{"type":"ScholarlyArticle","title":"Self-Organization of a Neural Network which Gives Position-Invariant Response","authors":[{"name":"Kunihiko Fukushima","slug":"kunihiko-fukushima","given":"Kunihiko","family":"Fukushima","affiliation":"NHK Broadcasting Science Research Laboratories 1-10-11 , Kinuta , Setagaya , Tokyo 157 , Japan"}],"abstract":"In this paper, I propose a new algorithm for self-organizing a multilayered neural network which has an ability to recognize patterns based on the geometrical similarity of their shapes. This network, whose nickname is \"neo-cognitron\", has a structure similar to the hierarchy model of the visual nervous system proposed by Hubel and Wiesel. The network consists of a photoreceptor layer followed by a cascade connection of a number of modular structures, each of which is composed of two layers of cells connected in a cascade. The first layer of each module consists of \"S-cells\", which show characteristics similar to simple cells or lower order hypercomplex cells, and the second layer consists of \"C-cells\" similar to complex cells or higher order hypercomplex cells. The imput synapses to each S-cell have plasticity and are modifiable. The network has an ability of unsupervised learning: We don't need any \"teacher\" during the process of self-organization, and it is only needed to present a set of stimulus patterns repeatedly to the input layer. The network has been simulated on a digital computer. After completion of self-organization, the stimulus patterns has become to elicit their own response from the last C-cell layer. That is, the response of the last C-cell layer changes without fail, if a stimulus patterns of a different category is presented to the input layer. The response of that layer, however, is not affected by the pattern's position at all. Neither is it affected by a certain amount of changes of the pattern's shape or size.","doi":null,"url":"https://ijcai.org/proceedings/1979/66","pdf":"https://ijcai.org/proceedings/1979/0066.pdf","markdown":"https://ijcai.org/proceedings/1979/66.md","bibtex":"https://ijcai.org/proceedings/1979/bibtex/66","volume":{"slug":"1979","title":"Proceedings of the Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1979","url":"https://ijcai.org/proceedings/1979/","year":1979,"location":"Tokyo, Japan","dates":"August 20-23, 1979","editors":"Bruce G. Buchanan","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":66,"pages":{"first":null,"last":null},"keywords":[],"videos":[],"references":[{"position":1,"raw":"Fukushima, K. ''Cognitron: A Self-organizing Multilayered Neural Network\". Biol. Cybernetics 20:3/4 (1975) 121-136.","title":"Cognitron: A Self-organizing Multilayered Neural Network","authors":"K Fukushima","year":"1975","venue":"Biol. Cybernetics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Hubel, D.H., Wiesel, T.N. \"Receptive Fields, Binocular Interaction and Functional Architec- ture in the Cat's Visual Cortex\". :!..:_ Physiol. (Lond.) 160:1 (1962) 106-154.","title":"Receptive Fields, Binocular Interaction and Functional Architecture in the Cat's Visual Cortex","authors":"D H Hubel, T N Wiesel","year":"1962","venue":"Physiol. (Lond.)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"Hubel, D.H., Wiesel, T.N. \"Receptive Fields and Functional Architecture in Two Nonstriate Visual Area (18 and 19) of the Cat\". :!..:_ Neuro- physiol. 28 (1965) 229-289.","title":"Receptive Fields and Functional Architecture in Two Nonstriate Visual Area (18 and 19) of the Cat","authors":"D H Hubel, T N Wiesel","year":"1965","venue":"Neurophysiol","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"Fukushima, K. \"Improvement in Pattern- Selectivity of a Cognitron\" (in Japanese). Paper of Tech. Group, MBE78-27, Inst.","title":"Improvement in Pattern-Selectivity of a Cognitron","authors":"K Fukushima","year":null,"venue":"Paper of Tech. Group","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}