Abstract: Disclosed are a training method and device for an analog hardware neural network, the method includes: inputting analog signals into the analog hardware neural network, and measuring output results of the analog hardware neural network after the analog hardware neural network establishes a response to the inputted signals; injecting a perturbation signal into a node while the analog hardware neural network is running; and updating parameters of the analog hardware neural network according to results of two measurements. The present disclosure has a higher recognition rate and generalization capabilities, and is applicable to training all types of analog hardware neural network, thereby solving the problem of reliance on a mathematical model in training of the analog hardware neural network.

Abstract: Disclosed herein is a computerized method including operations of receiving a request for a treatment recommendation, where the request includes a user ID and where a treatment is a notification, alert, or message to be provided by a network device. The operations further include retrieving a set of user data from an aggregated user data table according to the user ID and treatment data comprised of data related to a set of predefined treatments from a treatment datastore, determine a score for each of the set of candidate treatments through processing of the set of user data, a set of candidate treatments, and a configured objective as input by a machine learning model, generating a ranked list of treatments based on the scoring provided by the machine learning model, and providing the ranked list of the set of candidate treatments and the set of candidate treatments to the network device.

Abstract: Disclosed herein is a computerized method including operations of obtaining user attributes and user event data, generating user embeddings and aggregated user features from the user event data and the user attributes, obtaining treatment attributes and a set of treatments corresponding to the treatment attributes, generating treatment embeddings and aggregated treatment features from the set of treatments and the treatment attributes, and generating a trained machine learning model by processing the user embeddings, the aggregated user features, the treatment embeddings, and the aggregated treatment features by a machine learning algorithm, wherein the trained machine learning machine is configured to generate a score for each treatment of the set of treatments indicative of a likelihood that serving of a particular treatment will result in performance of an objective. The user event data may include event sequence data indicating a sequence of user input actions corresponding to one or more treatments.

Abstract: A method and a system for constructing a soil water movement model based on the physical information neural networks are provided. The soil water movement model is constructed by fusing the physical information neural network and a control equation of the soil water movement model, and the model adopts automatic differentiation to replace difference operation of grid scale, so that the calculation error caused by equation discretization in the solving process of numerical differentiation is avoided, and the calculation accuracy is improved; and the automatic differentiation mode is mainly carried out aiming at the output of a neural network, so that the numerical value of gradient calculation is more accurate.

Abstract: The present disclosure provides methods and systems for recommending pick-up points. The method may include obtaining information of a searched point of interest determined by a user; determining a first set of candidate pick-up points based at least on the information of the searched point of interest, the first set of candidate pick-up points including a plurality of candidate pick-up points; determining at least one recommended pick-up point through a preset algorithm based at least on the first set of candidate pick-up points, and displaying the at least one recommended pick-up point to the user.

Abstract: Disclosed is a method for correcting a dot product error of a variable resistor array. The method includes: (1) initializing and writing a target conductance matrix into the variable resistor array; (2) calculating an effective conductance matrix of the variable resistor array; and (3) comparing the effective conductance matrix obtained in step (2) with the target conductance matrix, finishing executing the method in a case that a convergence condition is satisfied, and otherwise, continuing to execute steps as follows: multiplying a difference matrix by an adjustment coefficient ?, such that an error conductance matrix is obtained; adjusting a conductance matrix Gwrite of actual variable resistors to Gwrite=G?write? Gerror, where Gerror is the error conductance matrix, G?write is a conductance matrix actually written into variable resistors last time; and executing steps (2) and (3) repeatedly after adjustment until a stop condition in step (3) is satisfied.

Abstract: The present disclosure provides methods and systems for recommending pick-up points. The method may include obtaining information of a searched point of interest determined by a user; determining a first set of candidate pick-up points based at least on the information of the searched point of interest, the first set of candidate pick-up points including a plurality of candidate pick-up points; determining at least one recommended pick-up point through a preset algorithm based at least on the first set of candidate pick-up points, and displaying the at least one recommended pick-up point to the user.

Abstract: A user verification system is configured to identify likely interactors approaching points of interaction to ensure accurate interactions and to provide loyalty rewards. In an example, a interaction system installs a user verification device with a stereo camera at an interacting device to capture images of the user and to obtain data from the device. The user verification device uses the stereo camera to determine the location of the user to determine if the user is a likely interactor. The user verification device recognizes motions of the user that are indicative of an interactor, such as reaching across the counter or looking at the operator. The user verification device identifies or verifies the interactor based on the record data or the display data. If the user is the likely interactor, then the system conducts a hands-free interaction with the user account or provides loyalty rewards to the user account.

Abstract: A service provider system registers with a service system. A user establishes an account with the service system and the service system establishes a facial template associated with the user account. The service system transmits, to a service provider device at a location, identification information and transmits a shared encryption key to a user computing device associated with the user. The user enters the merchant location carrying the user computing device. The service device receives the encryption key from the user device and decrypts the identification information associated with the user using the encryption key. The user initiates a service request and the service provider device verifies the identity of the user via the facial template associated with the user by generating a facial template based on an image captured of the user to compare against the facial template associated with the user. The service device processes the service request.

Abstract: A user verification system is configured to identify likely interactors approaching points of interaction to ensure accurate interactions and to provide loyalty rewards. In an example, a interaction system installs a user verification device with a stereo camera at an interacting device to capture images of the user and to obtain data from the device. The user verification device uses the stereo camera to determine the location of the user to determine if the user is a likely interactor. The user verification device recognizes motions of the user that are indicative of an interactor, such as reaching across the counter or looking at the operator. The user verification device identifies or verifies the interactor based on the record data or the display data. If the user is the likely interactor, then the system conducts a hands-free interaction with the user account or provides loyalty rewards to the user account.

Abstract: An account management system identifies a user near a location from among a plurality of facial images. An account management system establishes a facial template for a user based on an image of the user. When the user is approaching a location, the system receives an indication that an identification is desired and receives a plurality of facial images captured by a camera proximate to the location. The system identifies each pupil in a first image of the plurality of facial images and calculates a distance between each pupil. The system compares the calculated distance to a standard distance, the standard distance being a determined distance or distance range between pupils of a person near the location. Based on the comparison, the system determines whether the first image is associated with a user near the location. If not, the method is repeated on one or more other images.

Abstract: A user verification system is configured to identify likely interactors approaching points of interaction to ensure accurate interactions and to provide loyalty rewards. In an example, a interaction system installs a user verification device with a stereo camera at an interacting device to capture images of the user and to obtain data from the device. The user verification device uses the stereo camera to determine the location of the user to determine if the user is a likely interactor. The user verification device recognizes motions of the user that are indicative of an interactor, such as reaching across the counter or looking at the operator. The user verification device identifies or verifies the interactor based on the record data or the display data. If the user is the likely interactor, then the system conducts a hands-free interaction with the user account or provides loyalty rewards to the user account.

Abstract: A service provider system registers with a service system. A user establishes an account with the service system and the service system establishes a facial template associated with the user account. The service system transmits, to a service provider device at a location, identification information and transmits a shared encryption key to a user computing device associated with the user. The user enters the merchant location carrying the user computing device. The service device receives the encryption key from the user device and decrypts the identification information associated with the user using the encryption key. The user initiates a service request and the service provider device verifies the identity of the user via the facial template associated with the user by generating a facial template based on an image captured of the user to compare against the facial template associated with the user. The service device processes the service request.