The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Aug. 14, 2018
Filed:
Oct. 03, 2017
Sas Institute Inc., Cary, NC (US);
North Carolina State University, Raleigh, NC (US);
Samuel Paul Leeman-Munk, Cary, NC (US);
Saratendu Sethi, Raleigh, NC (US);
Christopher Graham Healey, Cary, NC (US);
Shaoliang Nie, Raleigh, NC (US);
Kalpesh Padia, Raleigh, NC (US);
Ravinder Devarajan, Cary, NC (US);
David James Caira, Chapel Hill, NC (US);
Jordan Riley Benson, Ellerbe, NC (US);
James Allen Cox, Cary, NC (US);
Lawrence E. Lewis, Raleigh, NC (US);
Mustafa Onur Kabul, Apex, NC (US);
SAS INSTITUTE INC., Cary, NC (US);
NORTH CAROLINA STATE UNIVERSITY, Raleigh, NC (US);
Abstract
Interactive visualizations of a convolutional neural network are provided. For example, a graphical user interface (GUI) can include a matrix having symbols indicating feature-map values that represent likelihoods of particular features being present or absent at various locations in an input to a convolutional neural network. Each column in the matrix can have feature-map values generated by convolving the input to the convolutional neural network with a respective filter for identifying a particular feature in the input. The GUI can detect, via an input device, an interaction indicating that that the columns in the matrix are to be combined into a particular number of groups. Based on the interaction, the columns can be clustered into the particular number of groups using a clustering method. The matrix in the GUI can then be updated to visually represent each respective group of columns as a single column of symbols within the matrix.