The present disclosure discloses an image haze removal method and apparatus, and a device. The method includes: acquiring a hazy image to be processed; and obtaining a haze-free image corresponding to the hazy image by inputting the hazy image into a pre-trained haze removal model. The present disclosure uses the residual dual attention fusion modules as basic modules of the neural network, so that each feature map can obtain pixel features while enhancing the global dependence, thus improving the image dehazing effect.

An information processing system including: a storage section that stores information about a plurality of agents capable of dialogue with a user, each agent having different attributes; a communication section that receives a message from the user from a client terminal, and also replies to the client terminal with a response message; and a control section that executes control to select a specific agent from the plurality of agents, according to an instruction from the user, record attributes of the specific agent updated according to dialogue between the specific agent and the user as the attributes of a user agent, specify a partner user who most resembles the attributes of the user agent by comparing the attributes of the user agent and attributes of a plurality of actually existing partner users, and notify the user of the existence of the partner user at a predetermined timing.

Disclosed are an artificial intelligence learning method and an operating method of a robot using the same. An on-screen label is generated based on image data acquired through a camera, an off-screen label is generated based on data acquired through other sensors, and the on-screen label and the off-screen label are used in learning for action recognition, thereby raising action recognition performance and recognizing a user's action even in a situation in which the user deviates from a camera's view.

The present disclosure describes a technology platform for creating and updating records of resources in a ledger. To create a record, a tenant organization may prepare a record to write to the ledger that may be flagged as temporary. Metadata may be added to the record, which flags the record as temporary. The metadata may comprise a unique code and an identification of a user that can approve the temporary record. The unique code and the identification may be sent, by the technology platform, to a device associated with one or more approving devices. Upon receiving the code and the identification of the transaction, the device may sign the unique code and invoke a routine based on the identification. The routine may fetch the temporary record. The device may compare the unique code to a code stored in the metadata of the temporary record. Upon valid verification of the unique code, the device may indicate authorization of the write. Based on the authorization, a proxy node associated with the technology platform may write a definitive record to the ledger based on the temporary record.

The present disclosure describes a technology platform for creating and updating records of resources in a ledger. To create a record, a tenant organization may prepare a record to write to the ledger that may be flagged as temporary. Metadata may be added to the record, which flags the record as temporary. The metadata may comprise a unique code and an identification of a user that can approve the temporary record. The unique code and the identification may be sent, by the technology platform, to a device associated with one or more approving devices. Upon receiving the code and the identification of the transaction, the device may sign the unique code and invoke a routine based on the identification. The routine may fetch the temporary record. The device may compare the unique code to a code stored in the metadata of the temporary record. Upon valid verification of the unique code, the device may indicate authorization of the write. Based on the authorization, a proxy node associated with the technology platform may write a definitive record to the ledger based on the temporary record.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating and executing biological convolutional neural network layers. One of the methods obtaining a network input; and processing the network input using a neural network to generate a network output, wherein the neural network is configured to perform operations comprising: generating a layer input to a convolutional neural network layer based on the network input; and generating a layer output of the convolutional neural network layer based on the layer input, comprising applying a convolutional kernel to the layer input, wherein the convolutional kernel corresponds to a specified neuron in a brain of a biological organism and values of parameters of the convolutional kernel are based on synaptic connectivity between the specified neuron and each of a plurality of other neurons in the brain of the biological organism.

Embodiments of the present disclosure provide a method for controlling virtual pets and a smart projection device. The method is applicable to the smart projection device. The smart projection device may project the virtual pets to the real space, display the same in a predetermined style, and may change different styles at will, such that the user may obtain the experience of raising different pets. In addition, the smart projection device may also receive the instruction information from the user, and control the virtual pets to conduct corresponding interaction behaviors according to the instruction information.

Techniques for generating multiple-resolutions of time series data are described. An input irregular time series having a plurality of data points is obtained, each data point of the plurality of data points including a timestamp and a feature vector. Based on the input irregular time series, multiple variant time series are generated. A data point in one of the variant time series is based in part on a combination of at least two data points of the input irregular time series. The multiple variant time series can then be used for machine learning tasks such as training a machine learning model or using a machine learning model to infer an output.

Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for training a neural network to control a real-world agent interacting with a real-world environment to cause the real-world agent to perform a particular task. One of the methods includes training the neural network to determine first values of the parameters by optimizing a first task-specific objective that measures a performance of the policy neural network in controlling a simulated version of the real-world agent; obtaining real-world data generated from interactions of the real-world agent with the real-world environment; and training the neural network to determine trained values of the parameters from the first values of the parameters by jointly optimizing (i) a self-supervised objective that measures at least a performance of internal representations generated by the neural network on a self-supervised task performed on the real-world data and (ii) a second task-specific objective.

An apparatus and method are provided for machine learning method using a network of agents. The agents are arranged in a network with respective links between pairs of agents, and the links enabling the exchange information. Different agents can apply different reasoning paradigms corresponding to different approaches to machine learning and artificial intelligence. These disparate approaches are seamlessly integrated to aggregate decisions and learning performed using different approaches using an economics model in which a Nash equilibrium is reached through the exchange of information. Each agent selects which other agents to exchange information with by seeking to optimize preference, utility, and objective functions, and these function include how well the agents obtain an assigned goal subject to other desirable features and characteristics (e.g., enforcing diversity).