Abstract: A display substrate and a display device. The display substrate includes a base, an insulating layer, a crack barrier structure, and a signal line. The crack barrier structure is located in a peripheral area, and at least a part of an orthographic projection of the crack barrier structure onto the base extends in an extension direction of a boundary of a display area. The crack barrier structure includes: a groove structure and a blocking portion, the groove structure is in the insulating layer, and a part of the blocking portion is located in the groove structure. The signal line is located at the peripheral area, and includes a top surface facing away from the base, and a side surface located between the top surface and the base, and at least a part of the side surface away from the display area is between the blocking portion and the groove structure.

Abstract: A machine learning method comprises: receiving input data comprising a set of feature variables each indicating features of a plurality of entities; encoding partial order relations between entities of the plurality of entities as a set of logic rules; constructing a hypergraph comprising a plurality of vertices representing the entities of the plurality of entities and a plurality of hyperlinks linking similar entities of the plurality of entities; adding directed edges to the hypergraph to represent partial order interactions between entities to form a partial order hypergraph; representing the partial order hypergraph as a set of matrices; forming an objective function using the logic rules and matrices of the set of matrices; minimizing the objective function to obtain a prediction function; and outputting an indication of the prediction function.

Abstract: A system includes an energy source, a focusing system, and a controller. The energy source is configured to output energy pulses to the focusing system. A chamber surrounds at least a portion of a metallic substrate and contain a liquid in contact with a surface of the metallic substrate. The controller is configured to cause the energy source to output energy pulses and cause the focusing system to focus a focal volume of the energy pulses at or near the surface of the metallic substrate that is in contact with the liquid to create micro-scale or smaller surface texturing on the metallic substrate.

Abstract: A system includes an energy source, a focusing system, and a controller. The energy source is configured to output energy pulses to the focusing system. A chamber surrounds at least a portion of a metallic substrate and contains a liquid in contact with a surface of the metallic substrate. The controller is configured to cause the energy source to output energy pulses and cause the focusing system to focus a focal volume of the energy pulses at or near the surface of the metallic substrate that is in contact with the liquid to create micro-scale or smaller surface texturing on the metallic substrate.

Abstract: A system may include an emitting device and a controller. The emitting device may be adapted to emit a first laser beam and a second laser beam. The controller may include one or more processors and may be operably coupled to the emitting device to control emission of the first and second laser beams. The controller may be adapted to remove a portion of a workpiece to form an exposed surface of the workpiece with the first laser beam using the emitting device and to remove a portion of the exposed surface with the second laser beam using the emitting device.

Abstract: A machine learning method comprises: receiving input data comprising a set of feature variables each indicating features of a plurality of entities; encoding partial order relations between entities of the plurality of entities as a set of logic rules; constructing a hypergraph comprising a plurality of vertices representing the entities of the plurality of entities and a plurality of hyperlinks linking similar entities of the plurality of entities; adding directed edges to the hypergraph to represent partial order interactions between entities to form a partial order hypergraph; representing the partial order hypergraph as a set of matrices; forming an objective function using the logic rules and matrices of the set of matrices; minimizing the objective function to obtain a prediction function; and outputting an indication of the prediction function.

Abstract: Methods and systems for predictive analysis are disclosed. A predictive analysis method comprises receiving input data comprising an indication of a user, an indication of an item, a user feature vector indicating features of the user and an item feature vector indicating features of the item; and constructing a cross feature vector indicating values for cross features between features of the user and features of the user. Embedding vectors derived from the cross feature vector, the user feature vector and the item feature vector are input into an attention network to determine a set of attentive weights which indicate cross features between the user and item features. These cross features are used in the identification of a user item preference.

Abstract: In some examples, a system includes an energy source, a focusing system, and a controller. The energy source is configured to output energy pulses to the focusing system. A chamber may surround at least a portion of a metallic substrate and contain a liquid in contact with a surface of the metallic substrate. The controller may be configured to cause the energy source to output energy pulses and cause the focusing system to focus a focal volume of the energy pulses at or near the surface of the metallic substrate that is in contact with the liquid to create micro-scale or smaller surface texturing on the metallic substrate.