Verifying Neural Networks
AssigneeImperial College Innovations Limited
InventorsAlessio LOMUSCIO, Patrick HENRIKSEN, Panagiotis KOUVAROS
Life of this patent
Estimating the term…
Loading patent…
AssigneeImperial College Innovations Limited
InventorsAlessio LOMUSCIO, Patrick HENRIKSEN, Panagiotis KOUVAROS
Estimating the term…
Systems and methods are provided for verifying the transformational robustness of a neural network. Data is obtained representing a trained neural network, a set of algebraic constraints on the output of the network, and a range of inputs to the neural network over which the algebraic constraints are to be verified, such that the data defines a transformational robustness verification problem. A set of complementary constrains on the pre-activation of a node in the network are then determined such that for any input in the range of inputs, at least one of the complementary constraints is satisfied. A plurality of child verification problems are generated based on the transformational robustness verification problem and the set of complementary constraints. For each child verification problem, it is determined whether a counter-example to the child verification problem exists. Based on the determination of whether counter-examples to the child verification problems exist, it is determined whether the neural network is transformationally robust.
A computer-implemented method for verifying the transformational robustness of a neural network, comprising the steps of:
Dependencies are inferred from the claim text.