The Role of Associative Processing in Cognitive Computing

Haikonen, Pentti O

doi:10.1007/s12559-009-9006-y

Cited by 22 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The challenge of making systems interoperate is leading some researchers to seek inspiration in the field of artificial intelligence, in particular the semantic web. However, in doing so, it is important to consider the literature discussing when such approaches might be unfruitful (Uschold, 2001;Haikonen, 2009;Ekbia, 2010;Guns, 2013). In the fields of artificial intelligence and cognitive science, the representations chosen are commonly considered to determine which types of tasks the system can handle (Churchland & Sejnowski, 1992;Valiant, 2000;Gärdenfors, 2004;Stewart & Eliasmith, 2012;Doumas & Hummel, 2012).…”

Section: Alternativementioning

confidence: 99%

Vector space architecture for emergent interoperability of systems by learning from demonstration

Emruli

Sandin

Delsing

2015

Biologically Inspired Cognitive Architectures

View full text Add to dashboard Cite

The rapid integration of physical systems with cyberspace infrastructure, the so-called Internet of Things, is likely to have a significant effect on how people interact with the physical environment and design information and communication systems. Internet-connected systems are expected to vastly outnumber people on the planet in the near future, leading to grand challenges in software engineering and automation in application domains involving complex and evolving systems. Several decades of artificial intelligence research suggests that conventional approaches to making such systems automatically interoperable using handcrafted ''semantic'' descriptions of services and information are difficult to apply. In this paper we outline a bioinspired learning approach to creating interoperable systems, which does not require handcrafted semantic descriptions and rules. Instead, the idea is that a functioning system (of systems) can emerge from an initial pseudorandom state through learning from examples, provided that each component conforms to a set of information coding rules. We combine a binary vector symbolic architecture (VSA) with an associative memory known as sparse distributed memory (SDM) to model context-dependent prediction by learning from examples. We present simulation results demonstrating that the proposed architecture can enable system interoperability by learning, for example by human demonstration. ª 2015 Published by Elsevier B.V.

show abstract

Section: Alternativementioning

confidence: 99%

Vector space architecture for emergent interoperability of systems by learning from demonstration

Emruli

Sandin

Delsing

2015

Biologically Inspired Cognitive Architectures

View full text Add to dashboard Cite

show abstract

“…The challenge of making systems interoperate is leading some researchers to seek inspiration in the field of aritificial intelligence, in particular the semantic web. However, in doing so, it is important to consider the literature discussing when such approaches might be unfruit-ful (Uschold, 2001;Haikonen, 2009;Ekbia, 2010;Guns, 2013). In the fields of artificial intelligence and cognitive science, the representations chosen are commonly considered to determine which types of tasks the system can handle (Churchland and Sejnowski, 1992;Valiant, 2000;Gardenfors, 2004;Stewart and Eliasmith, 2012;Doumas and Hummel, 2012).…”

Section: Related Workmentioning

confidence: 99%

Vector space architecture for emergent interoperability of systems by learning from demonstration

Emruli

Sandin

Delsing

2014

Biologically Inspired Cognitive Architectures

View full text Add to dashboard Cite

The rapid integration of physical systems with cyberspace infrastructure, the so-called Internet of Things, is likely to have a significant effect on how people interact with the physical environment and design information and communication systems. Internet-connected systems are expected to vastly outnumber people on the planet in the near future, leading to grand challenges in software engineering and automation in application domains involving complex and evolving systems. Several decades of artificial intelligence research suggests that conventional approaches to making such systems interoperable using handcrafted "semantic" descriptions of services and information are difficult to apply. In this paper we outline a bioinspired learning approach to creating interoperable systems, which does not require handcrafted semantic descriptions and rules. Instead, the idea is that a functioning system (of systems) can emerge from an initial pseudorandom state through learning from examples, provided that each component conforms to a set of information coding rules. We combine a binary vector symbolic architecture (VSA) with an associative memory known as sparse distributed memory (SDM) to model context-dependent prediction by learning from examples. We present simulation results demonstrating that the proposed architecture can enable system interoperability by learning, for example by human demonstration.

show abstract

“…The robot XCR-1 utilizes associative processing [4], which is based on the use of associative neurons and associative neuron groups. During learning, an associative neuron associates an associative signal vector with the so-called main signal so that later on, the same associative signal vector will evoke the main signal as the output of the neuron.…”

Section: Associative Processingmentioning

confidence: 99%

XCR-1: An Experimental Cognitive Robot Based on an Associative Neural Architecture

Haikonen

2011

Cogn Comput

Self Cite

View full text Add to dashboard Cite

The experimental cognitive robot XCR-1 is a small three-wheel robot with gripper hands, multiple sensory modalities, and self-talk. The robot XCR-1 is designed for studies and experiments with a new paradigm for cognitive computation, namely an associative neural processing style that inherently and seamlessly combines subsymbolic and symbolic computation. This operation is realized by using associative neurons and neuron groups organized according to the Haikonen Cognitive Architecture. Recently, there have been many efforts toward machine consciousness, and the Haikonen Cognitive Architecture is one attempt in that direction. Human consciousness is characterized by subjective inner experience that is related to qualia. Accordingly, it can be proposed that true conscious machines should also have some kind of inner experience and qualia. On the other hand, it has been argued that qualia are direct and cannot be artificially realized in symbolic systems. In order to facilitate qualiarelated practical investigations, the robot XCR-1 utilizes direct perception processes, with dedicated hardware and without symbolic pre-programmed algorithms. The robot XCR-1 does not utilize microprocessors or programs of any kind. Natural language is one manifestation of symbolic processing. The robot XCR-1 is designed also for experiments with simple speech and the basic grounding of the meaning of words. The experiments with the robot XCR-1 could be greatly enhanced if dedicated associative neuron group chips were available.

show abstract

The Role of Associative Processing in Cognitive Computing

Cited by 22 publications

References 19 publications

Vector space architecture for emergent interoperability of systems by learning from demonstration

Vector space architecture for emergent interoperability of systems by learning from demonstration

Vector space architecture for emergent interoperability of systems by learning from demonstration

XCR-1: An Experimental Cognitive Robot Based on an Associative Neural Architecture

Contact Info

Product

Resources

About