Inspired by the latest development in cognitive informatics and contemporary denotational mathematics, cognitive computing is an emerging paradigm of intelligent computing methodologies and systems, which implements computational intelligence by autonomous inferences and perceptions mimicking the mechanisms of the brain. This article presents a survey on the theoretical framework and architectural techniques of cognitive computing beyond conventional imperative and autonomic computing technologies. Theoretical foundations of cognitive computing are elaborated from the aspects of cognitive informatics, neural informatics, and denotational mathematics. Conceptual models of cognitive computing are explored on the basis of the latest advances in abstract intelligence and computational intelligence. Applications of cognitive computing are described from the aspects of autonomous agent systems and cognitive search engines, which demonstrate how machine and computational intelligence may be generated and implemented by cognitive computing theories and technologies toward autonomous knowledge processing.
TopIntroduction
Computing as a discipline in a narrow sense, is an application of computers to solve a given computational problem by imperative instructions; while in a broad sense, it is a process to implement the instructive intelligence by a system that transfers a set of given information or instructions into expected behaviors.
According to theories of cognitive informatics (Wang, 2002a, 2003, 2006, 2007b, 2007c, 2008a, 2009a; Wang et al., 2009b), computing technologies and systems may be classified into the categories of imperative, autonomic, and cognitive from the bottom up. Imperative computing is a traditional and passive technology based on stored-program controlled behaviors for data processing (Turing, 1950; von Neumann, 1946, 1958; Gersting, 1982; Mandrioli and Ghezzi, 1987; Lewis and Papadimitriou, 1998). An autonomic computing is goal-driven and self-decision-driven technologies that do not rely on instructive and procedural information (Kephart and Chess, 2003; IBM, 2006; Wang, 2004, 2007a). Cognitive computing is more intelligent technologies beyond imperative and autonomic computing, which embodies major natural intelligence behaviors of the brain such as thinking, inference, learning, and perceptions.
Definition 1. Cognitive computing is an emerging paradigm of intelligent computing methodologies and systems that implements computational intelligence by autonomous inferences and perceptions mimicking the mechanisms of the brain.
Cognitive computing systems are designed for cognitive and perceptive knowledge processing based on contemporary denotational mathematics (Zadeh, 1965; Wang, 2002b, 2007a, 2008b, 2008c, 2008d, 2008e; Wang et al, 2009a), which are centered by the parallel autonomous inference and perception mechanisms of the brain as revealed in the Layered Reference Model of the Brain (LRMB) (Wang et al., 2006). On the basis of cognitive computing, next generation cognitive computers and autonomous intelligent systems that think and feel may be designed and implemented.
This article presents the theoretical framework and architectural techniques of cognitive computing beyond conventional imperative and autonomic computing systems. Theoretical foundations of cognitive computing are elaborated from the aspects of cognitive informatics, neural informatics, and denotational mathematics. Conceptual models of cognitive computing are explored from the latest development in abstract intelligence, intelligent behaviors, and computational intelligence. Applications of cognitive computing are described with an autonomous agent system and a cognitive search engine, which demonstrate how machine and computational intelligence may be generated and implemented by cognitive computing theories and technologies toward autonomous knowledge processing.
TopTheoretical Foundations For Cognitive Computing
Theories and methodologies of cognitive computing are inspired by the latest advances in cognitive informatics and denotational mathematics. This section elaborates the cognitive informatics theories and denotational mathematical structures for cognitive computing.