A hierarchical attention-based neural network architecture, based on human brain guidance, for perception, conceptualisation, action and reasoning

Taylor, John G.; Hartley, Matthew; Taylor, Nigel; Panchev, Christo; Kasderidis, Stathis

doi:10.1016/j.imavis.2009.03.006

Cited by 13 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples include CLARION by Ron Sun [41], HTM by George & Hawkins [16], GNOSIS by John Taylor et al [135], ARTSCAN by Stephen Grossberg et al [136], Albus [42], and Tenenbaum et al [43].…”

Section: ) Behavior-based Methodsmentioning

confidence: 99%

Symbolic Models and Emergent Models: A Review

Weng

2012

IEEE Trans. Auton. Mental Dev.

View full text Add to dashboard Cite

Abstract-There exists a large conceptual gap between symbolic models and emergent models for the mind. Many emergent models work on low-level sensory data, while many symbolic models deal with high-level abstract (i.e., action) symbols. There has been relatively little study on intermediate representations, mainly because of a lack of knowledge about how representations fully autonomously emerge inside the closed brain skull, using information from the exposed two ends (the sensory end and the motor end). As reviewed here, this situation is changing. A fundamental challenge for emergent models is abstraction, which symbolic models enjoy through human handcrafting. The term abstract refers to properties disassociated with any particular form. Emergent abstraction seems possible, although the brain appears to never receive a computer symbol (e.g., ASCII code) or produce such a symbol. This paper reviews major agent models with an emphasis on representation. It suggests two different ways to relate symbolic representations with emergent representations: One is based on their categorical definitions. The other considers that a symbolic representation corresponds to a brain's outside behaviors observed and handcrafted by other outside human observers; but an emergent representation is inside the brain.

show abstract

“…Examples include CLARION by Ron Sun [41], HTM by George & Hawkins [16], GNOSIS by John Taylor et al [135], ARTSCAN by Stephen Grossberg et al [136], Albus [42], and Tenenbaum et al [43].…”

Section: ) Behavior-based Methodsmentioning

confidence: 99%

Symbolic Models and Emergent Models: A Review

Weng

2012

IEEE Trans. Auton. Mental Dev.

View full text Add to dashboard Cite

show abstract

“…The CODAM model has been recently used as part of an autonomous cognitive system called GNOSYS (Taylor et al 2009). The basic platform is a Pioneer P3AT robot with a Katana arm and the visual stimuli consist of sets of cylinders and sticks as well as a ball and a cube.…”

Section: Robotic Visionmentioning

confidence: 99%

“…Many useful conclusions were drawn that highlight the crucial role of perception, as modeled by a group of modules including CODAM, in performing tasks. More details are given in Taylor et al (2009).…”

Section: Robotic Visionmentioning

confidence: 99%

Vision, Attention Control, and Goals Creation System

Rapantzikos

Avrithis²,

Kolias³

2010

Perception-Action Cycle

View full text Add to dashboard Cite

Biological visual attention has been long studied by experts in the field of cognitive psychology. The Holy Grail of this study is the exact modeling of the interaction between the visual sensory and the process of perception. It seems that there is an informal agreement on the four important functions of the attention process: (a) the bottom-up process, which is responsible for the saliency of the input stimuli; (b) the top-down process that bias attention toward known areas or regions of predefined characteristics; (c) the attentional selection that fuses information derived from the two previous processes and enables focus; and (d) the dynamic evolution of the attentional selection process. In the following, we will outline established computational solutions for each of the four functions. OverviewMost of our impressions and memories are based on vision. Nevertheless vision mechanisms and functionalities are still not apparent. How do we perceive shape, color, or motion and how do we automatically focus on the most informative parts of the visual input? It has been long established that primates, including human, use focused attention and fast saccades to analyze visual stimuli based on the current situation or the desired goal. Neuroscientists have proven that neural information related to shape, motion, and color is transmitted through, at least, three parallel and interconnected channels to the brain rather than a single one. Hence a second question arises related to how these channels are "linked" in order to provide useful information to the brain.The Human Visual System (HVS) creates a perceptual representation of the world that is quite different than the two dimensional depiction of the retina.K. Rapantzikos ( ) Image, Video and

show abstract

“…A winner-take-all competition between units in the map ensures that the most salient unit is gazed first, followed by the second most salient one and so forth. Inhibition, the exact nature of which is still unknown, ensures that the previously gazed region is not attended again for a period of 500-900 ms. Other computational models have emphasized the need of an interaction between a bottom-up stimulus-driven module and a top-down attentive module, which drives attention to specific regions-of-interest (ROIs) in the saliency map [12,15,19,22,39,45,48].…”

Section: Introductionmentioning

confidence: 99%

A Cognitive Model of Saliency, Attention, and Picture Scanning

Cutsuridis

2009

Cogn Comput

View full text Add to dashboard Cite

To view and understand the visual world, we shift our gaze from one location to another about three times per second. These rapid changes in gaze direction result from very fast eye movements called saccades. Visual information is acquired only during fixations, stationary periods between saccades. Active visual search of pictures is the process of active scanning of the visual environment for a particular target among distracters or for the extraction of its meaning. This article discusses a cognitive model of saliency, overt attention, and natural picture scanning that unravels the neurocomputational mechanisms of how human gaze control operates during active real-world scene viewing.

show abstract

A hierarchical attention-based neural network architecture, based on human brain guidance, for perception, conceptualisation, action and reasoning

Cited by 13 publications

References 42 publications

Symbolic Models and Emergent Models: A Review

Symbolic Models and Emergent Models: A Review

Vision, Attention Control, and Goals Creation System

A Cognitive Model of Saliency, Attention, and Picture Scanning

Contact Info

Product

Resources

About