. The processor is further configured to produce a first word of a caption for the sequence by applying the top-layer features to a LSTM. The processor is further configured to produce subsequent words of the caption by (i) dynamically performing spatiotemporal attention and layer attention using the intermediate feature representations to form a context vector, and (ii) applying the LSTM to the context vector, a previous word of the caption, and a hidden state of the LSTM. The system includes a display device for displaying the caption.

Abstract: A video retrieval system is provided, that includes a set of servers, configured to retrieve a video sequence from a database and forward it to a requesting device responsive to a match between an input text and a caption for the video sequence. The servers are further configured to translate the video sequence into the caption by (A) applying a C3D to image frames of the video sequence to obtain therefor (i) intermediate feature representations across L convolutional layers and (ii) top-layer features, (B) producing a first word of the caption for the video sequence by applying the top-layer features to a LSTM, and (C) producing subsequent words of the caption by (i) dynamically performing spatiotemporal attention and layer attention using the representations to form a context vector, and (ii) applying the LSTM to the context vector, a previous word of the caption, and a hidden state of the LSTM.

Abstract: A context-aware attention-based neural network is provided for answering an input question given a set of purportedly supporting statements for the input question. The neural network includes a processing element. The processing element is configured to calculate a question representation for the input question, based on word annotations and word-level attentions calculated for the input question. The processing element is further configured to calculate a sentence representation for each of the purportedly supporting statements, based on word annotations and word-level attentions calculated for each of the purportedly supporting statements. The processing element is also configured to calculate a context representation for the set of purportedly supporting statements with respect to the sentence representation for each of the purportedly supporting statements.

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.