Abstract: A method of performing automatic tuning on a deep learning model includes: utilizing an instruction-based learned cost model to estimate a first type of operational performance metrics based on a tuned configuration of layer fusion and tensor tiling; utilizing statistical data gathered during a compilation process of the deep learning model to determine a second type of operational performance metrics based on the tuned configuration of layer fusion and tensor tiling; performing an auto-tuning process to obtain a plurality of optimal configurations based on the first type of operational performance metrics and the second type of operational performance metrics; and configure the deep learning model according to one of the plurality of optimal configurations.

Abstract: A heat-resistant alloy contains Y, a content of Ni is a content of Ni is 58.0 mass % or greater, a content of Cr is 20.0 mass % or greater and 23.0 mass % or less, a content of Mo is 8.0 mass % or greater and 10.0 mass % or less, a content of Nb is 3.15 mass % or greater and 4.15 mass % or less, a content of O is 0.002 mass % or greater and 0.1 mass % or less, and a ratio of a content of Y in terms of mass to a content of O in terms of mass is 0.5 or greater and 100 or less.

Abstract: A heat-resistant alloy contains at least one element selected from a group consisting of Al, Ti, Ni, Cr, and Mo, O, and Y, and a ratio of a content of Y in terms of mass to a content of O in terms of mass is 0.5 or greater and 100 or less.

Abstract: A heat-resistant alloy contains at least one element selected from a group consisting of Al, Ti, Ni, Cr, and Mo, O, and Y, and a ratio of a content of Y in terms of mass to a content of O in terms of mass is 0.5 or greater and 100 or less.

Abstract: The present approach similarly combines task and motion planning, but does so without symbolic representations and begins with simpler tasks than other models in such domains can handle. Unlike prior approaches, the present approach does so in continuous action and state spaces which require many precise steps in the configuration space to execute what otherwise is a single output token such as “pick up” for discrete problems.