A method and apparatus for training an information adjustment model of a charging station, an electronic device, and a storage medium are provided. An implementation comprises: acquiring a battery charging request, and determining environment state information corresponding to each charging station in a charging station set; determining, through an initial policy network, target operational information of each charging station in the charging station set for the battery charging request, according to the environment state information; determining, through an initial value network, a cumulative reward expectation corresponding to the battery charging request according to the environment state information and the target operational information; training the initial policy network and the initial value network by using a deep deterministic policy gradient algorithm; and determining the trained policy network as an information adjustment model corresponding to each charging station.

Accuracy of a model extracting a graph structure as an intermediate representation from input data is improved. An encoding unit (100) extracts a feature amount of each of a plurality of vertices included in a graph structure (Tr) from input data (10), and calculates a likelihood that an edge is connected to the vertex. A sampling unit (130) determines the graph structure (Tr) based on a conversion result of a Gumbel-Softmax function for the likelihood. A learning unit (150) optimizes a decoding unit (140) and the encoding unit (100) by back propagation using a loss function including an error (L.sub.P) between output data (20) generated from the graph structure (Tr) and correct data.

A computer implemented method for determining at least one target parameter set for a flow chemistry setup (110) for flow chemistry in slugs is disclosed. The method is a self-learning method. The method comprises the following steps: a) determining at least one process variable by using at least one sensor (122) of a flow chemistry setup (110); b) training of at least one machine-learning model (126) based on the process variable; c) determining the target parameter set by applying an optimizing algorithm in terms of at least one optimization target on the trained machine-learning model (126); d) providing the determined target parameter set and/or considering the determined target parameter set for evaluating a flow chemistry setup (110) and/or for evaluating at least one flow chemistry product.

A computer implemented method for determining at least one target parameter set for a flow chemistry setup (110) for flow chemistry in slugs is disclosed. The method is a self-learning method. The method comprises the following steps: a) determining at least one process variable by using at least one sensor (122) of a flow chemistry setup (110); b) training of at least one machine-learning model (126) based on the process variable; c) determining the target parameter set by applying an optimizing algorithm in terms of at least one optimization target on the trained machine-learning model (126); d) providing the determined target parameter set and/or considering the determined target parameter set for evaluating a flow chemistry setup (110) and/or for evaluating at least one flow chemistry product.

Embodiments disclose a method and system for a scene-aware audio-video representation of a scene. The scene-aware audio video representation corresponds to a graph of nodes connected by edges. A node in the graph is indicative of the video features of an object in the scene. An edge in the graph connecting two nodes indicates an interaction of the corresponding two objects in the scene. In the graph, at least one or more edges are associated with audio features of a sound generated by the interaction of the corresponding two objects. The graph of the audio-video representation of the scene may be used to perform a variety of different tasks. Examples of the tasks include one or a combination of an action recognition, an anomaly detection, a sound localization and enhancement, a noisy-background sound removal, and a system control.

A computer-implemented method for identifying a topology of a power distribution grid having a number of transformers includes acquiring measurement signals of one or more electrical quantities pertaining to nodes of the power distribution grid. A graph representation is generated using the measurement signals and grid topological information, wherein the measurement signals pertaining to respective nodes are used to derive node features and the grid topological information is used to encode edges representing certain and uncertain connections between the nodes. The graph representation is processed using a graph neural network to classify the nodes and output a mapping of each of the nodes to one of the transformers, whereby a status of the uncertain connections is determined.

Apparatuses, systems, and techniques to indicate an extent, to which text corresponds to one or more images. In at least one embodiment, an extent to which text corresponds to one or more images is indicated using one or more neural networks and used to train the one or more neural networks.

An electronic apparatus performs a method of recovering a complete and dense point cloud from a partial point cloud. The method includes: constructing a sparse but complete point cloud from the partial point cloud through a contrastive teacher-student neural network; and transforming the sparse but complete point cloud to the complete and dense point cloud. In some embodiments, the contrastive teacher-student neural network has a dual network structure comprising a teacher network and a student network both sharing the same architecture. The teacher network is a point cloud self-reconstruction network, and the student network is a point cloud completion network.

A systems including one or more processors and one or more non-transitory computer readable media storing computing instructions that, when executed on the one or more processors, perform: receiving a plurality of images from one or more devices, the images corresponding to a store shelf of a store; combining the plurality of images to generate a shelf image corresponding to the store shelf; encoding the shelf image into a first processing format; processing the shelf image in the first processing format with a neural network using pre-trained weights; determining positions in the shelf image that correspond to an out-of-stock detection based on outputs from the neural network; and generating a report for the out-of-stock detection, the report including an indication of coordinates of the out-of-stock detection and an item of the store that corresponds to the coordinates. Other embodiments are described.

A distributed learning system and method comprises the steps of: obtaining an initial global weight broadcast and applying the initial global weight to a local model; performing a simulation test on a local model using test data obtained in advance according to a pre-designated task to be performed by the distributed learning device;

when the local model to which the global weight is applied passes the simulation test according to a pre-designated test pass criterion, pruning in a pre-designated manner for a plurality of elements of the global weight; initializing values of unpruned residual elements in the global weight; locally training the local model to which the initialized weight is applied using learning data prepared in advance according to the task, and transmitting a local weight to the central server; and receiving the updated global weight for the next round according to the local weight in the central server.