A Tour of Robust Learning

Bārzdiņs conjectured that only recursively enumerable classes of functions can be learned robustly. This conjecture, which was finally refuted by Fulk, initiated the study of notions of robust learning. The present work surveys research on robust learning and focuses on the recently introduced variants of uniformly robust and hyperrobust learning. Proofs are included for the (already known) results that uniformly robust Ex-learning is more restrictive than robust Ex-learning, that uniformly robustly Ex-learnable classes are consistently learnable, that hyperrobustly Ex-learnable classes are in Num and that some hyperrobustly BC-learnable class is not in Num.

[1]  John Case,et al.  Learning Recursive Functions from Approximations , 1995, J. Comput. Syst. Sci..

[2]  Klaus P. Jantke,et al.  Combining Postulates of Naturalness in Inductive Inference , 1981, J. Inf. Process. Cybern..

[3]  Robert H. Sloan,et al.  BOOK REVIEW: "SYSTEMS THAT LEARN: AN INTRODUCTION TO LEARNING THEORY, SECOND EDITION", SANJAY JAIN, DANIEL OSHERSON, JAMES S. ROYER and ARUN SHARMA , 2001 .

[4]  Carl H. Smith,et al.  The Power of Pluralism for Automatic Program Synthesis , 1982, JACM.

[5]  John Case,et al.  Robust learning aided by context , 1998, COLT' 98.

[6]  Thomas Zeugmann,et al.  On the Nonboundability of total Effective Operators , 1984, Math. Log. Q..

[7]  Sanjay Jain.  Robust Behaviourally Correct Learning , 1998 .

[8]  Manuel Blum,et al.  Toward a Mathematical Theory of Inductive Inference , 1975, Inf. Control..

[9]  Eliana Minicozzi,et al.  Some Natural Properties of Strong-Identification in Inductive Inference , 1976, Theor. Comput. Sci..

[10]  Karlis Podnieks.  Comparing various concepts of function prediction. Part 1. , 1974 .

[11]  Leonard Pitt,et al.  Probabilistic inductive inference , 1989, JACM.

[12]  Sanjay Jain.  Robust Behaviorally Correct Learning , 1999, Inf. Comput..

[13]  Frank Stephan,et al.  Trees and learning , 2004, J. Comput. Syst. Sci..

[14]  Thomas Zeugmann.  On Barzdin's Conjecture , 1986, AII.

[15]  John Case,et al.  Robust learning--rich and poor , 2004, J. Comput. Syst. Sci..

[16]  Rolf Wiehagen,et al.  Identification of Formal Languages , 1977, MFCS.

[17]  John Case,et al.  Comparison of Identification Criteria for Machine Inductive Inference , 1983, Theor. Comput. Sci..

[18]  Frank Stephan,et al.  Avoiding coding tricks by hyperrobust learning , 2002, Theor. Comput. Sci..

[19]  Mark A. Fulk.  Robust separations in inductive inference , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[20]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[21]  Jerome A. Feldman,et al.  Some Decidability Results on Grammatical Inference and Complexity , 1972, Inf. Control..

[22]  Carl H. Smith,et al.  Robust Learning Is Rich , 2001, J. Comput. Syst. Sci..

[23]  Carl H. Smith,et al.  Probability and Plurality for Aggregations of Learning Machines , 1987, Inf. Comput..

[24]  Daniel N. Osherson,et al.  Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists , 1990 .

[25]  Frank Stephan,et al.  On the Uniform Learnability of Approximations to Non-Recursive Functions , 1999, ALT.

[26]  Rolf Wiehagen,et al.  Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen , 1976, J. Inf. Process. Cybern..