Abstract: A computing system is described, where the computing system includes a processor and memory storing instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving a query from an application executing on a client computing device that is in network communication with the computing system. The acts also include searching a computer-readable index of items based upon the query, identifying an item based upon the searching of the computer-readable index, transmitting the query to a computer-implemented model, and obtaining content generated by the computer-implemented model, where the computer-implemented model generated the content based upon the query. The acts further include returning at least one of the item or the content to the client computing device for presentment by way of the application executing on the client computing device.

Abstract: A computer-implemented technique performs machine learning that bypasses the traditional design of loss functions. The technique includes receiving plural instances of gradient objective information. Each of the plural instances includes a particular combination of plural gradient elements. The technique produces plural sets of machine-trained parameter values using the plural respective instances of gradient objective information. The technique performs this operation based on the plural instances of gradient objective information as given, without calculating the plural instances of gradient objective information using loss functions. The technique then measures performance of the plural sets of machine-trained parameter values in an application system. Based on the measured performance, the technique provides output information that identifies a particular set of machine-trained parameter values that satisfies a prescribed test.

Abstract: Systems and methods related to segmenting objects detected in an input view via a camera application in a live camera mode of an electronic device are disclosed herein. In some example aspects, a real-time object segmentation system is provided that receives input views during the live camera mode. The live camera mode may consist of at least one input view that is displayed on the screen of the electronic device prior to the capturing of a static image. The live camera mode may receive multiple views as the electronic device is moved, and these input views may be processed using at least one machine-learning algorithm to identify (or recognize) one or more objects. Based on the identification of the object or objects within the input view, at least one selectable action response may be provided to the user.