3 results about "Computer learning" patented technology

The invention discloses a laser remote obstacle clearance and monitoring system, which relates to the technical field of intelligent detection and control, and comprises the steps of acquiring image data of an obstacle clearance area, performing training calculation on obstacle characteristics in optimized image data by utilizing a computer learning algorithm, and confirming the position of an obstacle through similarity comparison. Marking the position data as obstacle position data; aiming according to the position data of the obstacle, calculating state information of the obstacle through a particle filtering method, adjusting the direction of the laser beam in real time, and aiming and tracking the position of the obstacle; laser parameters are adjusted according to the obstacle aiming position data in combination with the obstacle characteristics and the operation distance, laser beams are emitted to instantly heat and evaporate the surface of the target object, and the obstacle is removed; in the obstacle clearing process, the obstacle clearing area is continuously monitored, the obstacle clearing effect is fed back to the remote control center, the obstacle clearing strategy is adjusted in time, and the problems of insufficient accuracy and weak scene adaptability in the existing obstacle clearing technology are solved.

1. Name of the product subject to this design: Toy (Computer Learning Machine). 2. Purpose of this design: for children to play with. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

To efficiently search for mediators. [Solution] A mediator search method is provided, which involves a computer learning training data that associates experimental values ​​of the electrical properties of a solution containing a mediator and cells with the mediator; estimating the electrical properties of each of a plurality of mediators not included in the training data based on the results of the learning; and adding the experimental values ​​of the electrical properties of at least some of the plurality of mediators whose electrical properties have been estimated, along with the mediators themselves, to the training data, repeating this process until the experimental values ​​of the electrical properties meet a criterion, thereby searching for a mediator whose experimental values ​​meet the criterion.