USA flag logo/image

An Official Website of the United States Government

UBER-HEB: Universal Biologically-inspired Environment for Research:…

Award Information

Agency:
Department of Defense
Branch:
Defense Advanced Research Projects Agency
Award ID:
85006
Program Year/Program:
2008 / STTR
Agency Tracking Number:
08ST1-0122
Solicitation Year:
N/A
Solicitation Topic Code:
N/A
Solicitation Number:
N/A
Small Business Information
Aptima, Inc.
12 Gill Street Suite 1400 Woburn, MA -
View profile »
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
 
Phase 1
Fiscal Year: 2008
Title: UBER-HEB: Universal Biologically-inspired Environment for Research: Hierarchical Ersatz Brain
Agency / Branch: DOD / DARPA
Contract: W31P4Q-08-C-0433
Award Amount: $99,000.00
 

Abstract:

Decades of exponential advancement in computer capabilities have transformed the world, from toddlers' playthings to the technologies of war and peace. Some further advances are constrained by the limits of von Neumann machines; in particular, they do not learn well. Aptima proposes to conduct a feasibility study to design "UBER-HEB," a non-von Neumann hierarchical universal learning system. The work is grounded in the Ersatz Brain Project, a biologically-inspired architecture for cognitive computing, based on decades of research by Professor James Anderson of Brown University, a founder of neural networks. The team members have collaborated for a decade. The approach uses many sparsely connected modules inspired by cortical columns. Learning takes places via several integrated mechanisms: Hebbian, dynamic systems forming attractors, interference patterns of activations. It includes hierarchical structures and hierarchical properties also emerge naturally. It takes a biologically plausible and computationally powerful topographical approach to temporal encoding. We will structure the work around three test problems, for which we will develop running code. One of the problems concerns anomaly detection, which is of clear operational relevance. The feasibility assessment and resulting design will thus be based on both theoretical considerations and the results and analysis of the test problems.

Principal Investigator:

Paul Allopenna
Senior Cognitive Scientist
7814962486
pallopenna@aptima.com

Business Contact:

Margaret J. Clancy
Chief Financial Officer
7814962415
clancy@aptima.com
Small Business Information at Submission:

APTIMA, INC.
12 Gill Street Suite 1400 Woburn, MA 01801

EIN/Tax ID: 043281859
DUNS: N/A
Number of Employees:
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
Research Institution Information:
BROWN UNIV.
Box 1929
164 Angell Street, 3rd Floor
Providence, RI 2912
Contact: Michael Gaughan
Contact Phone: (401) 863-1799
RI Type: Nonprofit college or university