2011
DOI: 10.1162/neco_a_00195
|View full text |Cite
|
Sign up to set email alerts
|

Self-Organization of Topographic Bilinear Networks for Invariant Recognition

Abstract: We present a model for the emergence of ordered fiber projections that may serve as a basis for invariant recognition. After invariance transformations are self-organized, so-called control units competitively activate fiber projections for different transformation parameters. The model builds on a well-known ontogenetic mechanism, activity-based development of retinotopy, and it employs activity blobs of varying position and size to install different transformations. We provide a detailed analysis for the cas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2012
2012
2020
2020

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(9 citation statements)
references
References 48 publications
0
9
0
Order By: Relevance
“…These are composed of cooperating signal pathways of the kind a → b → b and a → a → b , while the competition between projection fibers that diverge from one point in the image or that converge on one point in the model is important for compliance with the one-to-one structure of the mapping. These interactions between projection fibers play the central role during the slow self-organization of fiber projections to be alternatively activated under control, as modeled in detail in (Zhu et al, 2010;Bergmann and von der Malsburg, 2011;Fernandes and von der Malsburg, 2015). Such mappings make the essence of the structural relations between image and model concrete.…”
Section: Example: Invariant Object Recognitionmentioning
confidence: 99%
See 2 more Smart Citations
“…These are composed of cooperating signal pathways of the kind a → b → b and a → a → b , while the competition between projection fibers that diverge from one point in the image or that converge on one point in the model is important for compliance with the one-to-one structure of the mapping. These interactions between projection fibers play the central role during the slow self-organization of fiber projections to be alternatively activated under control, as modeled in detail in (Zhu et al, 2010;Bergmann and von der Malsburg, 2011;Fernandes and von der Malsburg, 2015). Such mappings make the essence of the structural relations between image and model concrete.…”
Section: Example: Invariant Object Recognitionmentioning
confidence: 99%
“…These distortions have to be compensated by the fiber projections to the model domain in order to re-establish the metric relations in the world. This is possible on the basis of the a priori assumption that the metrics of the world are invariant to eye movements and ego motions, thus constituting the geometry of the visual space, according to Felix Klein's Erlangen program, as demonstrated in (Zhu et al, 2010;Bergmann and von der Malsburg, 2011;Fernandes and von der Malsburg, 2015).…”
Section: Example: Invariant Object Recognitionmentioning
confidence: 99%
See 1 more Smart Citation
“…The control units, encoding the object's position, thereby route the visual information from any retinal position to an object-centered reference frame on the top-most level of the 'what' pathway [13,3,11]. Such control neurons have been hypothesized to reside in the pulvinar [1], or the mediodorsal nucleus [16], of the thalamus.…”
Section: Modeling Backgroundmentioning
confidence: 99%
“…Although there have been studies of modeling the functional modularity in the development of ventral and dorsal streams (e.g., Jacobs et al, 1991; Mareschal et al, 1999), the bilinear models of visual routing (e.g., Olshausen et al, 1993; Memisevic and Hinton, 2007; Bergmann and von der Malsburg, 2011), in which a set of control neurons dynamically modifies the weights of the “what” pathway on a short time scale, or transform-invariance models (e.g., Földiák, 1991; Wiskott and Sejnowski, 2002) by encouraging the neurons to fire invariantly while transformations are performed in their input stimuli. However, a model that explains the development of conceptualization from both streams and results in an explicit representation of conceptualization of both streams while the visual stimuli is presented is still missing in the literature.…”
Section: Introductionmentioning
confidence: 99%