1155:, greedy grammar inference algorithms make, in iterative manner, decisions that seem to be the best at that stage. The decisions made usually deal with things like the creation of new rules, the removal of existing rules, the choice of a rule to be applied or the merging of some existing rules. Because there are several ways to define 'the stage' and 'the best', there are also several greedy grammar inference algorithms.
1349:
1014:
The simplest form of learning is where the learning algorithm merely receives a set of examples drawn from the language in question: the aim is to learn the language from examples of it (and, rarely, from counter-examples, that is, example that do not belong to the language). However, other learning
1130:
In the case of grammar induction, the transplantation of sub-trees corresponds to the swapping of production rules that enable the parsing of phrases from some language. The fitness operator for the grammar is based upon some measure of how well it performed in parsing some group of sentences from
1121:
programs as trees. He was able to find analogues to the genetic operators within the standard set of tree operators. For example, swapping sub-trees is equivalent to the corresponding process of genetic crossover, where sub-strings of a genetic code are transplanted into an individual of the next
1069:
suggests successively guessing grammar rules (productions) and testing them against positive and negative observations. The rule set is expanded so as to be able to generate each positive example, but if a given rule set also generates a negative example, it must be discarded. This particular
978:
or automaton of some kind) from a set of observations, thus constructing a model which accounts for the characteristics of the observed objects. More generally, grammatical inference is that branch of machine learning where the instance space consists of discrete combinatorial objects such as
1937:
1045:. A more recent textbook is de la Higuera (2010), which covers the theory of grammatical inference of regular languages and finite state automata. D'Ulizia, Ferri and Grifoni provide a survey that explores grammatical inference methods for natural languages.
1222:
from a disjoint set". The language of such a pattern is the set of all its nonempty ground instances i.e. all strings resulting from consistent replacement of its variable symbols by nonempty strings of constant symbols. A pattern is called
1126:
of the Lisp code. Similar analogues between the tree structured lisp representation and the representation of grammars as trees, made the application of genetic programming techniques possible for grammar induction.
1015:
models have been studied. One frequently studied alternative is the case where the learner can ask membership queries as in the exact query learning model or minimally adequate teacher model introduced by
Angluin.
1267:
in that it does not begin by prescribing algorithms and machinery to recognize and classify patterns; rather, it prescribes a vocabulary to articulate and recast the pattern concepts in precise language.
1830:
998:
and richer formalisms, such as multiple context-free grammars and parallel multiple context-free grammars. Other classes of grammars for which grammatical inference has been studied are
1673:
1035:
also devote a brief section to the problem, and cite a number of references. The basic trial-and-error method they present is discussed below. For approaches to infer subclasses of
1430:
1110:. Other early work on simple formal languages used the binary string representation of genetic algorithms, but the inherently hierarchical structure of grammars couched in the
1078:
text provide a simple example which nicely illustrates the process, but the feasibility of such an unguided trial-and-error approach for more substantial problems is dubious.
863:
901:
1496:
1470:
1450:
1924:
1898:
858:
848:
1234:. To this end, she builds an automaton representing all possibly relevant patterns; using sophisticated arguments about word lengths, which rely on
689:
1750:
1227:
for a finite input set of strings if its language is minimal (with respect to set inclusion) among all pattern languages subsuming the input set.
2076:
896:
1733:
1295:
Broad in its mathematical coverage, pattern theory spans algebra and statistics, as well as local topological and global entropic properties.
1716:
1320:
853:
704:
1662:." Proceedings of the 2001 workshop on Computational Natural Language Learning-Volume 7. Association for Computational Linguistics, 2001.
435:
1888:." Proceedings of the 32nd annual meeting on Association for Computational Linguistics. Association for Computational Linguistics, 1994.
936:
739:
1282:
Formulate prior distributions for hidden variables and models for the observed variables that form the vertices of a Gibbs-like graph.
1169:
creates a context-free grammar in a deterministic way such that it is necessary to store only the start rule of the generated grammar.
1646:
1356:
987:
Grammatical inference has often been very focused on the problem of learning finite state machines of various types (see the article
1976:
Charikar, M.; Lehman, E.; Liu, D.; Panigrahy, R.; Prabharakan, M.; Sahai, A.; Shelat, A. (2005), "The
Smallest Grammar Problem",
1512:
815:
1850:"Finding Minimal Generalizations for Unions of Pattern Languages and Its Application to Inductive Inference from Positive Data"
1606:
364:
1179:
These context-free grammar generating algorithms first read the whole given symbol-sequence and then start to make decisions:
1195:
A more recent approach is based on distributional learning. Algorithms using these approaches have been applied to learning
2132:
1532:
1135:
of a production rule corresponds to a leaf node of the tree. Its parent nodes corresponds to a non-terminal symbol (e.g. a
873:
636:
171:
1241:
Erlebach et al. give a more efficient version of
Angluin's pattern learning algorithm, as well as a parallelized version.
1562:
1208:
891:
1230:
Angluin gives a polynomial algorithm to compute, for a given input string set, all descriptive patterns in one variable
2137:
1476:) is known to be NP-hard, so many grammar-transform algorithms are proposed from theoretical and practical viewpoints.
1244:
Arimura et al. show that a language class obtained from limited unions of patterns can be learned in polynomial time.
1054:
724:
699:
648:
1517:
1200:
772:
767:
420:
1849:
1090:
is the process of evolving a representation of the grammar of a target language through some evolutionary process.
430:
68:
1003:
1312:
1041:
999:
991:
for details on these approaches), since there have been efficient algorithms for this problem since the 1980s.
988:
970:
929:
825:
589:
410:
1542:
1111:
800:
502:
278:
2127:
1950:
Kieffer, J. C.; Yang, E.-H. (2000), "Grammar-based codes: A new class of universal lossless source codes",
757:
694:
604:
582:
425:
415:
1831:"Learning One-Variable Pattern Languages Very Efficiently on Average, in Parallel, and by Asking Queries"
1389:
1304:
1118:
908:
820:
805:
266:
88:
1561:
The language of a pattern with at least two occurrences of the same variable is not regular due to the
994:
Since the beginning of the century, these approaches have been extended to the problem of inference of
868:
795:
545:
440:
228:
161:
121:
1279:
of a data set using real world data rather than artificial stimuli, which was commonplace at the time.
2015:
1383:
1316:
922:
528:
296:
166:
2101:
2086:
1695:
1473:
550:
470:
393:
311:
141:
103:
98:
58:
53:
1288:
Create the basic classes of stochastic models applied by listing the deformations of the patterns.
2110:
2082:
1681:
1264:
1260:
497:
346:
246:
73:
1642:
1690:
1271:
In addition to the new algebraic vocabulary, its statistical approach was novel in its aim to:
1087:
677:
653:
555:
316:
291:
251:
63:
1023:
There is a wide variety of methods for grammatical inference. Two of the classic sources are
2064:
1753:
Proceedings of the 25th annual ACM symposium on User interface software and technology. 2012.
1537:
1527:
1522:
1352:
1196:
1095:
1070:
approach can be characterized as "hypothesis testing" and bears some similarity to
Mitchel's
995:
631:
453:
405:
261:
176:
48:
2034:
1911:
1379:
1159:
1123:
975:
560:
510:
1660:
Unsupervised induction of stochastic context-free grammars using distributional clustering
1143:) in the rule set. Ultimately, the root node might correspond to a sentence non-terminal.
8:
1901:." Proceedings of the MT Summit VIII Workshop on Example-Based Machine Translation. 2001.
1203:
and have been proven to be correct and efficient for large subclasses of these grammars.
1103:
663:
599:
570:
475:
301:
234:
220:
206:
181:
131:
83:
43:
2147:
1993:
1708:
1481:
1455:
1435:
1371:
1360:
1341:
1324:
1183:
1172:
641:
565:
351:
146:
1645:." Proceedings of the conference on empirical methods in natural language processing.
1810:
1793:
1704:
1499:
1328:
1036:
734:
577:
490:
286:
256:
201:
151:
93:
1871:
1712:
1615:
1263:
to describe knowledge of the world as patterns. It differs from other approaches to
2142:
1997:
1985:
1959:
1805:
1700:
1375:
1308:
1152:
957:
762:
515:
465:
375:
359:
329:
191:
186:
136:
126:
24:
1826:
1276:
1132:
790:
594:
460:
400:
2068:
1252:
1091:
961:
810:
341:
78:
2121:
2021:
1847:
1824:
1256:
1071:
729:
658:
540:
271:
156:
1989:
1659:
1885:
1140:
1136:
535:
29:
1835:
Proc. 8th
International Workshop on Algorithmic Learning Theory — ALT'97
1303:
The principle of grammar induction has been applied to other aspects of
1734:
A Survey of
Grammatical Inference Methods for Natural Language Learning
684:
380:
306:
1963:
1291:
Synthesize (sample) from the models, not just analyze signals with it.
1764:"Compound probabilistic context-free grammars for grammar induction."
1238:
being the only variable, the state count can be drastically reduced.
1107:
1099:
1098:
of production rules that can be subjected to evolutionary operators.
843:
624:
1643:
Lexical generalization in CCG grammar induction for semantic parsing
2060:
1927:." DIMACS Working Group on The Burrows–Wheeler Transform 21 (2004).
1763:
1472:. The problem of finding a smallest grammar for an input sequence (
1382:(CFG) for the string to be compressed. Examples include universal
1162:
generating algorithms make the decision after every read symbol:
619:
2047:
1938:"Time series anomaly discovery with grammar-based compression."
1122:
generation. Fitness is measured by scoring the output from the
370:
1131:
the target language. In a tree representation of a grammar, a
1081:
1146:
614:
609:
336:
1912:
Probabilistic models of language processing and acquisition
1751:"Learning design patterns with bayesian grammar induction."
1364:
1060:
2014:
Duda, Richard O.; Hart, Peter E.; Stork, David G. (2001),
1975:
1848:
Hiroki
Arimura; Takeshi Shinohara; Setsuko Otsuki (1994).
1348:
1674:"Learning Regular Sets from Queries and Counter-Examples"
1166:
902:
List of datasets in computer vision and image processing
1614:. Cambridge: Cambridge University Press. Archived from
1600:
1598:
1307:, and has been applied (among many other problems) to
1048:
1914:." Trends in cognitive sciences 10.7 (2006): 335-344.
1899:
Transfer-rule induction for example-based translation
1608:
Grammatical
Inference: Learning Automata and Grammars
1484:
1458:
1438:
1392:
1355:(with start symbol Ăź) for the second sentence of the
1285:
Study the randomness and variability of these graphs.
1595:
2063:: Stanford University Computer Science Department,
1837:. LNAI. Vol. 1316. Springer. pp. 260–276.
1513:
Artificial grammar learning#Artificial intelligence
1498:is further compressed by statistical encoders like
1859:. LNCS. Vol. 775. Springer. pp. 649–660.
1490:
1464:
1444:
1424:
2119:
1875:. Vol. 1. Oxford: Oxford university press, 2007.
1872:Pattern theory: from representation to inference
1206:
1886:Hidden understanding models of natural language
1577:may occur several times, but no other variable
1378:algorithms based on the idea of constructing a
1218:to be "a string of constant symbols from ÎŁ and
2031:Syntactic Pattern Recognition and Applications
1762:Kim, Yoon, Chris Dyer, and Alexander M. Rush.
1114:language made trees a more flexible approach.
897:List of datasets for machine-learning research
2013:
1794:"Finding Patterns Common to a Set of Strings"
1732:D’Ulizia, A., Ferri, F., Grifoni, P. (2011) "
1637:
1635:
1604:
1075:
1066:
1032:
1006:, contextual grammars and pattern languages.
930:
1791:
1671:
2044:Syntactic Pattern Recognition, Applications
1949:
1910:Chater, Nick, and Christopher D. Manning. "
1082:Grammatical inference by genetic algorithms
1053:There are several methods for induction of
1925:Grammar-based compression of DNA sequences
1825:T. Erlebach; P. Rossmanith; H. Stadtherr;
1632:
1190:
1147:Grammatical inference by greedy algorithms
937:
923:
1809:
1694:
1647:Association for Computational Linguistics
1357:United States Declaration of Independence
1334:
1923:Cherniavsky, Neva, and Richard Ladner. "
1386:algorithms. To compress a data sequence
1347:
1061:Grammatical inference by trial-and-error
2054:
1869:Grenander, Ulf, and Michael I. Miller.
1798:Journal of Computer and System Sciences
1766:arXiv preprint arXiv:1906.10225 (2019).
2120:
1065:The method proposed in Section 8.7 of
2103:Language Identification in the Limit
2099:
2078:Language Identification in the Limit
2074:
1777:Journal of Machine Learning Research
1533:Language identification in the limit
1425:{\displaystyle x=x_{1}\cdots x_{n}}
1055:probabilistic context-free grammars
1049:Induction of probabilistic grammars
892:Glossary of artificial intelligence
13:
2085:, pp. 447–474, archived from
2041:
2028:
1432:, a grammar-based code transforms
1201:mildly context-sensitive languages
1028:
1024:
1009:
982:
14:
2159:
1518:Example-based machine translation
1374:or Grammar-based compression are
1247:
2057:A Study of Grammatical Inference
1478:Generally, the produced grammar
1359:. Each blue character denotes a
1340:This section is an excerpt from
1018:
1004:stochastic context-free grammars
1969:
1943:
1930:
1917:
1904:
1891:
1878:
1863:
1841:
1833:. In M. Li; A. Maruoka (eds.).
1818:
1785:
1568:
1298:
1000:combinatory categorial grammars
1769:
1756:
1743:
1738:Artificial Intelligence Review
1726:
1665:
1652:
1555:
1313:natural language understanding
1042:Induction of regular languages
989:Induction of regular languages
312:Relevance vector machine (RVM)
1:
1605:de la Higuera, Colin (2010).
1588:
1543:Syntactic pattern recognition
1367:-compression of the sentence.
1094:can easily be represented as
1076:Duda, Hart & Stork (2001)
1067:Duda, Hart & Stork (2001)
1033:Duda, Hart & Stork (2001)
801:Computational learning theory
365:Expectation–maximization (EM)
1811:10.1016/0022-0000(80)90041-0
1781:Theoretical Computer Science
1705:10.1016/0890-5401(87)90052-6
1452:into a context-free grammar
1363:; they were obtained from a
1086:Grammatical induction using
964:(usually as a collection of
758:Coefficient of determination
605:Convolutional neural network
317:Support vector machine (SVM)
7:
2133:Natural language processing
2055:Horning, James Jay (1969),
1740:, Vol. 36, No. 1, pp. 1–27.
1506:
1305:natural language processing
1102:of this sort stem from the
979:strings, trees and graphs.
909:Outline of machine learning
806:Empirical risk minimization
10:
2164:
2007:
1641:Kwiatkowski, Tom, et al. "
1339:
1167:Lempel-Ziv-Welch algorithm
546:Feedforward neural network
297:Artificial neural networks
2138:Computational linguistics
2059:(Ph.D. Thesis ed.),
1384:lossless data compression
1325:grammar-based compression
1317:example-based translation
529:Artificial neural network
1775:Clark and Eyraud (2007)
1548:
1474:smallest grammar problem
838:Journals and conferences
785:Mathematical foundations
695:Temporal difference (TD)
551:Recurrent neural network
471:Conditional random field
394:Dimensionality reduction
142:Dimensionality reduction
104:Quantum machine learning
99:Neuromorphic engineering
59:Self-supervised learning
54:Semi-supervised learning
2111:Information and Control
2083:Information and Control
2024:: John Wiley & Sons
1990:10.1109/tit.2005.850116
1978:IEEE Trans. Inf. Theory
1952:IEEE Trans. Inf. Theory
1884:Miller, Scott, et al. "
1779:; Ryo Yoshinaka (2011)
1682:Information and Control
1265:artificial intelligence
1191:Distributional learning
1088:evolutionary algorithms
247:Apprenticeship learning
2100:Gold, E. Mark (1967),
2075:Gold, E. Mark (1967),
2017:Pattern Classification
1829:; T. Zeugmann (1997).
1749:Talton, Jerry, et al.
1492:
1466:
1446:
1426:
1368:
1335:Compression algorithms
1186:and its optimizations.
1175:and its modifications.
1106:paradigm pioneered by
974:or alternatively as a
796:Bias–variance tradeoff
678:Reinforcement learning
654:Spiking neural network
64:Reinforcement learning
2042:Fu, King Sun (1977),
2029:Fu, King Sun (1982),
1936:Senin, Pavel, et al.
1792:Dana Angluin (1980).
1672:Dana Angluin (1987).
1538:Straight-line grammar
1528:Kolmogorov complexity
1523:Inductive programming
1493:
1467:
1447:
1427:
1353:Straight-line grammar
1351:
1197:context-free grammars
996:context-free grammars
954:grammatical inference
632:Neural radiance field
454:Structured prediction
177:Structured prediction
49:Unsupervised learning
2035:Englewood Cliffs, NJ
1482:
1456:
1436:
1390:
1380:context-free grammar
1321:language acquisition
1259:, is a mathematical
1160:context-free grammar
976:finite state machine
956:) is the process in
821:Statistical learning
719:Learning with humans
511:Local outlier factor
2128:Genetic programming
1658:Clark, Alexander. "
1372:Grammar-based codes
1104:genetic programming
1039:in particular, see
664:Electrochemical RAM
571:reservoir computing
302:Logistic regression
221:Supervised learning
207:Multimodal learning
182:Feature engineering
127:Generative modeling
89:Rule-based learning
84:Curriculum learning
44:Supervised learning
19:Part of a series on
2113:, pp. 447–474
1488:
1462:
1442:
1422:
1369:
1361:nonterminal symbol
1342:Grammar-based code
1214:Angluin defines a
1184:Byte pair encoding
232: •
147:Density estimation
2050:: Springer-Verlag
1964:10.1109/18.841160
1500:arithmetic coding
1491:{\displaystyle G}
1465:{\displaystyle G}
1445:{\displaystyle x}
1329:anomaly detection
1209:pattern languages
1153:greedy algorithms
1117:Koza represented
1037:regular languages
950:Grammar induction
947:
946:
752:Model diagnostics
735:Human-in-the-loop
578:Boltzmann machine
491:Anomaly detection
287:Linear regression
202:Ontology learning
197:Grammar induction
172:Semantic analysis
167:Association rules
152:Anomaly detection
94:Neuro-symbolic AI
2155:
2114:
2109:, vol. 10,
2108:
2096:
2095:
2094:
2081:, vol. 10,
2071:
2051:
2038:
2025:
2001:
2000:
1984:(7): 2554–2576,
1973:
1967:
1966:
1947:
1941:
1934:
1928:
1921:
1915:
1908:
1902:
1897:Brown, Ralf D. "
1895:
1889:
1882:
1876:
1867:
1861:
1860:
1854:
1845:
1839:
1838:
1822:
1816:
1815:
1813:
1789:
1783:
1773:
1767:
1760:
1754:
1747:
1741:
1730:
1724:
1723:
1721:
1715:. Archived from
1698:
1678:
1669:
1663:
1656:
1650:
1639:
1630:
1629:
1627:
1626:
1620:
1613:
1602:
1582:
1572:
1566:
1559:
1497:
1495:
1494:
1489:
1471:
1469:
1468:
1463:
1451:
1449:
1448:
1443:
1431:
1429:
1428:
1423:
1421:
1420:
1408:
1407:
1309:semantic parsing
1277:hidden variables
1255:, formulated by
1220:variable symbols
958:machine learning
939:
932:
925:
886:Related articles
763:Confusion matrix
516:Isolation forest
461:Graphical models
240:
239:
192:Learning to rank
187:Feature learning
25:Machine learning
16:
15:
2163:
2162:
2158:
2157:
2156:
2154:
2153:
2152:
2118:
2117:
2106:
2092:
2090:
2037:: Prentice-Hall
2010:
2005:
2004:
1974:
1970:
1948:
1944:
1935:
1931:
1922:
1918:
1909:
1905:
1896:
1892:
1883:
1879:
1868:
1864:
1852:
1846:
1842:
1823:
1819:
1790:
1786:
1774:
1770:
1761:
1757:
1748:
1744:
1731:
1727:
1719:
1696:10.1.1.187.9414
1676:
1670:
1666:
1657:
1653:
1640:
1633:
1624:
1622:
1618:
1611:
1603:
1596:
1591:
1586:
1585:
1573:
1569:
1560:
1556:
1551:
1509:
1504:
1503:
1483:
1480:
1479:
1457:
1454:
1453:
1437:
1434:
1433:
1416:
1412:
1403:
1399:
1391:
1388:
1387:
1345:
1337:
1301:
1250:
1212:
1193:
1149:
1133:terminal symbol
1096:tree structures
1092:Formal grammars
1084:
1074:algorithm. The
1063:
1051:
1021:
1012:
1010:Learning models
985:
983:Grammar classes
943:
914:
913:
887:
879:
878:
839:
831:
830:
791:Kernel machines
786:
778:
777:
753:
745:
744:
725:Active learning
720:
712:
711:
680:
670:
669:
595:Diffusion model
531:
521:
520:
493:
483:
482:
456:
446:
445:
401:Factor analysis
396:
386:
385:
369:
332:
322:
321:
242:
241:
225:
224:
223:
212:
211:
117:
109:
108:
74:Online learning
39:
27:
12:
11:
5:
2161:
2151:
2150:
2145:
2140:
2135:
2130:
2116:
2115:
2097:
2072:
2052:
2039:
2026:
2020:(2 ed.),
2009:
2006:
2003:
2002:
1968:
1958:(3): 737–754,
1942:
1929:
1916:
1903:
1890:
1877:
1862:
1857:Proc. STACS 11
1840:
1817:
1784:
1768:
1755:
1742:
1725:
1722:on 2013-12-02.
1664:
1651:
1631:
1593:
1592:
1590:
1587:
1584:
1583:
1567:
1553:
1552:
1550:
1547:
1546:
1545:
1540:
1535:
1530:
1525:
1520:
1515:
1508:
1505:
1487:
1461:
1441:
1419:
1415:
1411:
1406:
1402:
1398:
1395:
1346:
1338:
1336:
1333:
1300:
1297:
1293:
1292:
1289:
1286:
1283:
1280:
1253:Pattern theory
1249:
1248:Pattern theory
1246:
1211:
1205:
1192:
1189:
1188:
1187:
1177:
1176:
1170:
1148:
1145:
1083:
1080:
1062:
1059:
1050:
1047:
1020:
1017:
1011:
1008:
984:
981:
966:re-write rules
962:formal grammar
960:of learning a
945:
944:
942:
941:
934:
927:
919:
916:
915:
912:
911:
906:
905:
904:
894:
888:
885:
884:
881:
880:
877:
876:
871:
866:
861:
856:
851:
846:
840:
837:
836:
833:
832:
829:
828:
823:
818:
813:
811:Occam learning
808:
803:
798:
793:
787:
784:
783:
780:
779:
776:
775:
770:
768:Learning curve
765:
760:
754:
751:
750:
747:
746:
743:
742:
737:
732:
727:
721:
718:
717:
714:
713:
710:
709:
708:
707:
697:
692:
687:
681:
676:
675:
672:
671:
668:
667:
661:
656:
651:
646:
645:
644:
634:
629:
628:
627:
622:
617:
612:
602:
597:
592:
587:
586:
585:
575:
574:
573:
568:
563:
558:
548:
543:
538:
532:
527:
526:
523:
522:
519:
518:
513:
508:
500:
494:
489:
488:
485:
484:
481:
480:
479:
478:
473:
468:
457:
452:
451:
448:
447:
444:
443:
438:
433:
428:
423:
418:
413:
408:
403:
397:
392:
391:
388:
387:
384:
383:
378:
373:
367:
362:
357:
349:
344:
339:
333:
328:
327:
324:
323:
320:
319:
314:
309:
304:
299:
294:
289:
284:
276:
275:
274:
269:
264:
254:
252:Decision trees
249:
243:
229:classification
219:
218:
217:
214:
213:
210:
209:
204:
199:
194:
189:
184:
179:
174:
169:
164:
159:
154:
149:
144:
139:
134:
129:
124:
122:Classification
118:
115:
114:
111:
110:
107:
106:
101:
96:
91:
86:
81:
79:Batch learning
76:
71:
66:
61:
56:
51:
46:
40:
37:
36:
33:
32:
21:
20:
9:
6:
4:
3:
2:
2160:
2149:
2146:
2144:
2141:
2139:
2136:
2134:
2131:
2129:
2126:
2125:
2123:
2112:
2105:
2104:
2098:
2089:on 2016-08-28
2088:
2084:
2080:
2079:
2073:
2070:
2066:
2062:
2058:
2053:
2049:
2045:
2040:
2036:
2032:
2027:
2023:
2019:
2018:
2012:
2011:
1999:
1995:
1991:
1987:
1983:
1979:
1972:
1965:
1961:
1957:
1953:
1946:
1939:
1933:
1926:
1920:
1913:
1907:
1900:
1894:
1887:
1881:
1874:
1873:
1866:
1858:
1851:
1844:
1836:
1832:
1828:
1821:
1812:
1807:
1803:
1799:
1795:
1788:
1782:
1778:
1772:
1765:
1759:
1752:
1746:
1739:
1735:
1729:
1718:
1714:
1710:
1706:
1702:
1697:
1692:
1689:(2): 87–106.
1688:
1684:
1683:
1675:
1668:
1661:
1655:
1648:
1644:
1638:
1636:
1621:on 2019-02-14
1617:
1610:
1609:
1601:
1599:
1594:
1580:
1576:
1571:
1564:
1563:pumping lemma
1558:
1554:
1544:
1541:
1539:
1536:
1534:
1531:
1529:
1526:
1524:
1521:
1519:
1516:
1514:
1511:
1510:
1501:
1485:
1477:
1475:
1459:
1439:
1417:
1413:
1409:
1404:
1400:
1396:
1393:
1385:
1381:
1377:
1373:
1366:
1362:
1358:
1354:
1350:
1343:
1332:
1330:
1326:
1322:
1318:
1314:
1310:
1306:
1296:
1290:
1287:
1284:
1281:
1278:
1275:Identify the
1274:
1273:
1272:
1269:
1266:
1262:
1258:
1257:Ulf Grenander
1254:
1245:
1242:
1239:
1237:
1233:
1228:
1226:
1221:
1217:
1210:
1204:
1202:
1198:
1185:
1182:
1181:
1180:
1174:
1171:
1168:
1165:
1164:
1163:
1161:
1156:
1154:
1144:
1142:
1138:
1134:
1128:
1125:
1120:
1115:
1113:
1109:
1105:
1101:
1097:
1093:
1089:
1079:
1077:
1073:
1072:version space
1068:
1058:
1056:
1046:
1044:
1043:
1038:
1034:
1030:
1026:
1019:Methodologies
1016:
1007:
1005:
1001:
997:
992:
990:
980:
977:
973:
972:
967:
963:
959:
955:
951:
940:
935:
933:
928:
926:
921:
920:
918:
917:
910:
907:
903:
900:
899:
898:
895:
893:
890:
889:
883:
882:
875:
872:
870:
867:
865:
862:
860:
857:
855:
852:
850:
847:
845:
842:
841:
835:
834:
827:
824:
822:
819:
817:
814:
812:
809:
807:
804:
802:
799:
797:
794:
792:
789:
788:
782:
781:
774:
771:
769:
766:
764:
761:
759:
756:
755:
749:
748:
741:
738:
736:
733:
731:
730:Crowdsourcing
728:
726:
723:
722:
716:
715:
706:
703:
702:
701:
698:
696:
693:
691:
688:
686:
683:
682:
679:
674:
673:
665:
662:
660:
659:Memtransistor
657:
655:
652:
650:
647:
643:
640:
639:
638:
635:
633:
630:
626:
623:
621:
618:
616:
613:
611:
608:
607:
606:
603:
601:
598:
596:
593:
591:
588:
584:
581:
580:
579:
576:
572:
569:
567:
564:
562:
559:
557:
554:
553:
552:
549:
547:
544:
542:
541:Deep learning
539:
537:
534:
533:
530:
525:
524:
517:
514:
512:
509:
507:
505:
501:
499:
496:
495:
492:
487:
486:
477:
476:Hidden Markov
474:
472:
469:
467:
464:
463:
462:
459:
458:
455:
450:
449:
442:
439:
437:
434:
432:
429:
427:
424:
422:
419:
417:
414:
412:
409:
407:
404:
402:
399:
398:
395:
390:
389:
382:
379:
377:
374:
372:
368:
366:
363:
361:
358:
356:
354:
350:
348:
345:
343:
340:
338:
335:
334:
331:
326:
325:
318:
315:
313:
310:
308:
305:
303:
300:
298:
295:
293:
290:
288:
285:
283:
281:
277:
273:
272:Random forest
270:
268:
265:
263:
260:
259:
258:
255:
253:
250:
248:
245:
244:
237:
236:
231:
230:
222:
216:
215:
208:
205:
203:
200:
198:
195:
193:
190:
188:
185:
183:
180:
178:
175:
173:
170:
168:
165:
163:
160:
158:
157:Data cleaning
155:
153:
150:
148:
145:
143:
140:
138:
135:
133:
130:
128:
125:
123:
120:
119:
113:
112:
105:
102:
100:
97:
95:
92:
90:
87:
85:
82:
80:
77:
75:
72:
70:
69:Meta-learning
67:
65:
62:
60:
57:
55:
52:
50:
47:
45:
42:
41:
35:
34:
31:
26:
23:
22:
18:
17:
2102:
2091:, retrieved
2087:the original
2077:
2056:
2043:
2030:
2016:
1981:
1977:
1971:
1955:
1951:
1945:
1932:
1919:
1906:
1893:
1880:
1870:
1865:
1856:
1843:
1834:
1820:
1801:
1797:
1787:
1780:
1776:
1771:
1758:
1745:
1737:
1728:
1717:the original
1686:
1680:
1667:
1654:
1623:. Retrieved
1616:the original
1607:
1578:
1574:
1570:
1557:
1370:
1302:
1299:Applications
1294:
1270:
1251:
1243:
1240:
1235:
1231:
1229:
1224:
1219:
1215:
1213:
1207:Learning of
1194:
1178:
1157:
1150:
1129:
1116:
1085:
1064:
1052:
1040:
1022:
1013:
993:
986:
969:
965:
953:
949:
948:
816:PAC learning
503:
352:
347:Hierarchical
279:
233:
227:
196:
1940:Edbt. 2015.
1376:compression
1225:descriptive
1141:verb phrase
1137:noun phrase
971:productions
700:Multi-agent
637:Transformer
536:Autoencoder
292:Naive Bayes
30:data mining
2122:Categories
2093:2016-09-04
1625:2017-08-16
1589:References
1100:Algorithms
685:Q-learning
583:Restricted
381:Mean shift
330:Clustering
307:Perceptron
235:regression
137:Clustering
132:Regression
2148:Inference
2069:302483145
1827:A. Steger
1804:: 46–62.
1691:CiteSeerX
1581:may occur
1410:⋯
1261:formalism
1151:Like all
1124:functions
1108:John Koza
1029:Fu (1982)
1025:Fu (1977)
844:ECML PKDD
826:VC theory
773:ROC curve
705:Self-play
625:DeepDream
466:Bayes net
257:Ensembles
38:Paradigms
2065:ProQuest
2061:Stanford
2022:New York
1713:11873053
1507:See also
1173:Sequitur
267:Boosting
116:Problems
2143:Grammar
2008:Sources
1998:6900082
1649:, 2011.
1216:pattern
849:NeurIPS
666:(ECRAM)
620:AlexNet
262:Bagging
2067:
2048:Berlin
1996:
1711:
1693:
1327:, and
1158:These
642:Vision
498:RANSAC
376:OPTICS
371:DBSCAN
355:-means
162:AutoML
2107:(PDF)
1994:S2CID
1853:(PDF)
1720:(PDF)
1709:S2CID
1677:(PDF)
1619:(PDF)
1612:(PDF)
1549:Notes
1139:or a
864:IJCAI
690:SARSA
649:Mamba
615:LeNet
610:U-Net
436:t-SNE
360:Fuzzy
337:BIRCH
1365:gzip
1199:and
1119:Lisp
1112:EBNF
1027:and
952:(or
874:JMLR
859:ICLR
854:ICML
740:RLHF
556:LSTM
342:CURE
28:and
1986:doi
1960:doi
1806:doi
1736:",
1701:doi
968:or
600:SOM
590:GAN
566:ESN
561:GRU
506:-NN
441:SDL
431:PGD
426:PCA
421:NMF
416:LDA
411:ICA
406:CCA
282:-NN
2124::
2046:,
2033:,
1992:,
1982:51
1980:,
1956:46
1954:,
1855:.
1802:21
1800:.
1796:.
1707:.
1699:.
1687:75
1685:.
1679:.
1634:^
1597:^
1331:.
1323:,
1319:,
1315:,
1311:,
1057:.
1031:.
1002:,
869:ML
1988::
1962::
1814:.
1808::
1703::
1628:.
1579:y
1575:x
1565:.
1502:.
1486:G
1460:G
1440:x
1418:n
1414:x
1405:1
1401:x
1397:=
1394:x
1344:.
1236:x
1232:x
938:e
931:t
924:v
504:k
353:k
280:k
238:)
226:(
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.