Efficient Automatic Differentiation of Higher-Order Functions

Bookmark/Download	Download as PDF
Track Code	2019-SISK-68524
Categories	Computer Technology
Keywords	AI Computer Technology Machine Learning Software
Public Abstract	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
People	Siskind, Jeffrey M (Project leader) Pearlmutter, Barak Avrum
Intellectual Property	Application Date Apr 29, 2020 Type PCT-Gov. Funding Country of Filing WO Patent Number (None) Issue Date (None) Application Date Apr 29, 2019 Type Provisional-Patent Country of Filing United States Patent Number (None) Issue Date (None) Application Date (None) Type NATL-Patent Country of Filing United States Patent Number (None) Issue Date (None) Application Date (None) Type NATL-Patent Country of Filing Europe Patent Number (None) Issue Date (None)
Contact OTC	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