Cognitively Inspired Neural Network for Recognition of Situations

Ilin, Roman; Perlovsky, Leonid

doi:10.4018/jncr.2010010102

Cited by 34 publications

(17 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We summarize now a mathematical theory combining the discussed mechanisms of language and thinking as interaction between top-down and bottom-up signals at a single layer in multi-layer hierarchical system following [13,47,48]. Although language and cognition are not strict hierarchies and interactions across several hierarchical levels are present, for simplicity we will use the word hierarchy.…”

Section: Dynamic Logicmentioning

confidence: 99%

See 1 more Smart Citation

Neurally and Mathematically Motivated Architecture for Language and Thought

Perlovsky

Ilin²

2010

TONIJ

View full text Add to dashboard Cite

Neural structures of interaction between thinking and language are unknown. This paper suggests a possible architecture motivated by neural and mathematical considerations. A mathematical requirement of computability imposes significant constraints on possible architectures consistent with brain neural structure and with a wealth of psychological knowledge. How language interacts with cognition. Do we think with words, or is thinking independent from language with words being just labels for decisions? Why is language learned by the age of 5 or 7, but acquisition of knowledge represented by learning to use this language knowledge takes a lifetime? This paper discusses hierarchical aspects of language and thought and argues that high level abstract thinking is impossible without language. We discuss a mathematical technique that can model the joint language-thought architecture, while overcoming previously encountered difficulties of computability. This architecture explains a contradiction between human ability for rational thoughtful decisions and irrationality of human thinking revealed by Tversky and Kahneman; a crucial role in this contradiction might be played by language. The proposed model resolves long-standing issues: how the brain learns correct words-object associations; why animals do not talk and think like people. We propose the role played by language emotionality in its interaction with thought. We relate the mathematical model to Humboldt’s “firmness” of languages; and discuss possible influence of language grammar on its emotionality. Psychological and brain imaging experiments related to the proposed model are discussed. Future theoretical and experimental research is outlined.

show abstract

Section: Dynamic Logicmentioning

confidence: 99%

“…Second, association variables f(m|n) are defined according to (2). Third, parameter values are updated according to ([47])…”

Section: Dynamic Logicmentioning

confidence: 99%

Neurally and Mathematically Motivated Architecture for Language and Thought

Perlovsky

Ilin²

2010

TONIJ

View full text Add to dashboard Cite

show abstract

“…Learning language, like learning cognition is driven by an inborn drive, the language instinct [103] (LI). Mathematically it can be modeled by DL [22,23,74,104]. Linguists consider words to be learned by memorizing them.…”

Section: Abstract Concepts Language and The Mind Hierarchymentioning

confidence: 99%

“…Since the 1950s cognitive dissonances became a wide and well studied area of psychology. It is known that tolerating cognitive dissonances is difficult, and people often make irrational decisions to avoid them [104]. In 2002 this research was awarded Nobel Prize in economics, emphasizing the importance of this field of research.…”

Section: Cognitive Function Of Musicmentioning

confidence: 99%

Brain. Conscious and Unconscious Mechanisms of Cognition, Emotions, and Language

Perlovsky

Ilin

2012

Brain Sciences

Self Cite

View full text Add to dashboard Cite

Conscious and unconscious brain mechanisms, including cognition, emotions and language are considered in this review. The fundamental mechanisms of cognition include interactions between bottom-up and top-down signals. The modeling of these interactions since the 1960s is briefly reviewed, analyzing the ubiquitous difficulty: incomputable combinatorial complexity (CC). Fundamental reasons for CC are related to the Gödel’s difficulties of logic, a most fundamental mathematical result of the 20th century. Many scientists still “believed” in logic because, as the review discusses, logic is related to consciousness; non-logical processes in the brain are unconscious. CC difficulty is overcome in the brain by processes “from vague-unconscious to crisp-conscious” (representations, plans, models, concepts). These processes are modeled by dynamic logic, evolving from vague and unconscious representations toward crisp and conscious thoughts. We discuss experimental proofs and relate dynamic logic to simulators of the perceptual symbol system. “From vague to crisp” explains interactions between cognition and language. Language is mostly conscious, whereas cognition is only rarely so; this clarifies much about the mind that might seem mysterious. All of the above involve emotions of a special kind, aesthetic emotions related to knowledge and to cognitive dissonances. Cognition-language-emotional mechanisms operate throughout the hierarchy of the mind and create all higher mental abilities. The review discusses cognitive functions of the beautiful, sublime, music.

show abstract

“…This work builds on a cognitive theory proposed in [1], called dynamic logic, also referred to as neural modeling fields (NMF), and modeling fields theory (MFT) in other publications [2] [3] [4] [5] [6].This is a cognitively inspired mathematical framework providing a generic way of finding an optimal match between a set of parametric probabilistic models and sensor input data. The probabilistic models provide the ability to include a priori knowledge and to model the variability of real world data.…”

Section: Introductionmentioning

confidence: 99%