+ Resolve Article
+ Follow Us
Follow on FacebookFollow on Facebook
Follow on TwitterFollow on Twitter

+ Translate
+ Subscribe to Site Feed
GeoScience Most Shared ContentMost Shared Content

Pattern classification by adaptive machines

, : Pattern classification by adaptive machines. Science 156(3771): 38-44

Man's intelligent behavior is due in part to his ability to select, classify, and abstract significant information reaching him from his environment by way of his senses. This function, pattern recognition, has become a major focus of research by scientists working in the field of artificial intelligence. At the lowest level, pattern recognition reduces to pattern classification, which consists of the separation, into desired classes, of groups of objects, sounds, odors, events, properties, and the like; the separations are based on sets of measurements made on the entities being classified. The pattern classifier is composed of a data filter and a categorizer. The data filter selects the distinguishing features and represents them as sets of real numbers; each set is termed a pattern. The categorizer assigns each pattern to one of several desired classes. Patterns can be represented geometrically as points in an n-dimensional space; the n coordinates of each point are the numerical values of the features selected to represent the pattern. A pattern classification system separates an n-dimensional space into regions, each of which ideally contains points of only one class. One method to effect this separation is by means of ldquo;trainablerdquo; categorizers-major components of adaptive machines. They consist of networks whose internal parameters are varied according to a set of fixed rules during a training cycle. A statistically large sample of known patterns are presented, one at a time, to the networks; internal corrections are made each time a pattern is erroneously classified. Classifica-tion performance tends to improve as the set of known patterns is cycled repetitively through the machine. Finally, the adequacy of adaptation is tested by a separate set of similar patterns which have not been used in the training process. A number of different machine organizations and training rules have been developed and are being applied successfully to numerous classification problems. More difficult recognition problems requiring the aid of logioal tests and analysis, search and association, use the digital computer programmed to supplement the functions of the adaptive classifier.


PMID: 6020036

DOI: 10.1126/science.156.3771.38

Other references

Wager, E.; Woolley, K.; Adshead, V.; Cairns, A.; Fullam, J.; Gonzalez, J.; Grant, T.; Tortell, S., 2014: Awareness and enforcement of guidelines for publishing industry-sponsored medical research among publication professionals: the Global Publication Survey. To gather information about current practices and implementation of publication guidelines among publication professionals working in or for the pharmaceutical industry. Web-based survey publicised via email and social media to members of the Inte...

Richardson, S.; Twente, S.; Audhya, T., 1988: GHRF causes biphasic stimulation of SRIF secretion from rat hypothalamic cells. The complex interactions of the hypothalamic releasing peptides somatostatin (SRIF) and growth hormone (GH)-releasing hormone (GHRF), which regulate GH secretion, are still incompletely understood. To further scrutinize these interactions, we have...

Lehew, J.L., 1954: Evaluation of an amphetamine-barbiturate combination in the supportive treatment of the aged. A 1 yr. controlled study is reported of a d-amphetamine sulfate-amobarbital combination (Dexamyl) in the treatment of 52 very old residents of the Masonic Home for the Aged in Guthrie, Oklahoma. Four 3 mo. evaluations of the drug were made. Placeb...

Willemze R.; Fibbe W.E.; Zwaan F.E., 1983: Experience with intermediate and high dose cytosine arabinoside in refractory acute leukemia. Consecutive patients (28), age 15-58 yr with refractory acute leukemia (24 AML [acute myelocytic leukemia], 4 ALL [acute lymphocyte leukemia]) were treated with high or intermediate dose cytosine arabinoside (AraC). Twenty patients received AraC a...

Tanaka, S., 1990: Estimation of natural mortality coefficient of whales from the estimates of abundance and age composition data obtained from research catches. International Whaling Commission Report of the Commission, 40: 531-536

Kanthi, M.S.; Ridgel, G.T., 1977: Higher education and manpower utilization: lessons to developing world. Higher education can emphasize either the planning principle of manpower or the principle of free choice. In recent years the manpower principle, which rations higher education according to society's needs appears to be a more meaningful way...; P.K.eine; H. -J.S.hmoll, 1986: Pleurodesis using fibrin glue in the treatment of recurrent malignant pleural effusions. Journal of Cancer Research and Clinical Oncology 111(1 Supplement): S67-0

Hwang, I.Chul.; Kumar, R.; Kim, N.Dong.; Chun, Y.; Lee, J.Woo.; Kumar, P.; Mana, R.S.; Choi, C.; Lee, J.Rhung.; Kim, K.S., 2009: Controlling metal nanotoppings on the tip of silicide nanostructures. Utilizing the difference in surface tension between SiO2 and metal catalysts (Mn2+, Ni2+), we show how metals form nanoshells, nanodiscs and nanospheres at the tips of the SiO2 nanostructures of nanocones, nanorods and nanowires. For the Mn2+ cata...

Beach, D.F.; Somer, R., 2011: Novel approach to Gorlin syndrome: a patient treated with oral capecitabine. Journal of Clinical Oncology 29(14): E397-E401

Mäcke, H., 1991: Radiopharmaceuticals in kidney diagnosis. Nuclear medicine is potentially of great value in assessing renal function. Due to the many simple methods which have been proposed and new developments in renal radiopharmaceuticals and computer software, quick, reliable and precise answers to qu...