T. HANCOCK, Identifying -formula decision trees with queries, in Proc. of the Third Annual Workshop on Computational Learning Theory, ACM, New York, 1990, pp. 23--37. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Decision Trees have Approximate Fingerprints - Lavin, Raghavan (1997) (Correct)
....class has polynomial certificates. Decision trees are a popular representation of boolean functions, which form the basic inference engine used in many machine learning programs. The learnability of decision trees has been well studied in the learning theory community. For example, it is known [Han90] that decision trees are exactly learnable with equivalence and membership queries, but neither type of query alone suffices for polynomial learning. Bshouty [Bsh95] has shown that general decision trees are learnable with extended equivalence queries (the hypotheses used are depth three ....
T. Hancock. Identifying -Formula Decision Trees with Queries. Proceedings of the Third Annual Workshop on Computational Learning Theory, pages 23--37, 1990.
Randomly Fallible Teachers: Learning Monotone DNF with an.. - Angluin, al. (1994) (17 citations) (Correct)
....problems known to have polynomial time algorithms using equivalence and membership oracles. For example, deterministic finite state acceptors (Angluin, 1987) simple deterministic languages (Ishizaka, 1990) read once formulas (Angluin, Hellerstein, and Karpinski, 1993) formula decision trees (Hancock, 1990), switch configurations (Raghavan and Schach, 1990) and propositional Horn sentences (Angluin, Frazier, and Pitt, 1992) all have such algorithms. Of these, the problem of propositional Horn sentences is the closest to the case of monotone DNF, but the basic algorithms are quite different. ....
Hancock, T. (1990). Identifying -formula decision trees with queries. In Proceedings of the Third Annual Workshop on Computational Learning Theory, (pp. 23-37). Rochester, NY: Morgan Kaufmann.
Computational Complexity of Learning Read-Once Formulas.. - Hellerstein, Karpinski (1991) (1 citation) (Correct)
....this gives a polynomial time learning algorithm for arbitrary read once formulas over a threshold basis with negation using membership and equivalence queries. Furthermore we study the structural notion of nondegeneracy in the threshold formulas generalizing the result of [Heiman, Newman, Wigderson, 1990] on the uniqueness of read once formulas over different boolean bases and derive a negative result on learnability of nondegenerate read once formulas over the basis (AND, XOR) 1 Supported by a grant from the Siemens Corporation and ONR grant N00014 85 K 0445. A portion of this research was ....
....AND gates on a root leaf path, or two adjacent OR gates on root leaf path. We generalize this uniqueness result to apply to classes of read once formulas over boolean bases B satisfying the following four properties: 3 A similar result has been also obtained independently by T. R. Hancock, cf. H 90] 2 1. B is a symmetric basis (i.e. each gate of B computes a symmetric function) 2. if f is a function computed by a gate in B, then f (the complement of f) is not a monotone function. 3. if f is a function computed by a gate in B, then B does not contain a gate computing f . 4. f does ....
T. R. Hancock, Identifying -Formula Decision Trees with Queries, Technical Report TR-16-90, Aiken Computation Laboratory, Harvard University, 1990.
Decision Trees have Approximate Fingerprints - Lavin, Raghavan (1996) (Correct)
....class has polynomial certificates. Decision trees are a popular representation of boolean functions, which form the basic inference engine used in many machine learning programs. The learnability of decision trees has been well studied in the learning theory community. For example, it is known [Han90] that decision trees are exactly learnable with equivalence and membership queries, but neither type of query alone suffices for polynomial learning. Bshouty [Bsh95] has shown that general decision trees are learnable with extended equivalence queries (the hypotheses used are depth three ....
T. Hancock. Identifying -Formula Decision Trees with Queries. Proceedings of the Third Annual Workshop on Computational Learning Theory, pages 23--37, 1990.
Interpolating Arithmetic Read-Once Formulas - In Parallel Nader (Correct)
No context found.
T. HANCOCK, Identifying -formula decision trees with queries, in Proc. of the Third Annual Workshop on Computational Learning Theory, ACM, New York, 1990, pp. 23--37.
Interpolating Arithmetic Read-Once Formulas - In Parallel Nader (Correct)
No context found.
T. Hancock. Identifying -formula decision trees with queries. In The 1990 Workshop on Computational Learning Theory, pages 23--37, 1990.
How Many Queries are Needed to Learn? - Lisa Hellerstein Eecs (1996) (2 citations) (Correct)
No context found.
T. Hancock. Identifying -Formula Decision Trees with Queries. Proceedings of the Third Annual Workshop on Computational Learning Theory, pages 23--37, 1990.
Interpolating Arithmetic Read-Once Formulas in Parallel - Bshouty, Cleve (Correct)
No context found.
T. Hancock. Identifying -formula decision trees with queries. In The 1990 Workshop on Computational Learning Theory, pages 23--37, 1990.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC