MicroPsi: Contributions to a Broad Architecture of Cognition

Bach, Joscha; Bauer, Colin; Vuine, Ronnie

doi:10.1007/978-3-540-69912-5_2

Cited by 8 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Perceptual learning applies to the architectures that actively change the way sensory information is handled or how patterns are learned on-line. This kind of learning is frequently performed to obtain implicit knowledge about the environment, such as spatial maps (RCS [477], AIS [216], MicroPsi [33]), clustering visual features (HTM [292], BECCA [436], Leabra [405]) or finding associations between percepts. The latter can be used within the same sensory modality as in the case of the agent controlled by Novamente engine, which selects a picture of the object it wants to get from a teacher [188].…”

Section: Perceptual Learningmentioning

confidence: 99%

40 years of cognitive architectures: core cognitive abilities and practical applications

2018

View full text Add to dashboard Cite

In this paper we present a broad overview of the last 40 years of research on cognitive architectures. To date, the number of existing architectures has reached several hundred, but most of the existing surveys do not reflect this growth and instead focus on a handful of well-established architectures. In this survey we aim to provide a more inclusive and highlevel overview of the research on cognitive architectures. Our final set of 84 architectures includes 49 that are still actively developed, and borrow from a diverse set of disciplines, spanning areas from psychoanalysis to neuroscience. To keep the length of this paper within reasonable limits we discuss only the core cognitive abilities, such as perception, attention mechanisms, action selection, memory, learning, reasoning and metareasoning. In order to assess the breadth of practical applications of cognitive architectures we present information on over 900 practical projects implemented using the cognitive architectures in our list. We use various visualization techniques to highlight the overall trends in the development of the field. In addition to summarizing the current state-of-the-art in the cognitive architecture research, this survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.

show abstract

Section: Perceptual Learningmentioning

confidence: 99%

40 years of cognitive architectures: core cognitive abilities and practical applications

2018

View full text Add to dashboard Cite

show abstract

“…Joscha Bach and Dietrich Dörner use a similar technique to this in their Psi and MicroPsi cognitive architectures [4,3,2]. In the Psi model, gating nodes are used as intermediaries between nodes which are related in one of a fixed set of four ways, viz., the "is-in" relationship, the "succession" sequential relation and the inverses of these.…”

Section: Neurally Implementable Expression Of Relationshipsmentioning

confidence: 99%

“…Our endeavor here is motivated by and draws upon an array of previous experimental and theoretical work including cell assembly theory due to Wickelgren and others [42,43]; semantic network theory, which is reviewed in [38] and in [21]; and cognitive architecture methods due to Dörner, Bach and colleagues [2,3,4]. Observations by Quiroga and others [13,30,31,32] of cells responding robustly and specifically to conceptually oriented stimuli also serve to indicate that a theory ascribing an explicit conceptual role to neurons or sets of neurons may be accurate.…”

Section: Introductionmentioning

confidence: 99%

Neurally Implementable Semantic Networks

N.¹,

Collins²

2013

Preprint

View full text Add to dashboard Cite

We propose general principles for semantic networks allowing them to be implemented as dynamical neural networks. Major features of our scheme include: (a) the interpretation that each node in a network stands for a bound integration of the meanings of all nodes and external events the node links with; (b) the systematic use of nodes that stand for categories or types, with separate nodes for instances of these types; (c) an implementation of relationships that does not use intrinsically typed links between nodes.

show abstract

“…Rodin's "the thinker", being deep in thoughts while completely immobilized, can be seen as a symbolization of this decoupling of high-level cognitive processing and actions in the world ( Figure 1a). Contrary to this, the Braitenberg vehicle (Braitenberg 1984, Bach et al 2007) represents a direct interaction of sensory processing and corresponding actions (Figure 1b)³ and is therefore an example of pure low-level cognition. Figure 1 : The difference between high-and low-level cognition can be symbolized by the contrast of "the thinker (Rodin)" and a Braitenberg vehicle.…”

Section: Introduction Cognitive Science On Low-and High-level -A Divimentioning

confidence: 96%