Model-based robust deep learning
AssigneeThe Trustees of the University of Pennsylvania
InventorsGeorge J. Pappas, Hamed Hassani, Alexander Robey
Life of this patent
Estimating the term…
Abstract
Methods, systems, and computer readable media for model-based robust deep learning. In some examples, a method includes obtaining a model of natural variation for a machine learning task. The model of natural variation includes a mapping that specifies how an input datum can be naturally varied by a nuisance parameter. The method includes training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.
Claims21
A method for model-based deep robust learning, the method comprising:
- obtaining a model of natural variation for a machine learning task, wherein the model of natural variation comprises a mapping that specifies how an input datum can be naturally varied by a nuisance parameter;
- and
- training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.
A system for model-based deep robust learning, the system comprising:
- at least one processor and memory storing executable instructions for the at least one processor;
- and
- a machine learning trainer implemented on the at least one processor and configured for:
- obtaining a model of natural variation for a machine learning task, wherein the model of natural variation comprises a mapping that specifies how an input datum can be naturally varied by a nuisance parameter;
- and
- training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.
A non-transitory computer readable medium storing executable instructions that when executed by at least one processor of a computer control the computer to perform operations comprising:
- obtaining a model of natural variation for a machine learning task, wherein the model of natural variation comprises a mapping that specifies how an input datum can be naturally varied by a nuisance parameter;
- and
- training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.
Dependencies are inferred from the claim text.