Abstract: Certain aspects of the present disclosure provide techniques for detecting data entry errors. A method generally includes receiving a string value as user input for a data field, selecting a plurality of reference values previously entered into the data field within a time period, processing, with an embedding model configured to classify an input string value as a valid or invalid entry, the string value and the reference values and thereby generating a first vector as output, computing one or more statistics for the reference values and the string value, creating a second vector based on the one or more statistics, generating a concatenated vector by concatenating the first vector and the second vector, processing, with a classifier model configured to classify the string value as valid or invalid, the concatenated vector and thereby generating a classification output, and taking action based on the classification output.

Abstract: The present invention relates to a prediction method for stall and surge of an axial compressor based on deep learning. The method comprises the following steps: firstly, preprocessing data with stall and surge of an aeroengine, and partitioning a test data set and a training data set from experimental data. Secondly, constructing an LR branch network module, a WaveNet branch network module and a LR-WaveNet prediction model in sequence. Finally, conducting real-time prediction on the test data: preprocessing test set data in the same manner, and adjusting data dimension according to input requirements of the LR-WaveNet prediction model; giving surge prediction probabilities of all samples by means of the LR-WaveNet prediction model according to time sequence; and giving the probability of surge that data with noise points changes over time by means of the LR-WaveNet prediction model, to test the anti-interference performance of the model.

Abstract: Embodiments relate to managing tasks that when executed by a neural processor circuit instantiates a neural network. The neural processor circuit includes neural engine circuits and a neural task manager circuit. The neural task manager circuit includes multiple task queues and a task arbiter circuit. Each task queue stores a reference to a task list of tasks for a machine learning operation. Each task queue may be associated with a priority parameter. Based on the priority of the task queues, the task arbiter circuit retrieves configuration data for a task from a memory external to the neural processor circuit, and provides the configuration data to components of the neural processor circuit including the neural engine circuits. The configuration data programs the neural processor circuit to execute the task. For example, the configuration data may include input data and kernel data processed by the neural engine circuits to execute the task.

Abstract: Techniques for zero-shot and few-shot transfer of domain-adapted base networks are described. Multiple machine learning task layers are trained using a shared base feature extractor network. At least one task layer is trained with samples and corresponding labels from a first domain as well as a second domain. At least one other task layer is trained with samples and corresponding labels from only the first domain. Ultimately, the other task layer(s) are adapted to generate labels for the first domain via the base network being weighted based on all trainings.

Abstract: Techniques for predictive disease identification using simulations improved via machine learning. A method includes applying at least one machine learning model to features extracted from data including animal characteristics data of an animal, wherein outputs of the at least one machine learning model include a plurality of disease predictor values, wherein each disease predictor value corresponds to a respective disease type of a plurality of disease types, wherein each disease type of the plurality of disease types corresponds to a predetermined group of diseases; generating disease contraction statistics based on the outputs of the at least one machine learning model; and determining, based on the disease contraction statistics, at least one disease prediction for the animal.

Abstract: Some embodiments provide a compiler for optimizing the implementation of a machine-trained network (e.g., a neural network) on an integrated circuit (IC). The compiler of some embodiments receives a specification of a machine-trained network including multiple layers of computation nodes and generates a graph representing options for implementing the machine-trained network in the IC. In some embodiments, the compiler also generates instructions for gating operations. Gating operations, in some embodiments, include gating at multiple levels (e.g., gating of clusters, cores, or memory units). Gating operations conserve power in some embodiments by gating signals so that they do not reach the gated element or so that they are not propagated within the gated element. In some embodiments, a clock signal is gated such that a register that transmits data on a rising (or falling) edge of a clock signal is not triggered.

Abstract: Techniques regarding identifying candidate knowledge graph subgraphs in a question answering over knowledge graph task are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a question answering over knowledge graph component that encodes graph structure information of a knowledge graph subgraph and a question graph into neural network embeddings.

Abstract: Systems, methods, apparatuses, and computer program products for tracking weak signal traces under severe noise and/or distortions. A method may include tracking at least one candidate frequency trace from a time-frequency representation of a signal. The method may also include identifying a frequency trace of the signal based on tracking results. In addition, the method may include outputting an estimated frequency vector related to the frequency trace. Further, the tracking may be performed under a noisy condition environment.

Abstract: A method for employee biometric tracking is provided. The method comprises providing to a user a plurality of wearable devices capable of being connected to the user, establishing a wireless connection between the plurality of wearable devices and a mobile device, collecting by the plurality of wearable devices a plurality of biometric data from the user, receiving by an application stored on the mobile device the plurality of biometric data, inputting into a predictive engine biometric data selected from the plurality of biometric data, determining by the predictive engine in response to the biometric data whether the user is at, or soon will be at, an alert level, creating an alert signal, and displaying the alert signal to the user.

Abstract: In automated machine learning, an approximate best configuration can be selected among multiple candidate machine-learning configurations by progressively sampling training and test datasets for the iterative training and testing of the configurations while progressively pruning the set of candidate configurations based on associated estimated confidence intervals for their respective performance.

Abstract: One or more computer processors identify one or more similar, historical regression tests and historical builds utilizing a computed similarity measure between a regressed build and one or more historical builds conducted on a same release cycle, wherein the identified one or more similar historical regression tests and historical builds are K closest neighbors to the regressed build; predict an elapsed time of the one or more profiled regression tests utilizing a KNN algorithm comprising the K closest neighbors each weighted by a corresponding average distance from a test point and the elapsed time as a target variable; responsive to the predicted elapsed time exceeding an actual elapsed time associated with the regressed build, determine that the regressed build is an actual regression; responsive to determining that the regressed build is not due to variability, apply one or more mitigation actions to the regressed build.

Abstract: A reorganizable neural network computing device is provided. The computing device includes a data processing array unit including a plurality of operators disposed at locations corresponding to a row and a column. One or more chaining paths which transfer the first input data from the operator of the first row of the data processing array to the operator of the second row are optionally formed. The plurality of first data input processors of the computing device transfer the first input data for a layer of the neural network to the operators along rows of the data processing array unit, and the plurality of second data input processors of the computing device transfer the second input data to the operators along the columns of the data processing array.

Abstract: A point estimate value for an individual is computed using a Bayesian neural network model (BNN) by training a first BNN model that computes a weight mean value, a weight standard deviation value, a bias mean value, and a bias standard deviation value for each neuron of a plurality of neurons using observations. A plurality of BNN models is instantiated using the first BNN model. Instantiating each BNN model of the plurality of BNN models includes computing, for each neuron, a weight value using the weight mean value, the weight standard deviation value, and a weight random draw and a bias value using the bias mean value, the bias standard deviation value, and a bias random draw. Each instantiated BNN model is executed with the observations to compute a statistical parameter value for each observation vector of the observations. The point estimate value is computed from the statistical parameter value.

Abstract: Embodiments described herein combine both masked reconstruction and predictive coding. Specifically, unlike contrastive learning, the mutual information between past states and future states are directly estimated. The context information can also be directly captured via shifted masked reconstruction—unlike standard masked reconstruction, the target reconstructed observations are shifted slightly towards the future to incorporate more predictability. The estimated mutual information and shifted masked reconstruction loss can then be combined as the loss function to update the neural model.

Abstract: A design optimization method based on active learning, which involves dynamic exploration and exploitation of the design space of interest using an ensemble of machine learning algorithms. In this approach, a hybrid methodology incorporating an explorative weak learner which fits high-level information about the response surface, and an exploitative strong learner (based on committee machine) that fits finer details around promising regions identified by the weak learner, is employed. For each design iteration, an aristocratic approach is used to select a set of nominees, where points that meet a threshold merit value as predicted by the weak learner are selected to be evaluated using function evaluation. In addition to these points, the global optimum as predicted by the strong learner is also evaluated to enable rapid convergence to the actual global optimum once the most promising region has been identified by the optimizer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network. One of the methods includes maintaining a replay memory that stores trajectories generated as a result of interaction of an agent with an environment; and training an action selection neural network having policy parameters on the trajectories in the replay memory, wherein training the action selection neural network comprises: sampling a trajectory from the replay memory; and adjusting current values of the policy parameters by training the action selection neural network on the trajectory using an off-policy actor critic reinforcement learning technique.

Abstract: Networks and encodings therefor are provided that are adapted to provide increased energy efficiency and speed for convolutional operations. In various embodiments, a neural network comprises a plurality of neural cores. Each of the plurality of neural cores comprises a memory. A network interconnects the plurality of neural cores. The memory of each of the plurality of neural cores comprises at least a portion of a weight tensor. The weight tensor comprising a plurality of weights. Each neural core is adapted to retrieve locally or receive a portion of an input image, apply the portion of the weight tensor thereto, and store locally or send a result therefrom via the network to other of the plurality of neural cores.

Abstract: Disclosed is a method for convolution calculation in a neural network, comprising: reading an input feature map, depthwise convolution kernels and pointwise convolution kernels from a dynamic random access memory (DRAM); performing depthwise convolution calculations and pointwise convolution calculations by depthwise convolution calculation units and pointwise convolution calculation units, according to the input feature map, the depthwise convolution kernels and the pointwise convolution kernels to obtain output feature values of a first predetermined number p of points on all pointwise convolution output channels; storing the output feature values of a first predetermined number p of points on all pointwise convolution output channels into an on-chip memory; and repeating above operation to obtain output feature values of all points on all point wise convolution output channels. Therefore, the storage space for storing intermediate results may be reduced.

Abstract: In some examples, an individually-pruned neural network can estimate blood pressure from a seismocardiogram (SCG). In some examples, a baseline model can be constructed by training the model with SCG data and blood pressure measurement from a plurality of subjects. One or more filters (e.g., the filters in the top layer of the network) can be ranked by separability, which can be used to prune the model for each unseen user that uses the model thereafter, for example. In some examples, individuals can use individually-pruned models to calculate blood pressure using SCG data without corresponding blood pressure measurements.

Abstract: Some embodiments provide a compiler for optimizing the implementation of a machine-trained network (e.g., a neural network) on an integrated circuit (IC). The compiler of some embodiments receives a specification of a machine-trained network including multiple layers of computation nodes and generates a graph representing options for implementing the machine-trained network in the IC. In some embodiments, the graph includes nodes representing options for implementing each layer of the machine-trained network and edges between nodes for different layers representing different implementations that are compatible. In some embodiments, the graph is populated according to rules relating to memory use and the numbers of cores necessary to implement a particular layer of the machine trained network such that nodes for a particular layer, in some embodiments, represent fewer than all the possible groupings of sets of clusters.