Abstract: Provided are a preparation method for and use of a self-assembly-based nitrogen-doped ordered porous precious metal nanomaterial. The preparation method includes: with a pyridine nitrogen-containing amphiphilic block copolymer as a structure-directing agent and a phenolic resin as a template agent, adding a precious metal precursor, inducing self-assembly by means of volatilization of a solvent, and carbonizing in an inert atmosphere to prepare the nitrogen-doped ordered porous precious metal nanomaterial. The regularity, dispersity and uniformity of the precious metal nanomaterial are achieved; the problems of migration and inactivation after agglomeration of precious metal nanoparticles are solved; the lifespan of precious metal particles is prolonged; and in addition, the ORR electro-catalytic property of the material can be improved, and the nitrogen-doped ordered porous precious metal nanomaterial can be used to prepare a cathodic oxygen reduction catalyst for a fuel cell.

Abstract: Embodiments of the disclosed technologies receive, for a first machine learning task, a first set of raw features arranged according to a first schema, and, for a second machine learning task, a second set of raw features arranged according to a second schema different than the first schema. A multi-task raw feature set is created by storing, in a data store arranged according to a common schema, the first and second sets of raw features. A common feature that is common to both the first and second sets of raw features is identified. A multi-task transformed feature set and a model bundle are created. The multi-task transformed feature set is separated into first and second sets of transformed features. The first and second sets of transformed features and the model bundle can be used to create a trained multi-task machine learning model.