Abstract: A method for designing a tool string for use in a wellbore includes receiving a merit function, and determining, with a computing system and based on the merit function, a tool string design for a tool string. The merit function comprises one or more defined objectives for performing a process in a wellbore. The tool string design comprises an indication of one or more tools used to form a tool string for performing the process in the wellbore, and the tool string design satisfies the merit function.

Abstract: Analog processors for solving various computational problems are provided. Such analog processors comprise a plurality of quantum devices, arranged in a lattice, together with a plurality of coupling devices. The analog processors further comprise bias control systems each configured to apply a local effective bias on a corresponding quantum device. A set of coupling devices in the plurality of coupling devices is configured to couple nearest-neighbor quantum devices in the lattice. Another set of coupling devices is configured to couple next-nearest neighbor quantum devices. The analog processors further comprise a plurality of coupling control systems each configured to tune the coupling value of a corresponding coupling device in the plurality of coupling devices to a coupling. Such quantum processors further comprise a set of readout devices each configured to measure the information from a corresponding quantum device in the plurality of quantum devices.

Abstract: A system and method for reducing laser communication terminal pointing uncertainty. The method trains an artificial neural network (ANN) with input data characterizing terminal pointing error and dependent parameters. The method inputs the trained ANN a set of data of these dependent parameters with unknown pointing error. The method uses the ANN output to apply corrections to the terminal pointing solution to reduce pointing uncertainty. The method can condition the ANN generated corrections to avoid cases where application of the ANN correction could exceed the original pointing uncertainty. This conditioning includes computing the Euclidean distance between current ANN input parameter values and values in the ANN training dataset, and bounding the allowed magnitude of the ANN pointing correction. The method can train the ANN incrementally during terminal operation for real-time updates or train the ANN offline with gathered data and implement the trained ANN on the terminal for subsequent links.

Abstract: Methods, systems and devices for unsupervised learning utilizing at least one kT-RAM. An evaluation can be performed over a group of N AHaH nodes on a spike pattern using a read instruction (FF), and then an increment high (RH) instruction can be applied to the most positive AHaH node among the N AHaH nodes if an ID associated with the most positive AHaH node is not contained in a set, followed by adding a node ID to the set. In addition, an increment low (RL) instruction can be applied to all AHaH nodes that evaluated positive but were not the most positive, contingent on the most-positive AHaH node's ID not being contained in the set. In addition, node ID's can be removed from the set if the set size is equal to the N number of AHaH nodes.

Abstract: A method and an apparatus for camera-free light field video processing with all-optical neural network are disclosed. The method includes: mapping the light field video by a digital micro-mirror device (DMD) and an optical fiber coupler, a two-dimensional 2D spatial optical signal into a one-dimensional 1D input optical signal; realizing a multiply-accumulate computing model in a structure of all-optical recurrent neural network structure, and processing the 1D input signal to obtain the processed signal; and receiving the processed signal and outputting an electronic signal by a photodetector, or receiving the processed signal by a relay optical fiber for relay transmission of the processed signal. The method and system here realize light field video processing without the use of a camera and the whole system is all-optical, thus possessing the advantage in computing speed and energy-efficiency.

Abstract: A method, system, and computer program product, including generating a contrastive explanation for a decision of a classifier trained on structured data, highlighting an important feature that justifies the decision, and determining a minimal set of new values for features that alter the decision.

Abstract: Systems and methods related to charge locking circuits and a control system for qubits are provided. A system for controlling qubit gates includes a first packaged device comprising a quantum device including a plurality of qubit gates, where the quantum device is configured to operate at a cryogenic temperature. The system further includes a second packaged device comprising a control circuit configured to operate at the cryogenic temperature, where the first packaged device is coupled to the second packaged device, and where the control circuit comprises a plurality of charge locking circuits, where each of the plurality of charge locking circuits is coupled to at least one qubit gate of the plurality of qubit gates via an interconnect such that each of the plurality of charge locking circuits is configured to provide a voltage signal to at least one qubit gate.

Abstract: A method includes operating equipment to affect a variable state or condition of a space and determining a set of learned weights for a neural network by modeling an estimated cost of operating the equipment over a plurality of simulated scenarios. Each simulated scenario includes simulated measurements relating to the space. The neural network is configured to generate simulated control dispatches for the equipment based on the simulated measurements. The method also includes configuring the neural network for online control by applying the set of learned weights, applying actual measurements relating to the space to the neural network to generate a control dispatch for the equipment, and controlling the equipment in accordance with the control dispatch.

Abstract: The present disclosure relates to a system, and method for computer-based recursive learning of artificial intelligence (AI) apprentice agents. The system includes a system circuitry in communication with a database and a memory. The system circuitry is configured to receive a new data-structure comprising one or more inputs and a goal, and convert, using a perception agent, the one or more inputs of the new data-structure into one or more input feature parameters of the new data-structure. The system circuitry is configured to obtain, using a reasoning agent, an action for the new data-structure, and determine, using an evaluation agent, whether the action for the new data-structure generates the goal of the new data-structure. When it is determined that the action generates the goal of the new data-structure, the system circuitry is further configured to store the new data-structure in the database.

Abstract: A convolutional neural network processor includes an information decode unit and a convolutional neural network inference unit. The information decode unit is configured to receive a program input and weight parameter inputs and includes a decoding module and a parallel processing module. The decoding module receives the program input and produces an operational command according to the program input. The parallel processing module is electrically connected to the decoding module, receives the weight parameter inputs and includes a plurality of parallel processing sub-modules for producing a plurality of weight parameter outputs. The convolutional neural network inference unit is electrically connected to the information decode unit and includes a computing module. The computing module is electrically connected to the parallel processing module and produces an output data according to an input data and the weight parameter outputs.

Abstract: An embodiment of a graphics apparatus may include a context engine to determine contextual information, a recommendation engine communicatively coupled to the context engine to determine a recommendation based on the contextual information, and a configuration engine communicatively coupled to the recommendation engine to adjust a configuration of a graphics operation based on the recommendation. Other embodiments are disclosed and claimed.

Abstract: A system and method for allocating computational resources includes a plurality of classifiers, a memory array, and a memory controller to allocate memory from the memory array to each of the plurality of classifier. The system and method also include an optimization processor to determine an optimized bit precision value for at least one of the plurality of classifiers based upon a relative importance of the plurality of classifiers. The memory controller allocates the memory from the memory array to the plurality of classifiers based upon the determined optimized bit precision value.

Abstract: Embodiments of the present systems and methods may provide improved machine learning performance even though data drift has occurred. For example, a method may comprise providing a machine learning model in a computer system, operating the machine learning model using a first dataset to obtain results of the first dataset, operating the machine learning model using a second dataset to obtain results of the second dataset, performing statistical testing on a confidence distribution of results of the first dataset and of results of the second dataset to determine a difference in a result confidence distribution between the first dataset and of the second dataset, and determining whether data included in the second dataset has data drift relative to the first dataset based on the difference in a result confidence distribution between the first dataset and of the second dataset.

Abstract: One embodiment provides for a compute apparatus to perform machine learning operations, the compute apparatus comprising instruction decode logic to decode a single instruction including multiple operands into a single decoded instruction, the multiple operands including a first operand and a second operand, the first operand including vector of one-hot coded weights and the second operand including a vector of input data; and a general-purpose graphics compute unit including a first logic unit, the general-purpose graphics compute unit to execute the single decoded instruction, wherein to execute the single decoded instruction includes to perform multiple operations on the first set of operands and the second set of operands.

Abstract: A platform for developing data models includes a repository for kernel images, a data store of data sets and a development environment. The kernel images include a data model and configurable development code for developing the data model. The development of the data model is configurable according to development parameters for the development code. The kernel images specify the development parameters in a standardized syntax for the platform and specify the input data using standardized data types for the platform, preferably via a standardized API. The development environment is used to run sessions to develop the data models. Each session runs one of the kernel images, according to a configuration of the development parameters for the kernel image, and using one of the data sets in the data store as input data.

Abstract: An embodiment provided herein preprocesses the input samples to the classification neural network, e.g., by adding Gaussian noise to word/sentence representations to make the function of the neural network satisfy Lipschitz property such that a small change in the input does not cause much change to the output if the input sample is in-distribution. Method to induce properties in the feature representation of neural network such that for out-of-distribution examples the feature representation magnitude is either close to zero or the feature representation is orthogonal to all class representations. Method to generate examples that are structurally similar to in-domain and semantically out-of domain for use in out-of-domain classification training. Method to prune feature representation dimension to mitigate long tail error of unused dimension in out-of-domain classification. Using these techniques, the accuracy of both in-domain and out-of-distribution identification can be improved.

Abstract: A neural network training method includes inputting neuron input values of a neural network to the RRAM, and performing calculation for the neuron input values based on filters in the RRAM, to obtain neuron output values of the neural network, performing calculation based on kernel values of the RRAM, the neuron input values, the neuron output values, and backpropagation error values of the neural network, to obtain backpropagation update values of the neural network, comparing the backpropagation update values with a preset threshold, and when the backpropagation update values are greater than the preset threshold, updating the filters in the RRAM based on the backpropagation update values.

Abstract: Generally, the present disclosure is directed to novel machine-learned classification models that operate with hard attention to make discrete attention actions. The present disclosure also provides a self-supervised pre-training procedure that initializes the model to a state with more frequent rewards. Given only the ground truth classification labels for a set of training inputs (e.g., images), the proposed models are able to learn a policy over discrete attention locations that identifies certain portions of the input (e.g., patches of the images) that are relevant to the classification. In such fashion, the models are able to provide high accuracy classifications while also providing an explicit and interpretable basis for the decision.

Abstract: A system, a method, and a computer program for identifying and prioritizing a risky computing resource for security evaluation and remediation in a computer network that has a plurality of computing resources, comprising analyzing network-internal domain information to identify the risky computing resource in the computer network, generating a keyword for a cyberattack risk, analyzing open source intelligence domain information using the keyword, analyzing network-external domain information to identify additional risk attributes for the cyberattack risk, determining a ranking weight for the cyberattack risk, prioritizing the risky computing resource with respect to one or more computing resources based on the ranking weight, targeting the risky computing resource for penetration testing in accordance with the prioritization, and evaluating a threat risk of the risky computing resource to the computer network.

Abstract: Implementations of the present disclosure include methods, systems, and computer-readable storage mediums for receiving first and second data sets, both the first and second data sets including structured data in a plurality of columns, for each of the first data set and the second data set, inputting each column into an encoder specific to a column type of a respective column, the encoder providing encoded data for the first data set, and the second data set, respectively, providing a first multi-dimensional vector based on encoded data of the first data set, providing a second multi-dimensional vector based on encoded data of the second data set, and outputting the first multi-dimensional vector and the second multi-dimensional vector to a loss-function, the loss-function processing the first multi-dimensional vector and the second multi-dimensional vector to provide an output, the output representing matched data points between the first and second data sets.

Abstract: Processing circuitry for a deep neural network can include input/output ports, and a plurality of neural network layers coupled in order from a first layer to a last layer, each of the plurality of neural network layers including a plurality of weighted computational units having circuitry to interleave forward propagation of computational unit input values from the first layer to the last layer and backward propagation of output error values from the last layer to the first layer.

Abstract: Certain aspects involve a machine-learning query system that uses a dual deep learning network to service queries and other requests. In one example, a machine-learning query system services a query received from a client computing system. A dual deep learning network included in the machine-learning query system matches an unstructured input data object, received from the client computing system, to an unstructured reference data object. The matching may include generating an input feature vector by an embedding subnetwork, based on the unstructured input data object. The matching may also include generating an output probability by a relationship subnetwork, based on the input feature vector and a relationship feature vector that is based on the unstructured reference data object. The machine-learning query system may transmit a responsive message to the client system.

Abstract: According to an aspect of an embodiment, operations may include selecting, from a training dataset, a first data point as a seed data point. The operations may further include generating a population of data points by application of a genetic model on the seed data point. The population of data points may include the seed data point and a plurality of transformed data points of the seed data point. The operations may further include determining a best-fit data point in the generated population of data points based on application of a fitness function on the generated population of data points. The operations may further include executing a training operation on the DNN based on the determined best-fit data point. The operations may further include obtaining a trained DNN for the first data point based on the training operation on the DNN based on the determined best-fit data point.

Abstract: An embodiment of the present invention provides a quantization method for weights of a plurality of batch normalization layers, including: receiving a plurality of previously learned first weights of the plurality of batch normalization layers; obtaining first distribution information of the plurality of first weights; performing a first quantization on the plurality of first weights using the first distribution information to obtain a plurality of second weights; obtaining second distribution information of the plurality of second weights; and performing a second quantization on the plurality of second weights using the second distribution information to obtain a plurality of final weights, and thereby reducing an error that may occur when quantizing the weight of the batch normalization layer.

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: 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: 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: 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 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: 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: 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: 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 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: 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: 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 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: 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: 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: 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: 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: 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: 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).