Abstract: A reinforcement learning ranker can take into account previously-recommended media content items to produce a ranked list of media content items to recommend next. The ranker finds a policy that gives the probability of sampling a media content item given a state. The policy is learned such that it maximizes a reward. A reward function associated with the media content item can be defined with respect to whether the user finds the media content item relevant (likelihood that the user will like the media content item) and a diversity score of the media content item.

Abstract: A semiconductor wafer mapping apparatus comprising a frame forming a wafer load opening communicating with a load station for a substrate carrier disposed to hold more than one wafers vertically distributed in the substrate carrier for loading through the wafer load opening, a movable arm movably mounted to the frame so as to move relative to the wafer load opening and having at least one end effector movably mounted to the movable arm to load wafers from the substrate carrier through the wafer load opening, an image acquisition system including an array of cameras arranged on a common support and each camera fixed with respect to the common support that is static with respect to each camera of the array of cameras, wherein each respective camera is positioned with a field of view disposed to view through the wafer load opening with the common support positioned by the movable arm.

Abstract: A semiconductor wafer mapping apparatus comprising a frame forming a wafer load opening communicating with a load station for a substrate carrier disposed to hold more than one wafers vertically distributed in the substrate carrier for loading through the wafer load opening, a movable arm movably mounted to the frame so as to move relative to the wafer load opening and having at least one end effector movably mounted to the movable arm to load wafers from the substrate carrier through the wafer load opening, an image acquisition system including an array of cameras arranged on a common support and each camera fixed with respect to the common support that is static with respect to each camera of the array of cameras, wherein each respective camera is positioned with a field of view disposed to view through the wafer load opening with the common support positioned by the movable arm.

Abstract: An end effector for handling a sheet of flexible material. The end effector includes a support frame and manipulator assemblies, each attached to the support frame by a support mount. The manipulator assemblies include a holding tool having a lifting surface. The manipulator assemblies include a linear actuator, and the holding tool is connected to the linear actuator by a multiaxial joint. A drive provides—the displacement of the holding tool by the linear actuator. The end effector includes resilient members each rigidly affixed to two adjacent holding tools and positioned in a space providing a mutual distance between opposing faces of the adjacent holding tools, where each holding tool is connected to—adjacent holding tools—by the resilient members. The resilient members are configured to non-permanently deform in the space when adjacent holding tools are displaced relative to each other along displacement axes.

Abstract: A semiconductor wafer mapping apparatus comprising a frame forming a wafer load opening communicating with a load station for a substrate carrier disposed to hold more than one wafers vertically distributed in the substrate carrier for loading through the wafer load opening, a movable arm movably mounted to the frame so as to move relative to the wafer load opening and having at least one end effector movably mounted to the movable arm to load wafers from the substrate carrier through the wafer load opening, an image acquisition system including an array of cameras arranged on a common support and each camera fixed with respect to the common support that is static with respect to each camera of the array of cameras, wherein each respective camera is positioned with a field of view disposed to view through the wafer load opening with the common support positioned by the movable arm.

Abstract: An electronic device stores a plurality of vector representations for respective media content items in a vector space, where each vector represents a media content item. The electronic device receives a first set of input parameters representing a previous session of a user of the media-providing service where the previous session included two or more of the respective media content items. The electronic device then receives a second set of input parameters representing a current context of the user and provides the first set of input parameters and the second set of input parameters to a neural network to generate a prediction vector for a current session. The prediction vector is embedded in the vector space.

Abstract: An end effector for handling a sheet of flexible material. The end effector includes a support frame and manipulator assemblies, each attached to the support frame by a support mount. The manipulator assemblies include a holding tool having a lifting surface. The manipulator assemblies include a linear actuator, and the holding tool is connected to the linear actuator by a multiaxial joint. A drive provides—the displacement of the holding tool by the linear actuator. The end effector includes resilient members each rigidly affixed to two adjacent holding tools and positioned in a space providing a mutual distance between opposing faces of the adjacent holding tools, where each holding tool is connected to—adjacent holding tools—by the resilient members. The resilient members are configured to non-permanently deform in the space when adjacent holding tools are displaced relative to each other along displacement axes.

Abstract: A reinforcement learning ranker can take into account previously-recommended media content items to produce a ranked list of media content items to recommend next. The ranker finds a policy that gives the probability of sampling a media content item given a state. The policy is learned such that it maximizes a reward. A reward function associated with the media content item can be defined with respect to whether the user finds the media content item relevant (likelihood that the user will like the media content item) and a diversity score of the media content item.

Abstract: An electronic device stores a plurality of vector representations for respective media content items in a vector space, where each vector represents a media content item. The electronic device receives a first set of input parameters representing a previous session of a user of the media-providing service where the previous session included two or more of the respective media content items. The electronic device then receives a second set of input parameters representing a current context of the user and provides the first set of input parameters and the second set of input parameters to a neural network to generate a prediction vector for a current session. The prediction vector is embedded in the vector space.