- AutorIn
- Arash Kermani Kolankeh
- Titel
- Inhibition and loss of information in unsupervised feature extraction
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:ch1-qucosa2-209294
- Datum der Einreichung
- 09.10.2017
- Datum der Verteidigung
- 07.03.2018
- Abstract (EN)
- In this thesis inhibition as a means for competition among neurons in an unsupervised learning system is studied. In the first part of the thesis, the role of inhibition in robustness against loss of information in the form of occlusion in visual data is investigated. In the second part, inhibition as a reason for loss of information in the mathematical models of neural system is addressed. In that part, a learning rule for modeling inhibition with lowered loss of information and also a dis-inhibitory system which induces a winner-take-all mechanism are introduced. The models used in this work are unsupervised feature extractors made of biologically plausible neural networks which simulate the V1 layer of the visual cortex.
- Freie Schlagwörter (DE)
- Neuronale Netze, Neuronale Inhibition, Wettbewerb, Informationsverlust, Maschinelles Lernen, visueller Kortex, Objekterkennung
- Freie Schlagwörter (EN)
- unsupervised featuer extraction, competition, inhibition, hebbian learning, deep learning, loss of Information
- Klassifikation (DDC)
- 004
- Normschlagwörter (GND)
- Neuronales Netz, Wettbewerb, Maschinelles Lernen, Visueller Kortex, Objekterkennung
- GutachterIn
- Prof. Dr. Fred H. Hamker
- Prof. Dr. Vladimir Grigorievich Spitsyn
- BetreuerIn Hochschule / Universität
- Prof. Dr. Fred H. Hamker
- Den akademischen Grad verleihende / prüfende Institution
- Technische Universität Chemnitz, Chemnitz
- Version / Begutachtungsstatus
- angenommene Version / Postprint / Autorenversion
- URN Qucosa
- urn:nbn:de:bsz:ch1-qucosa2-209294
- Veröffentlichungsdatum Qucosa
- 27.03.2018
- Dokumenttyp
- Dissertation
- Sprache des Dokumentes
- Englisch