Journal of Symbolic Logic 69 (1):287-327 (2004)
|Abstract||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-computablefunction 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|
|Keywords||Computational learning theory minimal size program constructive ordinal notations limiting computable function|
|Categories||categorize this paper)|
|Through your library||Configure|
Similar books and articles
Michael Huemer (2009). When is Parsimony a Virtue? Philosophical Quarterly 59 (235):216-236.
Mark Changizi (1996). Function Identification From Noisy Data with Recursive Error Bounds. Erkenntnis 45 (1):91 - 102.
F. W. Kroon & W. A. Burkhard (1990). On a Complexity-Based Way of Constructivizing the Recursive Functions. Studia Logica 49 (1):133 - 149.
Alan Baker (2003). Quantitative Parsimony and Explanatory Power. British Journal for the Philosophy of Science 54 (2):245-259.
Samir Chopra & Eric Martin (2002). Generalized Logical Consequence: Making Room for Induction in the Logic of Science. [REVIEW] Journal of Philosophical Logic 31 (3):245-280.
H. E. Rose (1984). Subrecursion: Functions and Hierarchies. Oxford University Press.
Rodney G. Downey & Asher M. Kach (2010). Euclidean Functions of Computable Euclidean Domains. Notre Dame Journal of Formal Logic 52 (2):163-172.
Craig DeLancey (2011). Does a Parsimony Principle Entail a Simple World? Metaphysica 12 (2):87-100.
Sanjay Jain & Arun Sharma (1997). The Structure of Intrinsic Complexity of Learning. Journal of Symbolic Logic 62 (4):1187-1201.
Ganesh Baliga, John Case, Sanjay Jain & Mandayam Suraj (1994). Machine Learning of Higher-Order Programs. Journal of Symbolic Logic 59 (2):486-500.
Added to index2009-02-05
Total downloads3 ( #213,250 of 722,813 )
Recent downloads (6 months)0
How can I increase my downloads?