Abstract: Disclosed are a method for implementing and developing a network model and a related product. The method includes: an establishment command of a neural network model is received, and a computation graph of an initial neural network model is established accordingly; a computing module selected and a connection relationship of the computing module are acquired, the computing module and the connection relationship are added into the computation graph of the initial neural network model, and an intermediate neural network model is obtained; and an establishment ending command of the neural network model is collected, the intermediate neural network model is verified according to the ending command to determine whether the computing module conflicts with other computing modules or not; if not, an established neural network model matched with a computation graph of the intermediate network model is generated, and execution codes matched with the computation graph are generated.

Abstract: Systems and methods may generate a boundary of a FOU for an interval type-2 MF based on a transformation of another boundary of the FOU. The systems and methods may receive a plurality of parameters for a type-1 MF that defines a boundary of the FOU for the interval type-2 MF and may receive at least one other parameter. The systems and methods may generate, based on a transformation of the type-1 MF utilizing the at least one parameter, a type-1 MF that defines a different boundary of the FOU. The system and methods may adjust the plurality of parameters and the at least one second parameter to adjust the FOU for use in a model representing, for example, a real-world physical system, where execution of the model executes a fuzzy inference system and generates results representing a behavior of the real-world physical system.

Abstract: A system and method for algorithmically orchestrating conversational dialogue transitions within an automated conversational system may include extracting a set of slots defined within a plurality of utterances and converting the plurality of utterances to a plurality of skeleton utterances. The method may also include grouping the plurality of skeleton utterances into a plurality of skeleton utterance groups, identifying a plurality of valid slot transition pairs based on an assessment of the plurality of skeleton utterance groups, and deriving a plurality of slot ontology groups based on the plurality of valid slot transition pairs. The system and method may use the plurality of distinct slot ontology groups and the plurality of skeleton utterances to facilitate contextually relevant dialogue transitions in the automated conversational system.

Abstract: A method includes obtaining a plurality of master sensor responses with a master sensor in a set of training fluids and obtaining node sensor responses in the set of training fluids. A linear correlation between a compensated master data set and a node data set is then found for a set of training fluids and generating node sensor responses in a tool parameter space from the compensated master data set on a set of application fluids. A reverse transformation is obtained based on the node sensor responses in a complete set of calibration fluids. The reverse transformation converts each node sensor response from a tool parameter space to the synthetic parameter space and uses transformed data as inputs of various fluid predictive models to obtain fluid characteristics. The method includes modifying operation parameters of a drilling or a well testing and sampling system according to the fluid characteristics.

Abstract: According to a method and apparatus for neural network quantization, a quantized neural network is generated by performing learning of a neural network, obtaining weight differences between an initial weight and an updated weight determined by the learning of each cycle for each of layers in the first neural network, analyzing a statistic of the weight differences for each of the layers, determining one or more layers, from among the layers, to be quantized with a lower-bit precision based on the analyzed statistic, and generating a second neural network by quantizing the determined one or more layers with the lower-bit precision.

Abstract: The present disclosure discloses a system and method for distributed neural network training. The method includes: computing, by a plurality of heterogeneous computation units (HCUs) in a neural network processing system, a first plurality of gradients from a first plurality of samples; aggregating the first plurality of gradients to generate an aggregated gradient; computing, by the plurality of HCUs, a second plurality of gradients from a second plurality of samples; aggregating, at each of the plurality of HCUs, the aggregated gradient with a corresponding gradient of the second plurality of gradients to generate a local gradient update; and updating, at each of the plurality of HCUs, a local copy of a neural network with the local gradient update.

Abstract: In one respect, there is provided a system for training a neural network adapted for classifying one or more scripts. The system may include at least one processor and at least one memory. The memory may include program code which when executed by the at least one memory provides operations including: receiving a disassembled binary file that includes a plurality of instructions; processing the disassembled binary file with a convolutional neural network configured to detect a presence of one or more sequences of instructions amongst the plurality of instructions and determine a classification for the disassembled binary file based at least in part on the presence of the one or more sequences of instructions; and providing, as an output, the classification of the disassembled binary file. Related computer-implemented methods are also disclosed.

Abstract: A machine-learning accelerator system, comprising: a plurality of controllers each configured to traverse a feature map with n-dimensions according to instructions that specify, for each of the n-dimensions, a respective traversal size, wherein each controller comprises: a counter stack comprising counters each associated with a respective dimension of the n-dimensions of the feature map, wherein each counter is configured to increment a respective count from a respective initial value to the respective traversal size associated with the respective dimension associated with that counter; a plurality of address generators each configured to use the respective counts of the counters to generate at least one memory address at which a portion of the feature map is stored; and a dependency controller computing module configured to (1) track conditional statuses for incrementing the counters and (2) allow or disallow each of the counters to increment based on the conditional statuses.

Abstract: System and method for synthesizing a controller for a dynamical system includes a feeder neural network trained to estimate an ordinary differential equation (ODE) from time series training data (X) of a trajectory having embedded angular data and configured to learn dynamics of a physical system by encoding a generalization of a Hamiltonian representation of the dynamics using a constant external control term (u). A neural ODE solver receives the estimate of the ODE from the feeder neural network and synthesizes a controller to control the system to track a reference configuration.

Abstract: A system and method are disclosed including a computer and a processor and memory. The computer receives historical sales data comprising aggregated sales data for one or more items from one or more store for at least one past time period. The computer further trains a cyclic boosting model to learn model parameters by iteratively calculating for each feature and each bin factors for at least one full feature cycle. The computer further predicts one or more demand quantities during a prediction period by applying a prediction model to historical supply chain data, wherein a training period is earlier than the prediction period, and each of the one or more demand quantities is associated with at least one item of the one or more items and at least one stocking location of the one or more stocking locations during the prediction period and rendering a demand prediction feature explanation visualization.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing cell images using neural networks. One of the methods includes obtaining data comprising an input image of one or more biological cells illuminated with an optical microscopy technique; processing the data using a stained cell neural network; and processing the one or more stained cell images using a cell characteristic neural network, wherein the cell characteristic neural network has been configured through training to receive the one or more stained cell images and to process the one or more stained cell images to generate a cell characteristic output that characterizes features of the biological cells that are stained in the one or more stained cell images.

Abstract: A convolution calculation apparatus applied for convolution calculation of a convolution layer includes a decompression circuit, a data combination circuit and a calculation circuit. The decompression circuit decompresses compressed weighting data of a convolution kernel of the convolution layer to generate decompressed weighting data. The data combination circuit combines the decompressed weighting data and non-compressed data of the convolution kernel to restore a data order of weighting data of the convolution kernel. The calculation circuit performs calculation according to the weighting data of the convolution kernel and input data of the convolution layer.

Abstract: The present invention discloses a path planning method, including the following steps: establishing an empirical map and a corresponding episodic cognitive map using a RatSLAM algorithm based on an episodic memory model; extracting a road edge in a historical memory image with a Canny operator; performing conversion to a world coordinate system from a pixel coordinate system based on the road edge, and preliminarily judging connectivity according to slope of the road edge; continuously injecting energy into the potential path detection network according to continuous observation of a potential path, so as to further judge the road connectivity; fusing the detected potential path and the original episodic cognitive map, and correspondingly updating the empirical map; and planning a path based on the updated episodic cognitive map. The potential safe path in an environment may be detected, and a better path may be planned based on the updated episodic memory model.

Abstract: A sensor includes: a correlation matrix calculator which calculates a correlation matrix from biological information extracted using reception signals obtained by receiving, in a predetermined period, signals transmitted to a predetermined space; a first number information calculator which calculates first number information; a MUSIC spectrum calculator which estimates a candidate of a position of at least one living body and outputs a likelihood spectrum; and a second number information calculator which estimates a position or second number information, which is a total number of living bodies with an increased degree of likelihood, from first position information possibly including a plurality of position candidates.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform obtaining an input low resolution (LR) image comprising a height, a width, and a number of channels, implementing a feature learning deep neural network (DNN) configured to compute a feature tensor based on the input LR image, generating, by an upscaling DNN, a high resolution (HR) image, having a higher resolution than the input LR image, based on the feature tensor computed by the feature learning DNN, wherein a networking structure of the upscaling DNN differs depending on different scale factors, and wherein a networking structure of the feature learning DNN is a same structure for each of the different scale factors.

Abstract: According to some disclosed embodiments an action is performed by an electronic social agent. The electronic social agent collects a first dataset indicating the user's state, the user's environment state, and a first user response to the performed action. Then, it is determined whether it is desirable to collect a second response from the user and, if so, it is further determined whether to generate a question to be presented to the user based on an analysis of a first dataset and the first user response. Then, an optimal time for presenting the question to the user is determined. A question that is based on the collected data and the first user response is generated by the electronic social agent for actively collecting an additional user response. Then, based on the collected additional user response, the decision-making model of the electronic social agent is updated and improved.

Abstract: Given an input image, an image enhancement task, and no external examples available to train on, an Image-Specific Deep Network is constructed tailored to solve the task for this specific image. Since there are no external examples available to train on, the network is trained on examples extracted directly from the input image itself. The current solution solves the problem of Super-Resolution (SR), whereas the framework is more general and is not restricted to SR.

Abstract: A method, a computer program with instructions, and a device for predicting a course of a road based on radar data of a motor vehicle. The radar data to be processed is received and then accumulated in a measuring grid. Subsequently, clusters are formed for objects in the measuring grid. Cluster descriptions are generated for the clusters. The resulting clusters are processed to determine polynomials for describing the road edges. The polynomials are finally output for further use.

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: To provide a robust information processing system against attacks by Adversarial Example. A neural network model 608, a latent space database 609 for storing position information in a latent space in which first output vectors, which are output vectors of a predetermined hidden layer included in the neural network model, are embedded concerning input data used for learning of the neural network model, and an inference control unit 606 for making an inference using the neural network model and the latent space database are provided. The inference control unit infers the input data based on the positional relationship between the second output vector, which is an output vector of the predetermined hidden layer concerning input data to be inferred, and the first output vectors in said latent space.

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: Disclosed herein are methods, systems, and computer-readable media for training a machine learning model to label unlabeled data and/or perform automated actions. In an embodiment, a method comprises receiving unlabeled digital video data, generating pseudo-labels for the unlabeled digital video data, the generating comprising receiving labeled digital video data, training an inverse dynamics model (IDM) using the labeled digital video data, and generating at least one pseudo-label for the unlabeled digital video data, wherein the at least one pseudo-label is based on a prediction, generated by the IDM, of one or more actions that mimic at least one timestep of the unlabeled digital video data. In some embodiments, the method further comprises adding the at least one pseudo-label to the unlabeled digital video data and further training the IDM or a machine learning model using the pseudo-labeled digital video data.

Abstract: Systems and methods for improving a machine learning model are described. In an embodiment, a computing system stores a plurality of training examples comprising training inputs and training outputs. The computing system generates a machine learning model and training the machine learning model using the plurality of training examples. The computing system receives a particular input for the machine learning system and, using the particular input and the machine learning system, computes a particular output. For each training example of the plurality of training examples, the computing system adjusts a weight of the training example on the machine learning system and computes a relative numerical impact on the particular output for the training example, the relative numerical impact reflecting an importance of each training example on the particular output relative to an importance of the other training examples of the plurality of training examples on the particular output.

Abstract: An off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

Abstract: There is provided a computing apparatus that includes: a retaining unit configured to retain an approximation table that approximately represents an activation function of a neural network, the approximation table mapping between a plurality of discrete input samples of the activation function and output samples respectively corresponding to the plurality of input samples; and a computing unit configured to convert an input value of activation function computation to an output value using the approximation table retained by the retaining unit when the activation function is selected for the activation function computation. The plurality of input samples of the approximation table are set such that input samples more distant from a reference point in the domain of the activation function have a larger neighboring sample interval.

Abstract: The invention relates to a signal analyzer, comprising a signal receiving unit configured to receive a signal, in particular a radio frequency (RF) signal, a digitizing unit configured to digitize the received signal, and a trigger detection unit configured to detect a trigger event in the digitized signal. The signal analyzer further comprises an acquisition unit configured to store a segment of the digitized signal in a memory of the signal analyzer if the trigger detection unit detects the trigger event in the digitized signal, and an anomaly search unit configured to analyze the stored segment of the digitized signal in order to detect signal anomalies, in particular glitches, in the stored segment of the digitized signal.

Abstract: A system and method is disclosed for automated cross-node communication in a distributed directed acyclic graph. The method can include identifying a directed acyclic graph (“DAG”) overlaying a plurality of nodes and identifying the nodes underlying the DAG. A subordinate DAG can be generated in an entry vertex of the DAG. The subordinate DAG can include a vertex for each of the nodes underlying the DAG. Data and metadata can be received at the entry vertex. The data can be delivered to a next vertex in the DAG, and the metadata can be communicated to nodes underlying the DAG via the subordinate DAG.

Abstract: A memory controller includes an interface and a processor. The interface communicates with memory cells organized in multiple Word Lines (WLs). The processor is configured to read a Code Word (CW) of an Error Correction Code (ECC) from a group of multiple memory cells belonging to a target WL, to calculate for a given memory cell (i) a first soft metric, depending on a first threshold voltage of a first neighbor memory cell in a first WL neighboring the target WL, and (ii) a second soft metric, depending on a second threshold voltage of a second neighbor memory cell in a second WL neighboring the target WL, to calculate a combined soft metric based on both the first and second soft metrics and assign the combined soft metric to the given memory cell, and to decode the CW based on the combined soft metric, to produce a decoded CW.

Abstract: In one embodiment, a method includes obtaining candidate data generated by a vehicle. The candidate data comprises a subset of sensor data identified based on a set of neural network models executing on the vehicle. The method also includes determining whether the candidate data can be associated with one or more categories of a set of categories for training data based on a set of categorization models. The method further includes associating the candidate data with the first category in response to determining that the candidate data can be associated with at a first category of the set of categories. The method further includes determining whether the candidate data can be associated with a second category. The set of categories lacks the second category. The method further includes including the second category in the set of categories in response to determining that the candidate data can be associated with the second category.

Abstract: Embodiments are generally directed to an adaptive deformable kernel prediction network for image de-noising. An embodiment of a method for de-noising an image by a convolutional neural network implemented on a compute engine, the image including a plurality of pixels, the method comprising: for each of the plurality of pixels of the image, generating a convolutional kernel having a plurality of kernel values for the pixel; generating a plurality of offsets for the pixel respectively corresponding to the plurality of kernel values, each of the plurality of offsets to indicate a deviation from a pixel position of the pixel; determining a plurality of deviated pixel positions based on the pixel position of the pixel and the plurality of offsets; and filtering the pixel with the convolutional kernel and pixel values of the plurality of deviated pixel positions to obtain a de-noised pixel.

Abstract: One embodiment includes a method for generating representations of inputs with missing values. The method includes steps for receiving an input includes a set of one or more values for several features, wherein the set of values for at least one of the several features includes values for each of several points in time, and for identifying a missingness pattern of the input, wherein the missingness pattern for the at least one feature indicates whether the set of values is missing a value for each of the several points in time. The method further includes steps for determining a set of one or more transformation weights based on the missingness pattern, and transforming the input based on the determined transformation weights.

Abstract: In order to enable stabilizing control of communication in a communication network, a system according to an aspect of the present disclosure includes: an obtaining means for obtaining work-related information related to human work in network operation; and a training means for training a machine learning based controller for controlling communication in a communication network, based on the work-related information.

Abstract: This disclosure involves generating graph data structures that model inter-feature dependencies for use with machine-learning models to predict end-user behavior. For example, a processing device receives an input dataset and a request to modify a first input feature of the input dataset. The processing device uses a graph data structure that models the inter-feature dependencies to modify the input dataset by propagating the modification of the first input feature to a second input feature dependent on the first input feature. The modification to the second input feature is a function of at least (a) the value of the first input feature and (b) a weight assigned to an edge linking the first input feature to the second input feature within the directed graph. The processing device then applies a trained machine-learning model to the modified input dataset to generate a prediction of an outcome.

Abstract: The present disclosure provides an image classification method, apparatus, and device, and a readable storage medium. The image classification method includes: processing an image to be processed, by using a first convolutional network, to obtain a first feature map; processing the first feature map, by using a residual network, to obtain a second feature map, wherein the residual network includes a depth separable convolutional layer; and processing the second feature map, by using a second convolutional network, to determine a category label of the image to be processed.

Abstract: A system and method are disclosed for providing a private multi-modal artificial intelligence platform. The method includes splitting a neural network into a first client-side network, a second client-side network and a server-side network and sending the first client-side network to a first client. The first client-side network processes first data from the first client, the first data having a first type. The method includes sending the second client-side network to a second client. The second client-side network processes second data from the second client, the second data having a second type. The first type and the second type have a common association. Forward and back propagation occurs between the client side networks and disparate data types on the different client side networks and the server-side network to train the neural network.

Abstract: A data structuring system that provides a user interface to enable data wrangling and modeling, and methods for making and using the same.

Abstract: An endoscopic image processing method is provided. The method can include acquiring a current endoscopic image of a to-be-examined user, and predicting the current endoscopic image by using a deep convolutional network based on a training parameter. The training parameter can be determined according to at least one first endoscopic image and at least one second endoscopic image transformed from the at least one first endoscopic image, where the at least one endoscopic image corresponds to a human body part. The method can further include determining an organ category corresponding to the current endoscopic image. The method can make a prediction process more intelligent and more robust, thereby improving resource utilization of a processing apparatus.

Abstract: Embodiments for providing an enhanced codebase in a computing environment by a processor. One or more container specification files may be automatically generated for a codebase based on one or more extracted attribute names and values.

Abstract: Computer systems and computer-implemented methods modify a machine learning network, such as a deep neural network, to introduce judgment to the network. A “combining” node is added to the network, to thereby generate a modified network, where activation of the combining node is based, at least in part, on output from a subject node of the network. The computer system then trains the modified network by, for each training data item in a set of training data, performing forward and back propagation computations through the modified network, where the backward propagation computation through the modified network comprises computing estimated partial derivatives of an error function of an objective for the network, except that the combining node selectively blocks back-propagation of estimated partial derivatives to the subject node, even though activation of the combining node is based on the activation of the subject node.

Abstract: Systems as described herein may label data to preserve privacy. An annotation server may receive a document comprising a collection of text representing a plurality of confidential data from a first computing device. The annotation server may convert the document to a plurality of text embeddings. The annotation server may input the text embeddings into a machine learning model to generate a plurality of synthetic images, and receive a label for each of the plurality of synthetic images from a third-party labeler. Accordingly, the annotation server may send the confidential data and the corresponding labels to a second computing device.

Abstract: Embodiments for ensemble training in a distributed marketplace in a computing environment. One or more ensemble machine learning models may be provided from a plurality of machine learning models competing within the distributed marketplace that achieve a performance on ensemble training data equal to or greater than a selected performance threshold, wherein the distributed marketplace is a blockchain.

Abstract: The display device includes a plurality of pixels, a data driver, and a timing controller. The plurality of pixels are connected to a plurality of scan lines and a plurality of data lines. The data driver supplies a data voltage to the plurality of data lines in a light-emitting mode and supplies a neural network input voltage to the plurality of data lines in an artificial neural network mode. The timing controller is in an artificial neural network mode, and supplies a weight value control signal for performing a deep learning operation by using at least one of the plurality of pixels to the data driver. The weight value control signal is generated based on a predetermined weight value.

Abstract: A method for programming an activation function is provided. The method includes generating segment data for segmenting the activation function; segmenting the activation function into a plurality of segments using the segment data; and approximating at least one segment of the plurality of segments as a programmable segment. An apparatus for performing the method may include a programmable activation function generator configured to generate segment data for segmenting an activation function; segment the activation function into a plurality of segments using the generated segment data; and approximate at least one segment of the plurality of segments as a programmable segment. By using segment data, various non-linear activation functions, particularly newly proposed or known activation functions with some modifications, can be programmed to be processable in hardware.

Abstract: A diagnostic system for model governance is presented. The diagnostic system includes an auto-encoder to monitor model suitability for both supervised and unsupervised models. When applied to unsupervised models, the diagnostic system can provide a reliable indication on model degradation and recommendation on model rebuild. When applied to supervised models, the diagnostic system can determine the most appropriate model for the client based on a reconstruction error of a trained auto-encoder for each associated model. An auto-encoder can determine outliers among subpopulations of consumers, as well as support model go-live inspections.

Abstract: Disclosed herein is technology for performing predictive modeling to identify inputs for a manufacturing process. An example method may include receiving expected output data for a manufacturing process, wherein the expected output data defines an attribute of an output of the manufacturing process; accessing a plurality of machine learning models that model the manufacturing process; determining, using a first machine learning model, input data for the manufacturing process based on the expected output data for the manufacturing process, wherein the input data comprises a value for a first input and a value for a second input; combining the input data determined using the first machine learning model with input data determined using the second machine learning model to produce a set of inputs for the manufacturing process, wherein the set of inputs comprises candidate values for the first input and candidate values for the second input.

Abstract: A processing apparatus includes a driver configured to drive a controlled object, and a controller configured to control the driver by generating a command value to the driver based on a control error. The controller includes a first compensator configured to generate a first command value based on the control error, a second compensator configured to generate a second command value based on the control error, and an adder configured to obtain the command value by adding the first command value and the second command value. The second compensator includes a neural network for which a parameter value is decided by learning, and input parameters input to the neural network include at least one of a driving condition of the driver and an environment condition in a periphery of the controlled object in addition to the control error.

Abstract: Certain aspects of the present disclosure are directed to methods and apparatus for configuring a multiply-accumulate (MAC) block in an artificial neural network. A method generally includes receiving, at a neural processing unit comprising one or more logic elements, at least one input associated with a use-case of the neural processing unit; obtaining a set of weights associated with the at least one input; selecting a precision for the set of weights; modifying the set of weights based on the selected precision; and generating an output based, at least in part, on the at least one input, the modified set of weights, and an activation function.

Abstract: Systems and methods for natural language processing are described. One or more embodiments of the disclosure provide an entity matching apparatus trained using machine learning techniques to determine whether a query name corresponds to a candidate name based on a similarity score. In some examples, the query name and the candidate name are encoded using a character encoder to produce a regularized input sequence and a regularized candidate sequence, respectively. The regularized input sequence and the regularized candidate sequence are formed from a regularized character set having fewer characters than a natural language character set.

Abstract: A segmentation system utilizes a supervised learning method and a clustering analysis to identify clusters, thereby segmenting a population into groups, where the clusters are associated with various conversion potentials that indicate the probability of an event. The segmentation system employs the supervised learning method to train a model on training data comprising historical conversion data and features associated with members of the group. A subset of features is selected from a ranked order that is determined using weights generated by the supervised learning. A clustering analysis is performed for a population with respect to the subset to generate clusters. A superior cluster is identified based on it having a conversion potential greater than a conversion potential of another cluster. In a marketing context, the system can be employed to identify a superior cluster of users that have a higher conversion potential in response to an advertisement campaign.

Abstract: [Object] To provide a lightning threat information-providing apparatus, a lightning threat information-providing method, and a program that are capable of providing a user with accurate information regarding a lightning threat.