Abstract: A rotary driving device and a method for correcting a system error of the rotary driving device are provided. The rotary driving device includes a driven assembly, a driving assembly, a torque transmission member, a first torque sensor, and a second torque sensor. The driving assembly includes a fixed component and a rotating component, the rotating component is rotatably connected to the fixed component, the torque transmission member is connected to the rotating component and the driven assembly, the rotating component is configured to drive the driven assembly to rotate through the torque transmission member. The first torque sensor is connected to the fixed component and the torque transmission member, and the second torque sensor is disposed on the driven assembly.

Abstract: A linear drive and a method for correcting a systematic error of the linear drive are provided. The linear drive includes a fixed assembly, a movable assembly, a first force sensor and a second force sensor. The movable assembly is movably connected to one end of the fixed assembly, and the movable assembly capable of being movable in a direction towards or away from the fixed assembly. The first force sensor is disposed at one end of the fixed assembly away from the movable assembly and configured for detecting a force acting on the first force sensor from the fixed assembly towards the movable assembly. The second force sensor is disposed at one end of the movable assembly away from the fixed assembly and configured for detecting a force acting on the second force sensor from the movable assembly toward the fixed assembly.

Abstract: In some embodiments, a method receives a line item factor for a line item at a first model. The method receives a competition factor at a second model. The first model generates a first value for a representation parameter based on the line item factor. The representation parameter is used to generate a representation for estimating selection of the instance of supplemental content for the line item for delivery. The second model generates a modification factor based on the competition factor. The modification factor is configured to modify the first value for the representation parameter based on competition from other line items to select the instance of supplemental content for the line item for delivery. The method modifies the first value for the representation parameter using the modification factor to generate a second value for the representation parameter where the second value is used to generate the representation.

Abstract: In some embodiments, a method inputs a sequence of historical behaviors for a plurality of instances of content into a prediction network to generate a sequence of values that model the sequence of historical behaviors. A restriction on an operation performed by the prediction network is based on a characteristic of an viewing behavior. A sequence of attention scores is generated based on a similarity of a current behavior for a first instance of content to respective instances of historical behaviors in the sequence of historical behaviors. The method adjusts respective values based on corresponding attention scores to generate an adjusted sequence of values. The adjusted sequence of features are sampled to generate an output from the prediction network that models the sequence of historical behaviors based on the current behavior. The output for determining a prediction if the current behavior is indicative of the viewing behavior.

Abstract: In some embodiments, a method inputs a sequence of historical behaviors for a plurality of instances of content into a prediction network to generate a sequence of values that model the sequence of historical behaviors. A restriction on an operation performed by the prediction network is based on a characteristic of an viewing behavior. A sequence of attention scores is generated based on a similarity of a current behavior for a first instance of content to respective instances of historical behaviors in the sequence of historical behaviors. The method adjusts respective values based on corresponding attention scores to generate an adjusted sequence of values. The adjusted sequence of features are sampled to generate an output from the prediction network that models the sequence of historical behaviors based on the current behavior. The output for determining a prediction if the current behavior is indicative of the viewing behavior.