Abstract: Systems and methods for automatic speech recognition by training a neural network to learn features from raw speech. The system comprises a neural network executing on a computer system and comprising a feature extractor, a label classifier, and a domain classifier. The feature extractor processes raw speech data and generates a first output data. The label classifier processes the first output data and generates a second output data. The domain classifier processes the first output data and generating a third output data. The neural network calculates first loss data based on the second output, and second loss data based on the third output. Further, the neural network is trained to minimize a cross-entropy cost of the label classifier and to maximize a cross-entropy cost of the domain classifier using the first loss data and the second loss data.

Abstract: A method receives a second data set that is different from a first data set. A total number of operations based on the second data set using an operation estimator is generated. Also, an aggregate resource cost for the total number of operations based on the second data set using a resource cost estimator is generated. The method generates a simulation driver file including a sequence of operations from the total number of operations and a resource cost for each operation in the sequence of operations from the aggregate resource cost. The method simulates the sequence of operations by performing: requesting an amount of resource used by a respective operation on the simulated distributed computing system; reserving the amount of resource when available in the simulated distributed computing system without executing the respective operation; and calculating a time period associated with a simulated execution time of the respective operation.

Abstract: Computer vision systems and methods for machine learning using image hallucinations are provided. The system generates image hallucinations that are subsequently used to train a deep neural network to match image patches. In this scenario, the synthesized changes serve in the learning of feature-embedding that captures how a patch of an image might look like from a different vantage point. In addition, a curricular learning framework is provided which is used to automatically train the neural network to progressively learn more invariant representations.

Abstract: Systems and methods for unsupervised representation learning by sorting sequences are provided. An unsupervised representation learning approach is provided which uses videos without semantic labels. The temporal coherence as a supervisory signal can be leveraged by formulating representation learning as a sequence sorting task. A plurality of temporally shuffled frames (i.e., in non-chronological order) can be used as inputs and a convolutional neural network can be trained to sort the shuffled sequences and to facilitate machine learning of features by the convolutional neural network. Features are extracted from all frame pairs and aggregated to predict the correct sequence order. As sorting shuffled image sequence requires an understanding of the statistical temporal structure of images, training with such a proxy task can allow a computer to learn rich and generalizable visual representations from digital images.

Abstract: The present invention relates to a process for the purification of compound of formula II, wherein X may be independently selected from trifluoroacetic acid, hydrochloric acid, hydrobromic acid, p-toluene sulfonic acid and phosphoric acid; its isolation as solid and use for the preparation of carfilzomib.

Abstract: The present invention relates to a process for the purification of Carfilzomib of Formula I that reduces the level of an acetamide impurity of Formula II preferably below 0.10 wt %.

Abstract: In one embodiment, a method selects a new job to schedule for execution on a data processing system. The new job includes a. Performance information for a set of current jobs that are being executed in the data processing system is retrieved where the set of jobs are assigned to queues and currently classified with a current classification. The method analyzes the performance information to determine when one or more current jobs in the set of current jobs should be re-classified due to resource usage of a respective current job when being executed in the data processing system and re-classifies the classifications for the one or more current jobs in the queues. Then, the new job is assigned to one of the queues based on the classification of the new job and the classifications of jobs in the queues including the re-classified classifications for the one or more current jobs.

Abstract: Systems and methods for detection and localization of image and document forgery. The method can include the step of receiving a dataset having a plurality of authentic images and a plurality of manipulated images. The method can also include the step of benchmarking a plurality of image forgery algorithms using the dataset. The method can further include the step of generating a plurality of receiver operating characteristic (ROC) curves for each of the plurality of image forgery algorithms. The method also includes the step of calculating a plurality of area under curve metrics for each of the plurality of ROC curves. The method further includes the step of training a neural network for image forgery based on the plurality of area under curve metrics.

Abstract: Systems and methods for optical character resolution (OCR) at low resolutions are provided. The system receives a dataset and extracts document images from the dataset. The system then segments and extracts a plurality of text lines from the document images. The system then processes the plurality of text lines using a Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) module to perform line OCR. Finally, the system generates a plurality of text strings corresponding to the plurality of text lines.

Abstract: A method receives a second data set that is different from a first data set. A total number of operations based on the second data set using an operation estimator is generated. Also, an aggregate resource cost for the total number of operations based on the second data set using a resource cost estimator is generated. The method generates a simulation driver file including a sequence of operations from the total number of operations and a resource cost for each operation in the sequence of operations from the aggregate resource cost. The method simulates the sequence of operations by performing: requesting an amount of resource used by a respective operation on the simulated distributed computing system; reserving the amount of resource when available in the simulated distributed computing system without executing the respective operation; and calculating a time period associated with a simulated execution time of the respective operation.

Abstract: The present invention relates to a process for the purification of Carfiizomib of Formula I that reduces the level of an acetamide impurity of Formula II preferably below 0.10 wt %. Formula I Formula II.

Abstract: In one embodiment, a method selects a new job to schedule for execution on a data processing system. The new job includes a. Performance information for a set of current jobs that are being executed in the data processing system is retrieved where the set of jobs are assigned to queues and currently classified with a current classification. The method analyzes the performance information to determine when one or more current jobs in the set of current jobs should be re-classified due to resource usage of a respective current job when being executed in the data processing system and re-classifies the classifications for the one or more current jobs in the queues. Then, the new job is assigned to one of the queues based on the classification of the new job and the classifications of jobs in the queues including the re-classified classifications for the one or more current jobs.

Abstract: A method of identifying an optimum treatment for a patient suffering from coronary artery disease, comprising: (i) providing patient information selected from: (a) status in the patient of one or more coronary disease associated biomarkers; (b) one or more items of medical history information selected from prior condition history, intervention history and medication history; (c) one or more items of diagnostic history, if the patient has a diagnostic history; and (d) one or more items of demographic data; (ii) aggregating the patient information in: (a) a Bayesian network; (b) a machine learning and neural network; (c) a rule-based system; and (d) a regression-based system; (iii) deriving a predicted probabilistic adverse event outcome for each intervention comprising percutaneous coronary intervention by placement of a bare metal stent, or a drug-coated stent; or by coronary artery bypass grafting; and (iv) determining the intervention having the lowest predicted probabilistic adverse outcome.

Abstract: A method and system for cooperative diversity visual cognition in a wireless sensor network is disclosed. The method and system are capable of solving distributed visual cognition tasks (for example, online simultaneous reconstruction of 3D models of a large area) by using multiple video streams and exploiting cooperative diversity video sensing information while ensuring an optimal tradeoff between energy consumption and video quality of images received from said multiple video streams.

Abstract: A system is provided that manages consigned inventory. The system consumes consigned inventory items. The system further generates a consumption advice in response to the consumption of the consigned inventory items, where the consumption advice references a consignment agreement, a consignment order and a receipt. The system further communicates the consumption advice to a supplier. The consumption advice includes at least one of: a consumption advice number; a business unit; an inventory organization; a supplier; a supplier site; a start date; or an end date. The consumption advice includes one or more consumption advice lines, and each consumption advice line includes one or more consumption transactions.

Abstract: Multiple cameras are configured for use in video analytics. A single configuration tool is provided. The interrelationships between cameras are included within the configuration. Using a combination of text entry fields, registration of the cameras on a floor or other map, and marking on images from the cameras, an efficient workflow for configuration may be provided.

Abstract: An active set of discrete texture traces to a target point is determined in a first video frame and is applied to a second video frame to detect the target location in a second video frame. An estimate is made of the target location in the second video frame. A score map is computed of an area of locations. A location with a highest score in the score map is the new target location. If a threshold value is not met the active set of texture traces is stored. A score map for each of stored active sets is computed to determine the target location. If no score meets the threshold the target location in a previous video frame is made the current target location and a new active set of discrete texture traces is determined. Systems that implement the steps of the methods are also provided.

Abstract: A method of detecting an object in image data that is deemed to be a threat includes annotating sections of at least one training image to indicate whether each section is a component of the object, encoding a pattern grammar describing the object using a plurality of first order logic based predicate rules, training distinct component detectors to each identify a corresponding one of the components based on the annotated training images, processing image data with the component detectors to identify at least one of the components, and executing the rules to detect the object based on the identified components.

Abstract: A requirements management tool, where each requirement is defined by one or more design element values. Each of the design element values is a unique value and is a member of a group of design element values defined for the project. As each requirement is created, the design element values for the requirement are selected from the group of design element values, or alternatively, a new design element value may be entered by a user, and the new design element value will be added to the group of element values. Each design element value corresponds to a category that each of the requirements are broken down into. Design element values in the created requirement are compared to design element values in existing requirements, and results of this duplication check are presented to a user of the requirements management tool.

Abstract: First order predicate logics are provided, extended with a bilattice based uncertainty handling formalism, as a means of formally encoding pattern grammars, to parse a set of image features, and detect the presence of different patterns of interest implemented on a processor. Information from different sources and uncertainties from detections, are integrated within the bilattice framework. Automated logical rule weight learning in the computer vision domain applies a rule weight optimization method which casts the instantiated inference tree as a knowledge-based neural network, to converge upon a set of rule weights that give optimal performance within the bilattice framework. Applications are in (a) detecting the presence of humans under partial occlusions and (b) detecting large complex man made structures in satellite imagery (c) detection of spatio-temporal human and vehicular activities in video and (c) parsing of Graphical User Interfaces.