Efficient Automatic Differentiation of Higher-Order Functions

Back to all technologies
Download as PDF
2019-SISK-68524
Researchers at Purdue University have developed methods of Automatic Differentiation (AD) to be applied to both rigid computations and arbitrary computer programs. This technology greatly increases the efficiency of these processes while also reducing the amount of required computer memory, allowing for more complicated deep learning systems.

Advantages:
-Efficient
-Versatile

Potential Applications:
-Application Programmers
-Machine Learning
-AI
Oct 28, 2021
NATL-Patent
United States
(None)
(None)

Apr 29, 2020
PCT-Gov. Funding
WO
(None)
(None)

Apr 29, 2019
Provisional-Patent
United States
(None)
(None)

(None)
NATL-Patent
Europe
(None)
(None)
Purdue Office of Technology Commercialization
The Convergence Center
101 Foundry Drive, Suite 2500
West Lafayette, IN 47906

Phone: (765) 588-3475
Fax: (765) 463-3486
Email: otcip@prf.org