Invention Grant
- Patent Title: Neural network verification based on cognitive trajectories
-
Application No.: US16913318Application Date: 2020-06-26
-
Publication No.: US11861494B2Publication Date: 2024-01-02
- Inventor: Javier Felip Leon , Javier Sebastian Turek , David Israel Gonzalez Aguirre , Ignacio J. Alvarez , Javier Perez-Ramirez , Mariano Tepper
- Applicant: Intel Corporation
- Applicant Address: US CA Santa Clara
- Assignee: Intel Corporation
- Current Assignee: Intel Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Jordan IP Law, LLC
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/06 ; G06N3/008 ; G06N3/04 ; G06N7/06 ; G06N3/045 ; G06N3/0455
Abstract:
Systems, apparatuses and methods may provide for technology that identifies a cognitive space that is to be a compressed representation of activations of a neural network, maps a plurality of activations of the neural network to a cognitive initial point and a cognitive destination point in the cognitive space and generates a first cognitive trajectory through the cognitive space, wherein the first cognitive trajectory traverses the cognitive space from the cognitive initial point to the cognitive destination point.
Public/Granted literature
- US20200327415A1 NEURAL NETWORK VERIFICATION BASED ON COGNITIVE TRAJECTORIES Public/Granted day:2020-10-15
Information query
