Recently, rich subclasses of elementary formal systems (EFS) have been shown to be identifiable in the limit from only positive data. Examples of these classes are Angluin’s pattern languages, unions of pattern languages by Wright and Shinohara, and classes of languages definable by length-bounded elementary formal systems studied by Shinohara. The present paper employs two distinct bodies of abstract studies in the inductive inference literature to analyze the learnability of these concrete classes. The first approach, introduced by Freivalds and Smith, uses constructive ordinals to bound the number of mind changes. ω denotes the first limit ordinal. An ordinal mind change bound of ω means that identification can be carried out by a learner that after examining some element(s) of the language announces an upper bound on the number of mind changes it will make before converging; a bound of ω · 2 means that the learner reserves the right to revise this upper bound once; a bound of ω · 3 means the learner reserves the right to revise this upper bound twice, and so on. A bound of ω 2 means that identification can be carried out by a learner that announces an upper bound on the number of times it may revise its conjectured upper bound on the number of mind changes. It is shown in the present paper that the ordinal mind change complexity for identification of languages formed by unions of up to n pattern languages is ω n. It is

In this paper, we reconsider the denition of procrastinating learning machines. In the original denition of Freivalds and Smith [FS93], constructive ordinals are used to bound mindchanges. We investigate possibility of using arbitrary linearly ordered sets to bound mindchanges in similar way. It turns out that using certain ordered sets it is possible to dene inductive inference types dierent from the previously known ones. We investigate properties of the new inductive inference types and compare them to other types. This research was supported by Latvian Science Council Grant No.93.599 and NSF Grant 9421640. Some of the results from this paper were presented earlier [AFS96]. y The third author was supported in part by NSF Grant 9301339. 1 Introduction We study inductive inference using the model developed by Gold [Gol67]. There is a well known hierarchy of larger and larger classes of learnable sets of phenomena based on the number of time a learning machine is all...

The set of minimal indices of a G#del numbering ' is deøned as MIN' = fe : (8i ! e)[' i 6= 'e ]g. It has been known since 1972 that MIN' jT ; 00 , but beyond this MIN' has remained mostly uninvestigated. This thesis collects the scarce results on MIN' from the literature and adds some new observations including that MIN' is autoreducible, but neither regressive nor (1; 2)- computable. We also study several variants of MIN' that have been deøned in the literature like size-minimal indices, shortest descriptions, and minimal indices of decision tables. Some challenging open problems are left for the adventurous reader. 1 Introduction How long is the shortest program that solves your problem? There are at least two ways to interpret this question depending on the type of problem involved. If the program's task is to output one speciøc object, we are looking for a shortest description of that object. This interpretation is closely related to Kolmogorov complexity. Although we have sev...

This paper provides a beginning study of the effects on inductive inference of paradigm shifts whose absence is approximately modeled by various formal approaches to forbidding large changes in the size of programs conjectured. One approach, called severely parsimonious, requires all the programs conjectured on the way to success to be nearly (i.e., within a recursive function of) minimal size. It is shown that this very conservative constraint allows learning infinite classes of functions, but not infinite r.e. classes of functions. Another approach, called non-revolutionary, requires all conjectures to be nearly the same size as one another. This quite conservative constraint is, nonetheless, shown to permit learning some infinite r.e. classes of functions. Allowing up to one extra bounded size mind change towards a final program learned certainly doesn’t appear revolutionary. However, somewhat surprisingly for scientific (inductive) inference, it is shown that there are classes learnable with the non-revolutionary constraint (respectively, with severe parsimony), up to (i + 1) mind changes, and no anomalies, which classes cannot be learned with no size constraint, an unbounded, finite number of anomalies in the final program, but with no more than i mind changes. Hence, in some cases, the possibility of one extra mind change is considerably more liberating than removal of very conservative size shift constraints. The proofs of these results are also combinatorially interesting. 1

Freivalds defined an acceptable programming system independent criterion for learning programs for functions in which the final programs were required to be both correct and "nearly" minimal size, i.e, within a computable function of being purely minimal size. Kinber showed that this parsimony requirement on final programs limits learning power. However, in scientific inference, parsimony is considered highly desirable. A lim-computable function is (by definition) one calculable by a total procedure allowed to change its mind finitely many times about its output. Investigated is the possibility of assuaging somewhat the limitation on learning power resulting from requiring parsimonious final programs by use of criteria which require the final, correct programs to be "not-so-nearly" minimal size, e.g., to be within a lim-computable function of actual minimal size. It is shown that some parsimony in the final program is thereby retained, yet learning power strictly increases. Considered, then, are lim-computable functions as above but for which notations for constructive ordinals are used to bound the number of mind changes allowed regarding the output. This is a variant of an idea introduced by Freivalds and Smith. For this ordinal notation complexity bounded version of lim-computability, the power of the resultant learning criteria form finely graded, infinitely ramifying, infinite hierarchies intermediate between the computable and the lim-computable cases. Some of these hierarchies, for the natural notations determining them, are shown to be optimally tight.

This paper proposes the use of constructive ordinals as mistake bounds in the on-line learning model. This approach elegantly generalizes the applicability of the on-line mistake bound model to learnability analysis of very expressive concept classes like pattern languages, unions of pattern languages, elementary formal systems, and minimal models of logic programs. The main result in the paper shows that the topological property of effective finite bounded thickness is a sufficient condition for on-line learnability with a certain ordinal mistake bound. An interesting characterization of the on-line learning model is shown in terms of the identification in the limit framework. It is established that the classes of languages learnable in the on-line model with a mistake bound of α are exactly the same as the classes of languages learnable in the limit from both positive and negative data by a Popperian, consistent learner with a mind change bound of α. This result nicely builds a bridge between the two models. 1