
NSF Org: |
CCF Division of Computing and Communication Foundations |
Recipient: |
|
Initial Amendment Date: | September 11, 2019 |
Latest Amendment Date: | August 11, 2021 |
Award Number: | 1934960 |
Award Instrument: | Continuing Grant |
Program Manager: |
Christopher Stark
CCF Division of Computing and Communication Foundations CSE Directorate for Computer and Information Science and Engineering |
Start Date: | September 1, 2019 |
End Date: | August 31, 2023 (Estimated) |
Total Intended Award Amount: | $1,500,000.00 |
Total Awarded Amount to Date: | $1,500,000.00 |
Funds Obligated to Date: |
FY 2020 = $500,000.00 FY 2021 = $500,000.00 |
History of Investigator: |
|
Recipient Sponsored Research Office: |
3451 WALNUT ST STE 440A PHILADELPHIA PA US 19104-6205 (215)898-7293 |
Sponsor Congressional District: |
|
Primary Place of Performance: |
200 S 33rd Street, Moore Bldg Philadelphia PA US 19104-6314 |
Primary Place of
Performance Congressional District: |
|
Unique Entity Identifier (UEI): |
|
Parent UEI: |
|
NSF Program(s): |
TRIPODS Transdisciplinary Rese, HDR-Harnessing the Data Revolu |
Primary Program Source: |
01002021DB NSF RESEARCH & RELATED ACTIVIT 01002122DB NSF RESEARCH & RELATED ACTIVIT |
Program Reference Code(s): |
|
Program Element Code(s): |
|
Award Agency Code: | 4900 |
Fund Agency Code: | 4900 |
Assistance Listing Number(s): | 47.070 |
ABSTRACT
Recent advances in artificial intelligence have led to significant progress in our ability to extract information from images and time sequences. Maintaining this rate of progress hinges upon attaining equally significant results in the processing of more complex signals such as those that are acquired by autonomous systems and networks of connected devices, or those that arise in the study of complex biological and social systems. This award establishes FINPenn, the Center for the Foundations of Information Processing at the University of Pennsylvania. The focus of the center is to establish fundamental theory to enable the study of data beyond time and images. The center's premise is that humans' rich intuitive understanding of space and time may not necessarily be applicable to the processing of complex signals. Therefore, matching the success in time and space necessitates the discovery and development of foundational principles to guide the design of generic artificial intelligence algorithms. FINPenn will support a class of scholar trainees along with a class of visiting postdocs and students to advance this agenda. The center will engage the community through the organization of workshops and lectures and will disseminate knowledge with onsite and online educational activities at the undergraduate and graduate level.
FINPenn builds on two observations: (i) To understand the foundations of data science it is necessary to succeed beyond Euclidean signals in time and space. This is true even to understand the foundations for Euclidean signal processing. (ii) Humans live in Euclidean time and space. To succeed in information processing beyond signals with Euclidean structure, operation from foundational principles is necessary because human intuition is of limited help. For instance, convolutional neural networks have found success in the processing of images and signals in time but they rely heavily on spatial and temporal intuition. To generalize their success to unconventional signal domains it is necessary to postulate fundamental principles and generalize from those principles. If the generalizations are successful they not only illuminate the new application domains but they also help establish the validity of the postulated principles for Euclidean spaces in the tradition of predictive science. The proposers further contend that the foundational principles of data sciences are to be found in the exploitation of structure and the associated invariances and symmetries that structure generates. The initial focus of the center is in advancing the theory of information processing in signals whose structure is defined by a group, a graph, or a topology. These three types of signals generate three foundational research directions which build on the particular strengths of the University of Pennsylvania on network sciences, robotics, and autonomous systems which are areas in which these types of signals appear often.
This project is part of the National Science Foundation's Harnessing the Data Revolution (HDR) Big Idea activity.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
This grant funded FINPenn, the Center for the Foundations of Information Processing at the University of Pennsylvania (Penn). This center has had transformational impact at Penn. It is now subsumed within the Innovation in Data Engineering and Science (IDEAS) initiative, which is Penn’s signature initiative in the areas of data-driven engineering and artificial intelligence. FINPenn also supported the development of groundbreaking undergraduate courses on systems engineering, data sciences, and artificial intelligence. These courses supported the creation of an Artificial Intelligence major at Penn which is launching in the Fall of 2024.
Work at FINPenn has provided several foundational advances that expand the reach of artificial intelligence. Among these advances we highlight:
(I) Leveraging Data Symmetries with Constrained Learning. Most often, symmetries in data are leveraged with formulation that respect invariances by construction. We introduced and popularized the idea of enforcing invariances through constrains and data augmentation. This results in approaches to leverage symmetry that are more general, more flexible and that come with concrete guarantees in generalization performance.
(II) Learning by Transference. This novel concept entails training graph neural networks in small graphs to later execute them in, or transfer them to, larger graphs. This technique is now standard and has been enabled by our development of limit theories of GNNs.
(II) Relational Data Processing. We have also developed novel information processing techniques for signals supported on relational data structures. These structures are uniquely equipped to model rank, hierarchy, causality, and other complex relationships between data that classical artificial intelligence techniques are not equipped to handle.
These and other research contributions have provided research opportunities that involved 3 postdocs, 6 doctoral students, and 13 undergraduate students.
Last Modified: 03/17/2024
Modified by: Alejandro Ribeiro
Please report errors in award information by writing to: awardsearch@nsf.gov.