A Tighter Error Bound for Decision Tree Learning Using PAC Learnability
نویسندگان
چکیده
Error bounds for decision trees are generally based on depth or breadth of the tree. In this paper, we propose a bound for error rate that depends both on the depth and the breadth of a specific decision tree constructed from the training samples. This bound is derived from sample complexity estimate based on PAC learnability. The proposed bound is compared with other traditional error bounds on several machine learning benchmark data sets as well as on an image data set used in Content Based Image Retrieval (CBIR). Experimental results demonstrate that the proposed bound gives tighter estimation of the empirical error.
منابع مشابه
Quantum DNF Learnability Revisited
We describe a quantum PAC learning algorithm for DNF formulae under the uniform distribution with a query complexity of Õ(s/ǫ+ s/ǫ), where s is the size of DNF formula and ǫ is the PAC error accuracy. If s and 1/ǫ are comparable, this gives a modest improvement over a previously known classical query complexity of Õ(ns/ǫ). We also show a lower bound of Ω(s logn/n) on the query complexity of any...
متن کاملua nt - p h / 02 02 06 6 v 1 1 2 Fe b 20 02 Quantum DNF Learnability Revisited
We describe a quantum PAC learning algorithm for DNF formulae under the uniform distribution with a query complexity of Õ(s/ǫ+ s/ǫ), where s is the size of DNF formula and ǫ is the PAC error accuracy. If s and 1/ǫ are comparable, this gives a modest improvement over a previously known classical query complexity of Õ(ns/ǫ). We also show a lower bound of Ω(s logn/n) on the query complexity of any...
متن کاملA Learnability Model for Universal Representations and Its Application to Top-down Induction of Decision Trees
Automated inductive learning is a vital part of machine intelligence and the design of intelligent agents. A useful formalization of inductive learning is the model of PAC-learnability. Nevertheless, the ability to learn every target concept expressible in a given representation, as required in the PAC-learnability model, is highly demanding and leads to many negative results for interesting co...
متن کاملPAC-learnability of Probabilistic Deterministic Finite State Automata
We study the learnability of Probabilistic Deterministic Finite State Automata under a modified PAC-learning criterion. We argue that it is necessary to add additional parameters to the sample complexity polynomial, namely a bound on the expected length of strings generated from any state, and a bound on the distinguishability between states. With this, we demonstrate that the class of PDFAs is...
متن کاملLearning Decision Lists over Tree Patterns and Its Application
This paper introduces a new concept, a decision tree (or list) over tree patterns, which is a natural extension of a decision tree (or decision list), for dealing with tree structured objects. The learnability of this class is studied within the framework of the Probably Approximately Correct learning model and the Identi cation in the Limit model. It is found that the class k-node-DLRTP, a sub...
متن کامل