Neural Computers 1989
DOI: 10.1007/978-3-642-83740-1_24
|View full text |Cite
|
Sign up to set email alerts
|

The Never-Ending Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

1994
1994
2018
2018

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 1 publication
0
5
0
Order By: Relevance
“…
Fig. 10(From [51]). Growth of a GP module, based on the coincidence between an inner-flow and incoming stimuli.
…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…
Fig. 10(From [51]). Growth of a GP module, based on the coincidence between an inner-flow and incoming stimuli.
…”
Section: Methodsmentioning
confidence: 99%
“…When initiated in 1983, the Guided Propagation (GP) system implemented concept-cells named Event - Detectors ( EDs ), considered as potential targets for inner - flows of activity. The other main feature of this deterministic approach was the recruitment of new cells for growing the memory paths ending in EDs, in response to requests of a dynamic learning algorithm [51]. In this formalism, the direction/path taken by a given inner-flow depends on the occurrence of afferent stimuli, one after the other, hence the expression: “guided propagation”.…”
Section: Introductionmentioning
confidence: 99%
“…"Teenager"-cells would then form chains or neutral memory paths in active areas, made thus ready to receive new connections from series of unexpected stimuli at the time they occur. A differentiation episode would thus be restricted to new connections established along preformed memory paths, by following a coincidence-detection criterion [25].…”
Section: Gp Dynamic Learning In Questionmentioning
confidence: 99%
“…This option lessens the role of connection weights among learning actors; emphasis is set instead on the mechanisms that promote and guide the dynamic setting of neural structures. Mainly inspired by the brain spontaneous activity, the Guided Propagation (GP) model implements the continuous growth of memory paths ending in concept cells [25]. Thirdly, at the neuroanatomical level, significant data associate reward circuits with action-selection.…”
Section: Introductionmentioning
confidence: 99%
“…This type of learning is also called lifelong or never-ending (Beroule, 1988). For example, spam filtering and classification of news feeds with ever changing features are but a few useful applications of lifelong learning (Rennie, 2000;Sahami, Dumais, Heckerman, & Horvitz, 1998).…”
Section: Introductionmentioning
confidence: 98%