Abstract: Methods and systems, including computer programs encoded on a computer storage medium. In one aspect, a method includes the actions of receiving a request to perform convolutional computations for a neural network on a hardware circuit having a matrix computation unit, the request specifying the convolutional computation to be performed on a feature tensor and a filter and padding applied to the feature tensor prior to performing the convolutional computation; and generating instructions that when executed by the hardware circuit cause the hardware circuit to perform operations comprising: transferring feature tensor data from a main memory of the hardware circuit to a scratchpad memory of the hardware circuit; and repeatedly performing the following operations: identifying a current subset of the feature tensor; and determining whether a memory view into the scratchpad memory for the current subset is consistent with a memory view of the current subset in the main memory.

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: The present disclosure advantageously provides a system and a method for convolving data in a quantized convolutional neural network (CNN). The method includes selecting a set of complex interpolation points, generating a set of complex transform matrices based, at least in part, on the set of complex interpolation points, receiving an input volume from a preceding layer of the quantized CNN, performing a complex Winograd convolution on the input volume and at least one filter, using the set of complex transform matrices, to generate an output volume, and sending the output volume to a subsequent layer of the quantized CNN.

Abstract: A model calculation unit for calculating a multilayer perceptron model, the model calculation unit being designed in hardware and being hardwired, including: a process or core; a memory; a DMA unit, which is designed to successively instruct the processor core to calculate a neuron layer, in each case based on input variables of an assigned input variable vector and to store the respectively resulting output variables of an output variable vector in an assigned data memory section, the data memory section for the input variable vector assigned to at least one of the neuron layers at least partially including in each case the data memory sections of at least two of the output variable vectors of two different neuron layers.

Abstract: Systems and methods are disclosed for detecting anomalies in text content of data objects even when a format of the data and/or data object is unknown. These may include receiving a first data object that corresponds to a first application service and that includes first text content. An anomaly classifier may be trained based on an artificial neural network by using a natural language processing algorithm on respective text content of at least a portion of each of a plurality of data objects corresponding to the first computing service. Each of the plurality of data objects may be labeled as belonging a category. The trained anomaly classifier may identify one or more text character sequences in the first text content of the first data object as anomalous and output identifying information indicating the one or more anomalous text character sequences in the first text content of the first data object.

Abstract: Provided are operations including: receiving, with one or more processors of a robot, an image of an environment from an imaging device separate from the robot; obtaining, with the one or more processors, raw pixel intensity values of the image; extracting, with the one or more processors, objects and features in the image by grouping pixels with similar raw pixel intensity values, and by identifying areas in the image with greatest change in raw pixel intensity values; determining, with the one or more processors, an area within a map of the environment corresponding with the image by comparing the objects and features of the image with objects and features of the map; and, inferring, with the one or more processors, one or more locations captured in the image based on the location of the area of the map corresponding with the image.

Abstract: Systems, apparatuses, and methods for optimizing neural network training with a first-in, last-out (FILO) buffer are disclosed. A processor executes a training run of a neural network implementation by performing multiple passes and adjusting weights of the neural network layers on each pass. Each training phase includes a forward pass and a backward pass. During the forward pass, each layer, in order from first layer to last layer, stores its weights in the FILO buffer. An error is calculated for the neural network at the end of the forward pass. Then, during the backward pass, each layer, in order from last layer to first layer, retrieves the corresponding weights from the FILO buffer. Gradients are calculated based on the error so as to update the weights of the layer for the next pass through the neural network.

Abstract: In an illustrative embodiment, systems and methods for calculating risk scores for locations potentially affected by catastrophic events include receiving a risk score request for a location, the risk score request including a request for assessment of risk exposure related to a type of catastrophic event. Based on the type of catastrophic event, a data compression algorithm may be applied to a catastrophic risk model representing amounts of perceived risk to an area surrounding the location. In response to receiving the risk score request, a risk score for the location may be calculated that corresponds to a weighted estimation of one or more data points in a compressed catastrophic risk model. A risk score user interface screen may be generated in real-time to present the catastrophic risk score and one or more corresponding loss metrics for the location due to a potential occurrence of the type of catastrophic event.

Abstract: A learning method includes: acquiring input data and correct answer information, the input data including a set of multiple pieces of relationship data in which relationships between variables are recorded respectively; determining conversion rule corresponding to each of the multiple pieces of relationship data such that relationships before and after a conversion of a common variable commonly in the multiple pieces of relationship data are the same, when converting a variable value in each of the multiple pieces of relationship data into converted data rearranging the variable values in an order of input; converting each of the multiple pieces of relationship data into a multiple pieces of the converted data according to each corresponding conversion rule; and inputting a set of the multiple pieces of converted data to the neural network and causing the neural network to learn a learning model based on the correct answer information.

Abstract: Embodiments of the invention are directed to systems, methods, and computer program products for electronic query engine for an image processing model database. The system is configured is configured for constructing a model abstraction layer for machine-learning neural-network based image processing models configured for selection, mutation and construction of the image processing models. Here, the system is configured to receive and process a user input query comprising a plurality of discrete input language elements, wherein each of the plurality of discrete input language elements comprises a character string. The system is also configured to construct a second image processing model by mutating a first image processing model, in accordance with the discrete input language elements.

Abstract: A method of subgraph tile fusion in a convolutional neural network, including partitioning a network into at least one subgraph node, determining a layer order of at least one layer of the at least one subgraph node, determining a input layer of the at least one subgraph node, determining a weight layer of the at least one subgraph node, determining a output layer of the at least one subgraph node and fusing the at least one subgraph node, the input layer, the weight layer and the output layer in the layer order.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a system output using a remembered value of a neural network hidden state. In one aspect, a system comprises an external memory that maintains context experience tuples respectively comprising: (i) a key embedding of context data, and (ii) a value of a hidden state of a neural network at the respective previous time step. The neural network is configured to receive a system input and a remembered value of the hidden state of the neural network and to generate a system output. The system comprises a memory interface subsystem that is configured to determine a key embedding for current context data, determine a remembered value of the hidden state of the neural network based on the key embedding, and provide the remembered value of the hidden state as an input to the neural network.

Abstract: Methods for determining a cause of a detected anomalous event in a telecommunications system are provided. The methods include detecting an anomalous event in the telecommunications system and retrieving relevant call detail record (CDR) data associated with the detected anomalous event for at least one identified time interval responsive to detecting the anomalous event. The relevant CDR data includes both current CDR data for the at least one identified time interval and historical CDR data for past intervals corresponding to the at least one identified time interval. The relevant CDR data including the current CDR data and the historical CDR data is preprocessed and the preprocessed relevant CDR data is processed to determine a root cause of the detected anomalous event. Processing the preprocessed relevant CDR data includes comparing the current CDR data and the historical CDR data to determine the root cause of the detected anomalous event.

Abstract: Certain aspects of the present disclosure are directed to methods and apparatus for deep learning in an artificial neural network. One example method generally includes receiving input data at an input to a layer of the neural network; replicating a group of neural processing units in the layer to form a superset of neural processing units, the superset comprising n instances of the group of neural processing units; processing the input data using the superset to generate output data for the layer; and determining an uncertainty of the output data. Processing the input data includes performing a dropout function by zeroing out one or more weights of a set of weights for each of the n instances of the superset of neural processing units and convolving, for each of the n instances in parallel, the input data with one or more non-zeroed out weights of the set of weights.

Abstract: The present disclosure includes apparatuses and methods related to stopping criteria for layered iterative error correction. A number of methods can include receiving a codeword with an error correction circuit, iteratively error correcting the codeword with the error correction circuit including parity checking the codeword on a layer-by-layer basis and updating the codeword after each layer. Methods can include stopping the iterative error correction in response to a parity check being correct for a particular layer.

Abstract: A transmitting apparatus is provided. The transmitting apparatus includes: an encoder configured to generate a low-density parity check (LDPC) codeword by LDPC encoding based on a parity check matrix; an interleaver configured to interleave the LDPC codeword; and a modulator configured to map the interleaved LDPC codeword onto a modulation symbol, wherein the modulator is further configured to map a bit included in a predetermined bit group from among a plurality of bit groups constituting the LDPC codeword onto a predetermined bit of the modulation symbol.

Abstract: A system such as a service of a computing resource service provider includes executable code that, if executed by one or more processors, causes the one or more processors to initiate a training of a machine-learning model with a parameter for the training having a first value, the training to determine a set of parameters for the model, calculate output of the training, and change the parameter of the training to have a second value during the training based at least in part on the output. Training parameters may, in some cases, also be referred to as hyperparameters.

Abstract: Methods are provided for validating theoretical improvements in the decision-support processes facilitating surveillance and monitoring of a patient's risk for developing a particular disease or condition and detecting the disease or condition. Patient information is received from a source and populated into an active risk assessment that monitors the patient's risk for developing Sepsis. At least a first and second set of actionable criteria for determining a patient's risk for developing sepsis are received. For each set of actionable criteria, it is determined that actionable criteria have been met. In some embodiments, software agents, operating in a multi-agent computing platform, perform each determination of whether actionable criteria are met.

Abstract: Based on an analysis of historical data of listings for an item, an online marketplace generates a price curve for the item to describe the likelihood to sell as a function of price. Based on seller preference data, an analysis of historical data of listings, or both, the online marketplace estimates the utility preferences for the seller account, such as the cost of time. Using the utility preferences and the price curve for an item, the online marketplace can generate a utility curve that estimates the utility for the seller account as a function of the item price. Using the utility curve, the online marketplace generates utility-based price guidance for a particular seller of the item. A user interface presents the utility-based price guidance to the seller and enables the seller to set the price of the item based on the price guidance.

Abstract: A data processing system operable to process a neural network, and comprising a plurality of processors. The data processing system is operable to determine whether to perform neural network processing using a single processor or using plural processors. When it is determined that plural processors should be used, a distribution of the neural network processing among two or more of the processors is determined and the two or more processors are each assigned a portion of the neural network processing to perform. A neural network processing output is provided as a result of the processors performing their assigned portions of the neural network processing.

Abstract: A method for generating target codes for one or more network functions for execution in a network is provided. The method comprises: receiving, at a processor, a network function definition; receiving, at the processor, one or more templates comprising preprogrammed codes in a preset format; compiling, at the processor, the network function definition and the one or more templates by providing key terms from the network function definition to the one or more templates; and generating the target codes.

Abstract: Embodiments of the present disclosure relate to a model training method, a data processing method, an electronic device, and a computer program product. The method includes: acquiring storage information associated with a simulated network environment; and training a reinforcement learning model using simulated data and based on a simulated-data read request for a node among multiple nodes included in the simulated network environment and each having a cache. With the technical solutions of the present disclosure, the cache allocation and cache replacement problems can be simultaneously solved by using a reinforcement learning model to determine in a dynamic environment a data caching scheme that meets predetermined criteria, so that it is possible to not only improve the accuracy and efficiency of determining the data caching scheme with less cost overhead, but also improve the user experience of users using the caching system.

Abstract: Embodiments of the present specification provide chips and chip-based data processing methods. In an embodiment, a method comprises: obtaining data associated with one or more neural networks transmitted from a server; for each layer of a neural network of the one or more neural networks, configuring, based on the data, a plurality of operator units based on a type of computation each operator unit performs; and invoking the plurality of operator units to perform computations, based on neurons of a layer of the neural network immediately above, of the data for each neuron to produce a value of the neuron.

Abstract: Techniques are provided for generating workspace recommendations based on prior user ratings of selected workspaces, as well as other similar selections. One method comprises obtaining user workspace ratings provided by a user; calculating a first workspace recommendation score for workspaces that the user previously rated based on the obtained user workspaces ratings; calculating a second workspace recommendation score for additional workspaces that are: (i) similar to workspaces previously rated by the user based on a predefined workspace similarity metric, and/or (ii) selected by similar users, based on a predefined user similarity metric; and recommending workspaces for the user based on the first workspace recommendation score and the second workspace recommendation score.

Abstract: System and method for associating user-entered consumable item description to an entry in a consumable item database. In one embodiment, formally structured restaurant menu item is matched to a large database of food items that has been constructed via crowd-sourcing. A novel, practical, and scalable machine learning solution architecture, consisting of two major steps is utilized. First a query generation approach is applied, based on a Markov Decision Process algorithm, to reduce the time complexity of searching for matching candidates. That is then followed by a re-ranking step, using deep learning techniques, to ensure matching quality goals are met.

Abstract: Systems and methods for optimizing and/or solving objective functions are provided. Angle-based stochastic gradient descent (AG-SGD) can be used to alleviate pattern deviation(s) not resolved by related art systems and methods. AG-SGD can use the angle between the current gradient (CG) and the previous gradient (PG) to determine the new gradient (NG).

Abstract: A fully connected operation method and a processing device for performing the same are provided. The fully connected operation method designates distribution data and broadcast data. The distribution data is divided into basic data blocks and distributed to parallel processing units, and the broadcast data is broadcasted to the parallel processing units. Operations between the basic data blocks and the broadcasted data are carried out by the parallel processing units before the results are returned to a main unit for further processing. The technical solutions disclosed by the present disclosure provide short Operation time and low energy consumption.

Abstract: A system and a method of quantizing a pre-trained neural network, includes determining by a layer/channel bit-width determiner for each layer or channel of the pre-trained neural network a minimum quantization noise for the layer or the channel for each master bit-width value in a predetermined set of master bit-width values; and selecting by a bit-width selector for the layer or the channel the master bit-width value having the minimum quantization noise for the layer or the channel. In one embodiment, the minimum quantization noise for the layer or the channel is based on a square of a range of weights for the layer or the channel that is multiplied by a constant to a negative power of a current master bit-width value.

Abstract: An image-processing system that can perform predetermined image processing on a manuscript character in a captured image is provided. A method for image processing includes training a neural network using composite image data including a background image and a manuscript image and correct image data corresponding to the composite image data, obtaining a captured image of an original that contains a manuscript character, and performing predetermined image processing on the captured image using the neural network.

Abstract: Subject matter disclosed herein may relate to storage and/or processing of signals and/or states representative of neural network parameters in a computing device, and may relate more particularly to compressing signals and/or states representative of neural network nodes in a computing device.

Abstract: Systems and techniques for neural network training are described herein, a training set may be received for a neural network. Here, the neural network may comprise a set of nodes arranged in layers and a set of inter-node weights between nodes in the set of nodes. The neural network may then be iteratively trained to create a trained neural network. An iteration of the training may include generating a random unit vector and creating an update vector by calculating a magnitude for the random unit vector based on a degree that the random unit vector matches a gradient—where the gradient is represented by a dual number. The iteration may continue by updating a parameter vector for an inter-node weight by subtracting the update vector from a previous parameter vector of the inter-node weight. The trained neural network may then be used to classify data.

Abstract: As provided herein, a list of locales of interest in a location may be sorted into one or more categories. A user performing a search for a locale of interest (e.g., a restaurant) may be identified. A local score may be assigned to the locale of interest based upon a number of local users (e.g., users residing in the location) that perform the search. A second user may be determined to be near the locale of interest. A category of interest may be determined for the second user (e.g., an interest in local non-tourist restaurants). Responsive to the category of interest corresponding to the category and the local score of the locale of interest exceeding an interest threshold, the second user may be provided with a recommendation to go to the locale of interest. The locale of interest may be a local favorite restaurant rather than a tourist trap.

Abstract: A method and apparatus for private information retrieval from a database, wherein the retrieval includes providing a covering vector for a plurality of database entries of the database. The covering vector is defined such that an inner product of the covering vector is zero with more than one member of a covering vector family that includes the covering vector. The retrieval includes generating database queries based on the covering vector and transmitting the database queries to at least two servers. An identical copy of the database may be stored on each of the at least two servers. Shares are received in response to the query, and these shares are aggregated, and a reconstruction algorithm executes to reconstruct the query results.

Abstract: Embodiments of the disclosure provide methods and systems for performing machine learning. The method can include: receiving training data; training a machine learning model based on the training data, wherein the machine learning model includes multiple layers each having one or more nodes having one or more connections with a node from another layer of the machine learning model; evaluating weights associated with the connections of the machine learning model, wherein each connection has a corresponding weight; removing, from the machine learning model, one or more connections having a weight that does not satisfy a threshold condition; and after the connections have been removed, updating the machine learning model.

Abstract: Embodiments are directed to data verification of business or consumer data. Certain embodiments include a data verification system that receives or selects data to be verified, selects one or more verification methods to verify, update, and/or append/enhance the data. The data verification system may verify the data with one or more data verification methods, either alone or in combination. The methods may include a web-crawling verification method, an agent web verification method, a call verification method, a direct mail method, an email method, an in-person verification method, or other methods. The system has the ability to, automatically or manually, (1) blend automatic and manual segmentation of records or elements by criteria such as industry type, best times of day/month/year to verify, update, or append, cost, and level of importance (2) select the best verification processing method(s), and (3) manage the results and properly verify, update, append/enhance records.

Abstract: Provided are a computer program product, system, and method for using a machine learning module to select one of multiple cache eviction algorithms to use to evict a track from the cache. A first cache eviction algorithm determines tracks to evict from the cache. A second cache eviction algorithm determines tracks to evict from the cache, wherein the first and second cache eviction algorithms use different eviction schemes. At least one machine learning module is executed to produce output indicating one of the first cache eviction algorithm and the second cache eviction algorithm to use to select a track to evict from the cache. A track is evicted that is selected by one of the first and second cache eviction algorithms indicated in the output from the at least one machine learning module.

Abstract: In various example embodiments, a system and method for projecting visual aspects into a vector space are presented. A query that includes visual data is received by the system from a client device. A visual aspect indicated in the visual data is analyzed. One or more symbols that correspond to the analyzed visual aspect is generated by the system. The analyzed visual aspect is projected into a vector space using the one or more symbols. A group of projections are identified, the group of projections being within a predetermined distance from the projected visual aspect in the vector space. An interface that depicts the further visual aspects is generated. The interface is displayed on the client device.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to perform malware detection using a generative adversarial network. An example apparatus includes a first encoder network to encode an input sample into a first encoded sample, the first encoder network implemented using a multilayer perception (MLP) network, a generator network to reconstruct the first encoded sample to generate a reconstructed sample, a discriminator network to, in response to obtaining the first encoded sample and the reconstructed sample, generate a loss function based on the reconstructed sample and the input sample, and an optimization processor to, when the loss function satisfies a threshold loss value, classify the input sample as malicious.

Abstract: A method, system, and computer program product for detecting multi-scale objects. The method may include receiving a sample dataset including multi-scale objects associated with a specific environment, where the sample dataset has an existing resolution. The method may also include inputting the sample dataset into a trained neural network, where the trained neural network has a plurality of scale regions. The method may also include processing the sample dataset for detecting the multi-scale objects by means of the trained neural network. The method may also include calculating a distribution of contribution degree in a course of processing the sample dataset, where the contribution degree is associated with each of the plurality of scale regions. The method may also include generating a set of configuration parameters associated with the specific environment for the trained neural network based at least in part on the distribution of contribution degree.

Abstract: The disclosed embodiments relate to a system that determines whether an inferential model is susceptible to spillover false alarms. During operation, the system receives a set of time-series signals from sensors in a monitored system. The system then trains the inferential model using the set of time-series signals. Next, the system tests the inferential model for susceptibility to spillover false alarms by performing the following operations for one signal at a time in the set of time-series signals. First, the system adds degradation to the signal to produce a degraded signal. The system then uses the inferential model to perform prognostic-surveillance operations on the time-series signals with the degraded signal. Finally, the system detects spillover false alarms based on results of the prognostic-surveillance operations.

Abstract: According to one embodiment, a first set of features is received, where each of the features in the first set being associated with a predetermined category. A bloom filter is applied to the first set of features to generate a second set of features. A neural network model is trained by applying the second set of features to a first layer of nodes of the neural network model to generate an output, the neural network model including a plurality of layers of nodes coupled to each other via a connection. The output of the neural network model is compared with a target value associated with the predetermined category to determine whether the neural network model satisfies a predetermined condition.

Abstract: Some embodiments include a system operable to construct hierarchical training data sets for use with machine-learning for multiple controlled devices. Other embodiments of related systems and methods are also provided.

Abstract: Disclosed herein are methods and system for training artificial intelligence models configured to execute image segmentation techniques. The methods and system describe a server that receives a first image including a set of pixels depicting multiple objects. The server also receives a second image having a second set of pixels depicting the same set of objects. The server then analyzes the pixels from the first and second images. When a difference between at least one visual attribute of a pixel within the second image and a corresponding pixel within the first image satisfies a predetermined threshold, it will be encoded as spikes to send to the model, the model will be trained using supervised STDP rule by revising weights associated with the nodes within the AI model where the node corresponds to the pixels within the first and/or the second image.

Abstract: Subject matter disclosed herein may relate to storage of signals and/or states representative of parameters in a computing device, and may relate more particularly to storage of signals and/or states representative of neural network parameters in a computing device.

Abstract: A method of quantizing an artificial neural network includes dividing an input distribution of the artificial neural network into a plurality of segments, generating an approximated density function by approximating each of the plurality of segments, calculating at least one quantization error corresponding to at least one step size for quantizing the artificial neural network, based on the approximated density function, and determining a final step size for quantizing the artificial neural network based on the at least one quantization error.

Abstract: A scalable stream synaptic supercomputer for extreme throughput neural networks is provided. The firing state of a plurality of neurons of a first neurosynaptic core is determined substantially in parallel. The firing state of the plurality of neurons is delivered to at least one additional neurosynaptic core substantially in parallel.

Abstract: A computer-based system and method for determining similarity between at least two heterogenous unstructured data records and for optimizing processing performance. A plurality of occupational data records is generated and, for each of the occupational data records, a respective vector is created to represent the occupational data record. Each of the vectors is sliced into a plurality of chunks. Thereafter, semantic matching of the chunks occurs in parallel, to compare at least one occupational data record to at least one other occupational data record simultaneously and substantially in real time. Thereafter, values representing similarities between at least two of the occupational data records are output.

Abstract: A memory component can include memory cells with a memory region to store a machine learning model and input data and another memory region to store host data from a host system. The memory component can include an in-memory logic, coupled to the memory cells, to perform a machine learning operation by applying the machine learning model to the input data to generate an output data. A bus can receive additional data from the host system and can provide the additional data to the other memory region or the in-memory logic based on a characteristic of the additional data.

Abstract: A method for operating artificial neural network with nonvolatile memory device having at least one artificial neural nonvolatile memory network. The forgoing artificial neural nonvolatile memory network (ANN) comprises M×N numbers nonvolatile memory cells that are arranged to form a memory array, and the nonvolatile memory cell can be a non-overlapped implementation (NOI) MOSFET, a RRAM element, a PCM element, a MRAM element, or a SONOS element. By applying this novel method to the ANN, it is able to perform feedforward and recurrent operations in the M×N numbers of nonvolatile memory devices in the ANN, so as to adjust or correct the weights stored in the M×N numbers of nonvolatile memory devices.

Abstract: Providing knowledge representation of material content being consumed by a user combines the user's current behavioral data and data from external sources such as internet web sites and social media network. Visual representations of entities and their relationships in the content being consumed by the user are created while the user is consuming content, and displayed via a graphical user interface.