Pattern storage in a sparsely coded neural network with cyclic activation

Stroffek, Julius; Kuriščák, Eduard; Maršálek, Petr

doi:10.1016/j.biosystems.2006.04.023

Cited by 5 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…k x q n denotes the activities of individual neurons within iteration q of the cycle in pattern k. The learning rule itself is the same as in the Willshaw model except that it is rewritten in a form that include neural activities within cycles. Further details can be found in [39,40]. Synaptic facilitation and depression can additionally enlarge the network capacity, as demonstrated in [41,42,43].…”

Section: Recurrent Networkmentioning

confidence: 96%

Biological context of Hebb learning in artificial neural networks, a review

et al. 2015

Self Cite

View full text Add to dashboard Cite

Section: Recurrent Networkmentioning

confidence: 96%

Biological context of Hebb learning in artificial neural networks, a review

et al. 2015

Self Cite

View full text Add to dashboard Cite

“…Processes of activation and deactivation of pathways, possibly functioning in a cyclical manner, appear to be features of perception and cognition (Casey et al, 2000;Haider et al, 2006;Stroffek et al, 2007). Thus, activation of a name or sensory pathway is followed by a deactivation of this pathway that is accompanied by an activation of its connected sensory or name pathway; subsequent deactivation of this secondary sensory or name pathway is accompanied by re-activation of the initial name or sensory pathway.…”

Section: Stimulus-response Nature Of Their Wiringmentioning

confidence: 99%

The Name Pathway, an Elementary Cognitive Model of Names as Sensory Representations

Dass¹

2014

American Journal of Neuroscience

View full text Add to dashboard Cite

Names function as sensory representations, but the relationship between names and sensory stimuli/responses remains unclear. This study proposes the existence of a class of stimulus-response pathways, the name pathway, where a name is a reproducible and communicable symbol and the name pathway is one where the same name is both the stimulus and the response. Once a stimulus-response "name" pathway is formed as a result of reinforcement-based learning and in concert with the formation of the associated stimulus-response "sensory" pathway for a named object, act or process, Hebbian cross-pathway connectivity between the sensory and name pathways allows each pathway's stimulus to activate the other's response. The model proposes that every higher-order cognitive function exists only because it was named and that each such function may be defined mechanistically to be the outcome of the "recognition," "interpretation," and "retrieval" of sensory experiences from networks of names for that function.

show abstract

Short-term potentiation effect on pattern recall in sparsely coded neural network

Stroffek¹,

Maršálek²

2012

Neurocomputing

View full text Add to dashboard Cite

Pattern storage in a sparsely coded neural network with cyclic activation

Cited by 5 publications

References 18 publications

Biological context of Hebb learning in artificial neural networks, a review

Biological context of Hebb learning in artificial neural networks, a review

The Name Pathway, an Elementary Cognitive Model of Names as Sensory Representations

Short-term potentiation effect on pattern recall in sparsely coded neural network

Contact Info

Product

Resources

About