Einsteinian neural network for spectrum estimation

Perlovsky, Leonid; Plum, Charles P.; Franchi, Peter R.; Tichovolsky, Elihu J.; Choi, David; Weijers, B.

doi:10.1016/s0893-6080(97)00081-6

Cited by 33 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are defined similarly to the a posteriori Bayes probabilities, they range between 0 and 1, and as a result of learning they converge to the probabilities, under certain conditions. This mathematical breakthrough led to solving many problems that could not have been solved previously [68][69][70][71][72][73][74][75][76][77][78][79][80].…”

Section: DL a Logic-processmentioning

confidence: 99%

Mathematical Model of Embodied Symbols: Cognition and Perceptual Symbol System

Perlovsky¹,

Ilin²

2012

JBBS

View full text Add to dashboard Cite

A mathematical model of perceptual symbol system is developed. This development requires new mathematical methods of dynamic logic (DL), which have overcome limitations of classical artificial intelligence and connectionist approaches. The paper discusses these past limitations, relates them to combinatorial complexity (exponential explosion) of algorithms in the past, and relates it further to the static nature of classical logic. DL is a process-logic; its salient property is evolution of vague representations into crisp. We first consider one aspect of PSS: situation learning from object perceptions. Next DL is related to PSS mechanisms of concepts, simulators, grounding, embodiment, productiveity, binding, recursion, and to the mechanisms relating embodied-grounded and amodal symbols. We discuss DL capability for modeling cognition on multiple levels of abstraction. PSS is extended toward interaction between cognition and language. Experimental predictions of the theory are discussed. They might influence experimental psychology and impact future theoretical developments in cognitive science, including knowledge representation, and mechanisms of interaction between perception, cognition, and language. All mathematical equations are also discussed conceptually, so mathematical understanding is not required. Experimental evidence for DL and PSS in brain imaging is discussed as well as future research directions

show abstract

Section: DL a Logic-processmentioning

confidence: 99%

Mathematical Model of Embodied Symbols: Cognition and Perceptual Symbol System

Perlovsky¹,

Ilin²

2012

JBBS

View full text Add to dashboard Cite

show abstract

“…The analogy with models is literal and neural representations are also called mental models. Mathematical models of concept mechanisms is discussed in (Perlovsky et al, 1997, 2011; Perlovsky, 2006a). Proof of detailed theoretical predictions of the mechanism in experimental neuro-imaging, including detailed descriptions of the brain regions involved was obtained by Bar et al (2006) and Kveraga et al (2007).…”

Section: Fundamental Principles Of the Mind-brainmentioning

confidence: 99%

Physics of the Mind

Perlovsky

2016

Front. Syst. Neurosci.

Self Cite

View full text Add to dashboard Cite

Is it possible to turn psychology into “hard science”? Physics of the mind follows the fundamental methodology of physics in all areas where physics have been developed. What is common among Newtonian mechanics, statistical physics, quantum physics, thermodynamics, theory of relativity, astrophysics… and a theory of superstrings? The common among all areas of physics is a methodology of physics discussed in the first few lines of the paper. Is physics of the mind possible? Is it possible to describe the mind based on the few first principles as physics does? The mind with its variabilities and uncertainties, the mind from perception and elementary cognition to emotions and abstract ideas, to high cognition. Is it possible to turn psychology and neuroscience into “hard” sciences? The paper discusses established first principles of the mind, their mathematical formulations, and a mathematical model of the mind derived from these first principles, mechanisms of concepts, emotions, instincts, behavior, language, cognition, intuitions, conscious and unconscious, abilities for symbols, functions of the beautiful and musical emotions in cognition and evolution. Some of the theoretical predictions have been experimentally confirmed. This research won national and international awards. In addition to summarizing existing results the paper describes new development theoretical and experimental. The paper discusses unsolved theoretical problems as well as experimental challenges for future research.

show abstract

“…detection, tracking, fusion in strong clutter [44,45,46,47,48]. We also describe a solution to a longstanding unsolved problem of autonomous situational awareness.…”

Section: Applications Of Dl-nmf To Classical Previously Unsolved Probmentioning

confidence: 99%

Computational Intelligence Applications for Defense

Perlovsky¹

2011

Self Cite

View full text Add to dashboard Cite

The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing the burden, to Department of Defense, Washington Headquarters Services, Directorate for Information Operations and Reports (0704-0188),

show abstract

Einsteinian neural network for spectrum estimation

Cited by 33 publications

References 7 publications

Mathematical Model of Embodied Symbols: Cognition and Perceptual Symbol System

Mathematical Model of Embodied Symbols: Cognition and Perceptual Symbol System

Physics of the Mind

Computational Intelligence Applications for Defense

Contact Info

Product

Resources

About