Machine Learning and Cognitive Algorithms for Engineering Applications

Machine Learning and Cognitive Algorithms for Engineering Applications

Leonid Perlovsky (Harvard University, Cambridge, MA, USA) and Gary Kuvich (IBM, USA)
DOI: 10.4018/ijcini.2013100104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Mind is based on intelligent cognitive processes, which are not limited by language and logic only. The thought is a set of informational processes in the brain, and such processes have the same rationale as any other systematic informational processes. Their specifics are determined by the ways of how brain stores, structures, and process this information. Systematic approach allows representing them in a diagrammatic form that can be formalized. Semiotic approach allows for the universal representation of such diagrams. In that approach, logic is a way of synthesis of such structures, which is a small but clearly visible top of the iceberg. The most efforts were traditionally put into logics without paying much attention to the rest of the mechanisms that make the entire thought system working autonomously. Dynamic fuzzy logic is reviewed and its connections with semiotics are established. Dynamic fuzzy logic extends fuzzy logic in the direction of logic-processes, which include processes of fuzzification and defuzzification as parts of logic. The paper reviews basic cognitive mechanisms, including instinctual drives, emotional and conceptual mechanisms, perception, cognition, language, a model of interaction between language and cognition upon the new semiotic models. The model of interacting cognition and language is organized in an approximate hierarchy of mental representations from sensory percepts at the “bottom” to objects, contexts, situations, abstract concepts-representations, and to the most general representations at the “top” of mental hierarchy. Knowledge Instinct and emotions are driving feedbacks for these representations. Interactions of bottom-up and top-down processes in such hierarchical semiotic representation are essential for modeling cognition. Dynamic fuzzy logic is analyzed as a fundamental mechanism of these processes. Future research directions are discussed.
Article Preview

2. System Thinking And Semiotic Knowledge Representation

Cognitive and computer sciences have accumulated multiple models of intelligent processes. It would be possibly wrong to say that brain plays such models. But the right statement is that those models reflect some brain processes. Assume that we need to design a system, where human mind is a prototype. To start building, we need to provide its specifications that are based on some rationale. This is needed for Use Cases that describe how system may work. It would be also smart to reuse what is already accumulated in other areas. And if we try to apply experience that has been accumulated in cognitive and computer sciences and software and computer industries, we shall notice some interesting analogies.

Virtual reality and modern computer games become more and more sophisticated, and closer to real life. We are trying to build more and more sophisticated game engines. But it would be no mistake to state a trivial on the first sight thing: life is also a game. Could our brain use same principles that a sophisticated intelligent game engine would be using? The life game engine needs to drive a core life cycle that consists of perception, cognition, prediction, decision, and action. (Figure 1) This process is not completely linear, and there are sub-cycles, and feedbacks. Cognition builds situation model for the prediction process from perceptual information and other cognitive models, which also include linguistic models with help of Synthesis – Analysis cycle. Third component of this cycle – Search – is not shown.

Figure 1.

Cycles of intelligent engine. Please note that a separation between perception and cognition is imaginary and in fact they form a single multilevel hierarchical system with feedbacks. In this sense, they are perceptual and conceptual levels in the hierarchy with multiple feedbacks between levels rather than separated subsystems. Also, prediction and emotions are shown only between cognition and actions while they form feedback mechanisms on every level.

Outcomes of prediction process transform via Goals into Decision. Emotional components (Kuvich, 2005; Perlovsky, Deming, & Ilin, 2011) play role of positive or negative feedbacks to generate a Decision upon the cognitive models. Language models are inseparable part of the cognitive models, and they are shown here as such. Decision turns appropriate Action on, and cycle repeats.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 10: 4 Issues (2016)
Volume 9: 4 Issues (2015)
Volume 8: 4 Issues (2014)
Volume 7: 4 Issues (2013)
Volume 6: 4 Issues (2012)
Volume 5: 4 Issues (2011)
Volume 4: 4 Issues (2010)
Volume 3: 4 Issues (2009)
Volume 2: 4 Issues (2008)
Volume 1: 4 Issues (2007)
View Complete Journal Contents Listing