1 resultado para Pattern of Use
em Boston University Digital Common
Filtro por publicador
- JISC Information Environment Repository (1)
- Aberystwyth University Repository - Reino Unido (4)
- Academic Archive On-line (Stockholm University; Sweden) (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (2)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (5)
- Aquatic Commons (29)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (1)
- Archimer: Archive de l'Institut francais de recherche pour l'exploitation de la mer (2)
- Archive of European Integration (5)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (4)
- Aston University Research Archive (37)
- Avian Conservation and Ecology - Eletronic Cientific Hournal - Écologie et conservation des oiseaux: (1)
- Biblioteca de Teses e Dissertações da USP (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (44)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (12)
- Biodiversity Heritage Library, United States (1)
- Bioline International (4)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (69)
- Boston University Digital Common (1)
- Brock University, Canada (4)
- Bucknell University Digital Commons - Pensilvania - USA (3)
- Bulgarian Digital Mathematics Library at IMI-BAS (1)
- CaltechTHESIS (1)
- Cambridge University Engineering Department Publications Database (5)
- CentAUR: Central Archive University of Reading - UK (49)
- Central European University - Research Support Scheme (1)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (40)
- Cochin University of Science & Technology (CUSAT), India (13)
- Coffee Science - Universidade Federal de Lavras (1)
- Collection Of Biostatistics Research Archive (1)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (7)
- CORA - Cork Open Research Archive - University College Cork - Ireland (3)
- Dalarna University College Electronic Archive (3)
- Deakin Research Online - Australia (55)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (1)
- Digital Archives@Colby (1)
- Digital Commons - Michigan Tech (2)
- Digital Commons at Florida International University (5)
- Digital Peer Publishing (2)
- DigitalCommons - The University of Maine Research (1)
- DigitalCommons@The Texas Medical Center (18)
- DigitalCommons@University of Nebraska - Lincoln (2)
- DRUM (Digital Repository at the University of Maryland) (1)
- Duke University (5)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (8)
- Greenwich Academic Literature Archive - UK (2)
- Helda - Digital Repository of University of Helsinki (39)
- Indian Institute of Science - Bangalore - Índia (22)
- Ministerio de Cultura, Spain (2)
- National Center for Biotechnology Information - NCBI (38)
- Nottingham eTheses (1)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (3)
- Portal de Revistas Científicas Complutenses - Espanha (8)
- Publishing Network for Geoscientific & Environmental Data (13)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (60)
- Queensland University of Technology - ePrints Archive (82)
- RCAAP - Repositório Científico de Acesso Aberto de Portugal (1)
- Repositório Alice (Acesso Livre à Informação Científica da Embrapa / Repository Open Access to Scientific Information from Embrapa) (4)
- Repositório Científico da Universidade de Évora - Portugal (1)
- Repositório digital da Fundação Getúlio Vargas - FGV (1)
- Repositório Digital da UNIVERSIDADE DA MADEIRA - Portugal (2)
- Repositório Institucional da Universidade de Aveiro - Portugal (4)
- Repositório Institucional da Universidade Federal do Rio Grande do Norte (3)
- Repositorio Institucional de la Universidad de Málaga (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (105)
- Repositorio Institucional Universidad de Medellín (1)
- Research Open Access Repository of the University of East London. (1)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (2)
- SAPIENTIA - Universidade do Algarve - Portugal (2)
- Universidad de Alicante (3)
- Universidad del Rosario, Colombia (2)
- Universidad Politécnica de Madrid (17)
- Universidade Estadual Paulista "Júlio de Mesquita Filho" (UNESP) (1)
- Universidade Federal do Pará (3)
- Universidade Federal do Rio Grande do Norte (UFRN) (9)
- Universidade Metodista de São Paulo (1)
- Universidade Técnica de Lisboa (1)
- Universitat de Girona, Spain (3)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (3)
- Université de Lausanne, Switzerland (2)
- Université de Montréal (1)
- Université de Montréal, Canada (7)
- University of Connecticut - USA (3)
- University of Michigan (19)
- University of Queensland eSpace - Australia (25)
- Worcester Research and Publications - Worcester Research and Publications - UK (1)
Resumo:
It is a neural network truth universally acknowledged, that the signal transmitted to a target node must be equal to the product of the path signal times a weight. Analysis of catastrophic forgetting by distributed codes leads to the unexpected conclusion that this universal synaptic transmission rule may not be optimal in certain neural networks. The distributed outstar, a network designed to support stable codes with fast or slow learning, generalizes the outstar network for spatial pattern learning. In the outstar, signals from a source node cause weights to learn and recall arbitrary patterns across a target field of nodes. The distributed outstar replaces the outstar source node with a source field, of arbitrarily many nodes, where the activity pattern may be arbitrarily distributed or compressed. Learning proceeds according to a principle of atrophy due to disuse whereby a path weight decreases in joint proportion to the transmittcd path signal and the degree of disuse of the target node. During learning, the total signal to a target node converges toward that node's activity level. Weight changes at a node are apportioned according to the distributed pattern of converging signals three types of synaptic transmission, a product rule, a capacity rule, and a threshold rule, are examined for this system. The three rules are computationally equivalent when source field activity is maximally compressed, or winner-take-all when source field activity is distributed, catastrophic forgetting may occur. Only the threshold rule solves this problem. Analysis of spatial pattern learning by distributed codes thereby leads to the conjecture that the optimal unit of long-term memory in such a system is a subtractive threshold, rather than a multiplicative weight.