{"type":"ScholarlyArticle","title":"Network Regions: Alternatives to the Winner-Take-All Structure","authors":[{"name":"Hon Wai Chun","slug":"hon-wai-chun","given":"Hon Wai","family":"Chun","affiliation":""},{"name":"Lawrence A. Bookman","slug":"lawrence-a-bookman","given":"Lawrence A.","family":"Bookman","affiliation":"Honeywell Bull Computer Science Department Honeywell Bull 300 Concord Road , MA30-8g5A; Brandeis University 300 Concord Road , MA30-8g5A Billerica , MA 01821-4186 Waltham , MA 02254 Billerica , : MA 01821-4186"},{"name":"Niki Afshartous","slug":"niki-afshartous","given":"Niki","family":"Afshartous","affiliation":"Honeywell Bull Computer Science Department Honeywell Bull 300 Concord Road , MA30-8g5A"}],"abstract":"Winner-take-all (WTA) structures are currently used in massively parallel (connectionist) networks to represent competitive behavior among sets of alternative hypotheses. However, this form of competition might be too rigid and not be appropriate for certain applications. For example, applications that involve noisy and erroneous inputs might mislead WTA structures into selecting a wrong outcome. In addition, for networks that continuously process input data, the outcome must dynamically change with changing inputs; WTA structures might \"lock-in\" on a previous outcome. This paper offers an alternative competition model for these applications. The model is based upon a meta-network representation scheme called network regions that are analogous to net spaces in partitioned semantic networks. Network regions can be used in many ways to clarify the representational structure in massively parallel networks. This paper focuses on how they are used to provide a fiexible and adaptive competition model. Regions can be considered as representational units that represent the conceptual abstraction of a collection of nodes (or hypotheses). Through this higher-level ab:;traction, regions can better infiuence the collective behavior or nodes within the region. Several AI applications were used to test and evaluate this model.","doi":null,"url":"https://ijcai.org/proceedings/1987/78","pdf":"https://ijcai.org/proceedings/1987/0078.pdf","markdown":"https://ijcai.org/proceedings/1987/78.md","bibtex":"https://ijcai.org/proceedings/1987/bibtex/78","volume":{"slug":"1987","title":"Proceedings of the Tenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1987","url":"https://ijcai.org/proceedings/1987/","year":1987,"location":"Milan, Italy","dates":"","editors":"John McDermott","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Knowledge Representation","track":"Knowledge Representation","number":78,"pages":{"first":380,"last":386},"keywords":[],"videos":[],"references":[{"position":1,"raw":"Feldman, J.A. and D.H. Ballard, \"Connectionist Models and Their Properties,\" Cognitive Science, 6, 1g82, pp.205-254.","title":"Connectionist Models and Their Properties","authors":"J A Feldman, D H Ballard","year":null,"venue":"Cognitive Science","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Hinton, G.E. and J.A. Anderson (eds.), Parallel Models of Associative Memory, Hillsdale: Lawrence Erlbaum Associates, 1g81.","title":"Parallel Models of Associative Memory","authors":null,"year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"Rumelhart, D.E. & McClelland, J.L., Parallel Distri- buted Processing: Explorations in the Microstructure of Cognition Volume 1, MIT Press, 1g86.","title":"Parallel Distributed Processing: Explorations in the Microstructure of Cognition","authors":"D E Rumelhart, J L Mcclelland","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"McClelland, J.L. & D.E. Rumelhart, Parallel Distri- . buted Processing: Explorations in the Microstructure of Cognition Volume 2, MIT Press, 1986.","title":"Parallel Distri-. buted Processing: Explorations in the Microstructure of Cognition","authors":"J L Mcclelland, D E Rumelhart","year":"1986","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"Shastri, L. and J.A. Feldman, \"Semantic Networks and Neural Nets,\" Computer Science Department, The University of Rochester, TR131, June, Hl84.","title":"Semantic Networks and Neural Nets","authors":"L Shastri, J A Feldman","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"Hendrix, G.G., \"Expanding the Utility of Semantic Networks Through Partitioning,\" In Proceedings of IJCAI-75, 1975, pp.115-121","title":"Expanding the Utility of Semantic Networks Through Partitioning","authors":"G G Hendrix","year":"1975","venue":"Proceedings of IJCAI-75","doi":null,"url":null,"internal_url":"/proceedings/1975/18"},{"position":7,"raw":"Brachman, R.J. and H.J. Levesque, \"On the Parti- tioning of Concerns in Knowledge Representation,\" In Proceedings of AAAI-82, Hl82.","title":"On the Partitioning of Concerns in Knowledge Representation","authors":"R J Brachman, H J Levesque","year":null,"venue":"Proceedings of AAAI-82","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"Bookman, L.A. and H.W. Chun, \"A Model of Higher- Order Concept Interaction Using Network Regions,\" Computer Science Department, Brandeis University, Technical Report, CS-87-130, Massachusetts, 1987.","title":"A Model of Higher-Order Concept Interaction Using Network Regions","authors":"L A Bookman, H W Chun","year":"1987","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"Reggia, J.A., \"Virtual Lateral Inhibition in Parallel Activation Models of Associative Memory,\" In Proceedings of IJCAI-85, 1987, pp.244-248.","title":"Virtual Lateral Inhibition in Parallel Activation Models of Associative Memory","authors":"J A Reggia","year":"1987","venue":"Proceedings of IJCAI-85","doi":null,"url":null,"internal_url":"/proceedings/1985/45"},{"position":10,"raw":"Grossberg, S., \"Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks,\" Studies in Applied Mathematics, Vol. LII, No.3, September, 1973, pp.213-257.","title":"Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks","authors":"S Grossberg","year":"1973","venue":"Studies in Applied Mathematics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Chun, H.W., \"AINET-2 User's Manual,\" Computer Science Department, Brandeis University, Technical Report, CS-86-126, Massachusetts, 1986.","title":"AINET-2 User's Manual","authors":"H W Chun","year":"1986","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"Waltz, D. 1., \"Understanding Line Drawings of Scenes with Shadows,\" in The Psychology of Com- puter Vision, P. Winston (ed), McGraw-Hill, 1975.","title":"Understanding Line Drawings of Scenes with Shadows","authors":"D Waltz","year":"1975","venue":"The Psychology of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Chun, •H.W., \"A Representation for Temporal Sequence and Duration in Massively Parall~l Net- works: Exploiting Link Interactions,\" In Proceedings of AAAI-86, August 1986.","title":"A Representation for Temporal Sequence and Duration in Massively Parall~l Networks: Exploiting Link Interactions","authors":"• H W Chun","year":"1986","venue":"Proceedings of AAAI-86","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"Wong, M.K. and H.W. Chun, \"Toward a Massively Parallel System for Word Recognition,\" 1986 IEEE- International Conference on Acoustics, Speech, and Signal Processing, Tokyo, Japan, April1986.","title":"Toward a Massively Parallel System for Word Recognition","authors":"M K Wong, H W Chun","year":"1986","venue":"IEEE-International Conference on Acoustics, Speech, and Signal Processing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"Elman, J.L. and J.L. McClelland, \"Speech Percep- tion as a Cognitive Process: The Interactive Activa- tion Model,\" In N. Lass (ed.), Speech and Language: Vol. X, Orlando, Florida, Academic, 1984.","title":"Speech Perception as a Cognitive Process: The Interactive Activation Model","authors":"J L Elman, J L Mcclelland","year":"1984","venue":"Speech and Language","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"Bookman, L.A., \"A Microfeature Based Scheme For Modelling Semantics,\" In Proceedings of IJCAI-87, 1987.","title":"A Microfeature Based Scheme For Modelling Semantics","authors":"L A Bookman","year":"1987","venue":"Proceedings of IJCAI-87","doi":null,"url":null,"internal_url":"/proceedings/1987/120"},{"position":17,"raw":"Cottrell, G.W. \"A connectionist approach to word sense disambiguation,\" (PhD thesis) TR 154, U. of Rochester CS Dept., 1985.","title":"A connectionist approach to word sense disambiguation","authors":"G W Cottrell","year":"1985","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"Waltz, D.L. and J.B. Pollack, \"Massively Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation,\" Cognitive Science, Volume 9, Number 1, January-March, 1985.","title":"Massively Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation","authors":"D L Waltz, J B Pollack","year":"1985","venue":"Cognitive Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}