International Business Machines Corporation

Sean A McKenna

Mathieu Sinn

Ambrish Rawat

Fearghal O'Donncha

William Karol Lynch

Fearghal O'donncha

Techniques of facilitating deep learning model rescaling by computing devices. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise: a rescaling component; and a forecasting component. The rescaling component can determine a scaling ratio that maps low mesh resolution predictive data output by a partial differential equation (PDE)-based model for a sub-domain to high-resolution observational or ground-truth data for a domain comprising the sub-domain. The forecasting component can generate high mesh resolution predictive data for the domain with a machine-learning model using input data of the PDE-based model and the scaling ratio.

Superresolution and consistency constraints to scale up deep learning models

A computing device configured for automatic selection of model parameters includes a processor and a memory coupled to the processor. The memory stores instructions to cause the processor to perform acts including providing an initial set of model parameters and initial condition information to a model based on historical data. A model generates data based on the model parameters and the initial condition information. After determining whether the model-generated data is similar to an observed data, updated model parameters are selected for input to the model based on the determined similarity.

System for continuous update of advection-diffusion models with adversarial networks

A computer-implemented method of extracting properties of one or more variables of a mathematical transformation in a document identified by automatic feature engineering (AFE) is provided. The document is parsed to extract at least one of a mathematical formula including identifying data, a textual description of the one or more variables of the mathematical transformation, or a category identifier to which the document belongs. Constraints are determined to apply to the one or more variables extracted from the mathematical transformations in the document. At least one candidate feature is automatically generated from a portion of an input data that conforms to the determined constraints.

Growing community of inventors

Reno, NV, United States of America

Sean A McKenna