Abstract: Exemplary embodiments provide distributed parallel training of a machine learning model. Multiple processors may be used to train a machine learning model to reduce training time. To synchronize trained model data between the processors, data is communicated between the processors after some number of training cycles. To improve the communication efficiency, exemplary embodiments synchronize data among a set of processors after a predetermined number of training cycles, and synchronize data between one or more processors of each set of the processors after a predetermined number of training cycles. During the first synchronization among a set of processors, compressed model gradient data generated after performing the training cycles may be communicated. During the second synchronization between the set of processors, trained models or full model gradient data generated after performing the training cycles may be communicated.

Abstract: A data processing technique uses an Artificial Neural Network (ANN) with Rectifier Linear Units (ReLU) to yield improve accuracy in a runtime task, for example, in processing audio-based data acquired by a speech-enabled device. The technique includes a first aspect that relates to initialization of the ANN weights to initially yield a high fraction of positive outputs from the ReLU. These weights are then modified using an iterative procedure in which the weights are incrementally updated. A second aspect relates to controlling the size of the incremental updates (a “learning rate”) during the iterations of training according to a variance of the weights at each layer.

Abstract: Features are disclosed for modifying a statistical model to more accurately discriminate between classes of input data. A subspace of the total model parameter space can be learned such that individual points in the subspace, corresponding to the various classes, are discriminative with respect to the classes. The subspace can be learned using an iterative process whereby an initial subspace is used to generate data and maximize an objective function. The objective function can correspond to maximizing the posterior probability of the correct class for a given input. The initial subspace, data, and objective function can be used to generate a new subspace that better discriminates between classes. The process may be repeated as desired. A model modified using such a subspace can be used to classify input data.

Abstract: Features are disclosed for improving the robustness of a neural network by using multiple (e.g., two or more) feature streams, combing data from the feature streams, and comparing the combined data to data from a subset of the feature streams (e.g., comparing values from the combined feature stream to values from one of the component feature streams of the combined feature stream). The neural network can include a component or layer that selects the data with the highest value, which can suppress or exclude some or all corrupted data from the combined feature stream. Subsequent layers of the neural network can restrict connections from the combined feature stream to a component feature stream to reduce the possibility that a corrupted combined feature stream will corrupt the component feature stream.

Abstract: Features are disclosed for using an artificial neural network to generate customized speech recognition models during the speech recognition process. By dynamically generating the speech recognition models during the speech recognition process, the models can be customized based on the specific context of individual frames within the audio data currently being processed. In this way, dependencies between frames in the current sequence can form the basis of the models used to score individual frames of the current sequence. Thus, each frame of the current sequence (or some subset thereof) may be scored using one or more models customized for the particular frame in context.

Abstract: Features are disclosed for using a neural network to tag sequential input without using an internal representation of the neural network generated when scoring previous positions in the sequence. A predicted or determined label (e.g., the highest scoring or otherwise most probable label) for input at a given position in the sequence can be used when scoring input corresponding to the next position the sequence. Additional features are disclosed for training a neural network for use in tagging sequential input without using an internal representation of the neural network generated when scoring previous positions the sequence.

Abstract: Features are disclosed for performing speech recognition on utterances using a grammar and a statistical language model, such as an n-gram model. States of the grammar may correspond to states of the statistical language model. Speech recognition may be initiated using the grammar. At a given state of the grammar, speech recognition may continue at a corresponding state of the statistical language model. Speech recognition may continue using the grammar in parallel with the statistical language model, or it may continue using the statistical language model exclusively. Scores associated with the correspondences between states (e.g., backoff arcs) may be determined according to a heuristically or based on test data.

Abstract: Features are disclosed for reducing the dynamic range of an approximated trained artificial neural network weight matrix in an automatic speech recognition system. The weight matrix may be approximated as two low-rank matrices using a decomposition technique. This approximation technique may insert an additional layer between the two original layers connected by the weight matrix. The dynamic range of the low-rank decomposition may be reduced by applying the square root of singular values, combining them with both low-rank matrices, and utilizing a random rotation matrix to further compress the low-rank matrices. Reduction of dynamic range may make fixed point scoring more effective due to smaller quantization error, as well as make the neural network system more favorable for retraining after approximating a neural network weight matrix. Features are also disclosed for adjusting the learning rate during retraining to account for the low-rank approximations.

Abstract: Features are disclosed for estimating affine transforms in Log Filter-Bank Energy Space (“LFBE” space) in order to adapt artificial neural network-based acoustic models to a new speaker or environment. Neural network-based acoustic models may be trained using concatenated LFBEs as input features. The affine transform may be estimated by minimizing the least squares error between corresponding linear and bias transform parts for the resultant neural network feature vector and some standard speaker-specific feature vector obtained for a GMM-based acoustic model using constrained Maximum Likelihood Linear Regression (“cMLLR”) techniques. Alternatively, the affine transform may be estimated by minimizing the least squares error between the resultant transformed neural network feature and some standard speaker-specific feature obtained for a GMM-based acoustic model.

Abstract: Features are disclosed for reducing the dynamic range of an approximated trained artificial neural network weight matrix in an automatic speech recognition system. The weight matrix may be approximated as two low-rank matrices using a decomposition technique. This approximation technique may insert an additional layer between the two original layers connected by the weight matrix. The dynamic range of the low-rank decomposition may be reduced by applying the square root of singular values, combining them with both low-rank matrices, and utilizing a random rotation matrix to further compress the low-rank matrices. Reduction of dynamic range may make fixed point scoring more effective due to smaller quantization error, as well as make the neural network system more favorable for retraining after approximating a neural network weight matrix. Features are also disclosed for adjusting the learning rate during retraining to account for the low-rank approximations.

Abstract: A method and apparatus for displaying periodic signals generated by a medical device is disclosed. A method and apparatus for displaying quasi-periodic signals generated by a medical device also is disclosed.

Abstract: A method and apparatus for remote monitoring of a medical patient is described. A sensor device is placed in physical contact with the patient. The sensor communicates with a computing device using Bluetooth or another wireless communication protocol. The computing device then communicates with a remote server that compiles data regarding the patient. The system can gather data such as the patient's temperature, the amount of exercise undertaken by the patient, the amount of sleep by the patient, and whether the patient has physically fallen.

Abstract: An improved method and apparatus for providing integrated medical services is disclosed.

Abstract: A topology of a multitier compute infrastructure is automatically discovered. Discovery can be roughly divided into two phases. In one phase, components and physical relationships are discovered. In the other phase, non-physical relationships between the components are deduced. The second phase typically is based in part on information obtained in the first phase. In one application, the components and relationships that are discovered/deduced are used to build a map of the multitier compute infrastructure.

Abstract: A multitier topology map describes a multitier compute infrastructure. The multitier topology map identifies components from at least two different tiers of the multitier compute infrastructure and indicates relationships between components including at least one cross-tier relationship between components. An interface module accesses the multitier topology map.

Abstract: A multitier topology map describes a multitier compute infrastructure. The multitier topology map identifies components from at least two different tiers of the multitier compute infrastructure and indicates relationships between components including at least one cross-tier relationship between components. An interface module accesses the multitier topology map.

Abstract: A multitier topology map describes a multitier compute infrastructure. The multitier topology map identifies components from at least two different tiers of the multitier compute infrastructure and indicates relationships between components including at least one cross-tier relationship between components. An interface module accesses the multitier topology map.

Abstract: A descriptor for a multitier compute infrastructure is provided. A multitier topology map contains an inventory of network tier, application tier, and compute tier components and the relationships among the components. A business service can be defined as a logical grouping of components that transactionally implement a business process. A service descriptor includes the component dependencies that define the business service. The business service leverages the component dependencies to provide cross-tier visibility of the business process and performance analysis features.

Abstract: An application model automates deployment of an application. In one embodiment, the application model includes a static description of the application and a run-time description of the application. Deployment phases, such as installation, configuration and activation of the application are executed according to the application model.

Abstract: An application model automates deployment of an application. In one embodiment, the application model includes a static description of the application and a run-time description of the application. Deployment phases, such as installation, configuration and activation of the application are executed according to the application model.