The ACIP Project
Overview:
Cognitive computing systems make intelligent decisions, learn from
previous experiences, and are introspective, constantly improving
their behavior and performance over time. Recently, the Artificial
Intelligence community has made significant advances in algorithms for
cognitive processing. Areas of innovation include Bayesian Inference,
Evolutionary Computing, and Knowledge-Based Reasoning. The ACIP
project brings together algorithm designers and computer architects to
develop high-performance implementations of cognitive systems. Key
areas of innovation span algorithms, compilers, runtime systems, and
architectures.
The ACIP project is a DARPA initiative, and involves researchers from
academia, industry, and the Department of Defense. At UMD, we are
conducting an in-depth applications study to identify the performance
requirements of key cognitive kernels. Our group is also developing
architectural support to speed up these kernels. Current techniques
under investigation include mechanisms for exploiting soft
computing properties, data-driven processor architectures,
computation and data migration for locality management, and helper
threading for introspection and dynamic optimization.
People:
Faculty
Students
Publications:
Funding:
The ACIP project is funded by the Defense Advanced Research Projects
Agency (DARPA) through the Department of the Interior National
Business Center under grant #NBCH104009.
Last updated:
September 2006
by
Donald Yeung
(yeung@eng.umd.edu)