Neural network-based dynamical system modeling for contrastively learned conservation laws
AssigneeInternational Business Machines Corporation
InventorsLam Minh Nguyen, Wang Zhang, Subhro Das, Alexandre Megretski, Luca Daniel
Life of this patent
Estimating the term…
Abstract
Obtain, using at least one hardware processor, data characterizing a physical system governed by a physical conservation law. Apply, using the at least one hardware processor, contrastive learning to the data to automatically capture system invariants of the physical system. Employ, using the at least one hardware processor, a neural projection layer to guarantee that a corresponding dynamic machine learning model preserves the captured system invariants. Optionally, predict performance of the physical system using the corresponding dynamic machine learning model.
Claims20
A method comprising:
- obtaining, using at least one hardware processor, data characterizing a physical system governed by a physical conservation law;
- applying, using the at least one hardware processor, contrastive learning to the data to automatically capture system invariants of the physical system;
- and
- employing, using the at least one hardware processor, a neural projection layer to guarantee that a corresponding dynamic machine learning model preserves the captured system invariants.
A computer program product, comprising:
- one or more tangible computer-readable storage media and program instructions stored on at least one of the one or more tangible computer-readable storage media, the program instructions executable by a processor, the program instructions comprising:
- obtaining, using at least one hardware processor, data characterizing a physical system governed by a physical conservation law;
- applying, using the at least one hardware processor, contrastive learning to the data to automatically capture system invariants of the physical system;
- and
- employing, using the at least one hardware processor, a neural projection layer to guarantee that a corresponding dynamic machine learning model preserves the captured system invariants.
A system comprising:
- a memory;
- and
- at least one processor, coupled to said memory, and operative to perform operations comprising:
- obtaining, using at least one hardware processor, data characterizing a physical system governed by a physical conservation law;
- applying, using the at least one hardware processor, contrastive learning to the data to automatically capture system invariants of the physical system;
- and
- employing, using the at least one hardware processor, a neural projection layer to guarantee that a corresponding dynamic machine learning model preserves the captured system invariants.
Dependencies are inferred from the claim text.