Learning pulse coded spatio-temporal neurons with a local learning rule

Klaassen, Arno J.; Dev, Ajay

doi:10.1109/ijcnn.1991.155286

Cited by 2 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But we do not model the neuron with cable equation as in [18], which can be very long to integrate for large numbers of neurons. Our model is built on a simpler neuron model such as those described in [1] or [26].…”

Section: 2mentioning

confidence: 99%

See 1 more Smart Citation

Time in neural networks

Chappelier¹,

Grumbach²

1994

SIGART Bull.

View full text Add to dashboard Cite

After the revival of interest in connectionism in the eighties and its successful application to pattern recognition problems, the time has come to consider its role in the field of temporal processing. We present here a general overview of the field of temporal neural networks. In order to give a broad framework to this presentation, we first present general properties of time that are used by AI models. This sets out the properties of time: -on its own, -with respect to a problem, -with respect to a model. We then present a short summary of time processing in symbolic AI. The main part of this article, a classification of temporal neural models, is introduced by a short presentation of basic connectionist models. This classification is then made and several relevant examples are presented. We conclude the article with underlining the difference between temporal reasoning and neural temporal processing, and give an introduction to the following papers of this Sigart speciM section.

show abstract

Section: 2mentioning

confidence: 99%

“…Klaassen [18] too manages connections with temporal weights, but he also introduces time at the neuron level. The neuron model, coming from biology, consists of modeling neuron electrical activity propagation with cable differential equations (hke electrical cables).…”

Section: 2mentioning

confidence: 99%

Time in neural networks

Chappelier¹,

Grumbach²

1994

SIGART Bull.

View full text Add to dashboard Cite

show abstract

“…which basically Increments a weight upon detection of coincidence of a high post-synaptic potential and the arrival of an action potential althe very same synapse. could accountfor learning a tonic version of the classical XOR-problem with a low frequency Input standing for a 0 and a high one for a 1 (3). In this paper we question why It does so and whether changing a weight Is the sole or even the best way to Implement adaptive behaviour.…”

mentioning

confidence: 96%

On the Adapative Capabilities of Pulse-Coded Cable Neurons

Klaassen

Hoekstra

1993

Icann ’93

View full text Add to dashboard Cite

Learning pulse coded spatio-temporal neurons with a local learning rule

Cited by 2 publications

References 5 publications

Time in neural networks

Time in neural networks

On the Adapative Capabilities of Pulse-Coded Cable Neurons

Contact Info

Product

Resources

About