The IBM Research SyNAPSE project [1] defines cognitive systems as “the quest for approximating the mind-like function, low power, small volume, and real-time performance of the human brain.”

IBM [2] has described cognitive systems as a new generation of computing systems characterized as data-centric, designed for statistical analysis, scale-in, and automate system and workload management with exploration in core technologies, architectures and applications.

Dr. Kelly [3] has described a new era of cognitive systems characterized by learning from interactions and generating insight from data, becoming ubiquitous and pervasive while evolving from command driven to advice offering.

Rob High [4] asserts that cognitive systems are able to learn their behavior through education; they support forms of expression that are more natural for human interaction; their primary value is their expertise; and they continue to evolve as they experiences new information, new scenarios, and new responses; and does so at enormous scale.

Cognition has its roots in the meaning of “to know”, it is said to reside in the mind and be capable of judgment. In this paper, we propose a theoretical framework that uses human cognition as a model to explain a continuum of computational systems, referred to as cognitive systems. Cognitive systems are adaptive and intelligent systems that enhance information organization, learning and understanding for the benefit and augmentation of people, business and the world.

First, the theoretical framework begins with eight elements of cognition, which make up the mind-like function mentioned by [1]. Second, a set of capability metrics are introduced to differentiate and evaluate cognitive capabilities in multiple important dimensions. Third, architectural alternatives for implementing the elements of cognition are surveyed. Lastly, we conclude with some observations.

By: Jeffrey T. Kreulen

Published in: RJ10522 in 2014


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to .