Anytime Induction of Low-cost, Low-error Classifiers: a Sampling-based Approach
نویسندگان
چکیده
Machine learning techniques are gaining prevalence in the production of a wide range of classifiers for complex real-world applications with nonuniform testing and misclassification costs. The increasing complexity of these applications poses a real challenge to resource management during learning and classification. In this work we introduce ACT (anytime cost-sensitive tree learner), a novel framework for operating in such complex environments. ACT is an anytime algorithm that allows learning time to be increased in return for lower classification costs. It builds a tree top-down and exploits additional time resources to obtain better estimations for the utility of the different candidate splits. Using sampling techniques, ACT approximates the cost of the subtree under each candidate split and favors the one with a minimal cost. As a stochastic algorithm, ACT is expected to be able to escape local minima, into which greedy methods may be trapped. Experiments with a variety of datasets were conducted to compare ACT to the state-of-the-art cost-sensitive tree learners. The results show that for the majority of domains ACT produces significantly less costly trees. ACT also exhibits good anytime behavior with diminishing returns.
منابع مشابه
Anytime Induction of Cost-sensitive Trees
Machine learning techniques are increasingly being used to produce a wide-range of classifiers for complex real-world applications that involve nonuniform testing costs and misclassification costs. As the complexity of these applications grows, the management of resources during the learning and classification processes becomes a challenging task. In this work we introduce ACT (Anytime Cost-sen...
متن کاملSimulation of Store Separation using Low-cost CFD with Dynamic Meshing
The simulation of the store separation using the automatic coupling of dynamic equations with flow aerodynamics is addressed. The precision and cost (calculation time) were considered as comparators. The method used in the present research decreased the calculation cost while limiting the solution error within a specific and tolerable interval. The methods applied to model the aerodynamic force...
متن کاملA Novel Sampling Approach in GNSS-RO Receivers with Open Loop Tracking Method
Propagation of radio occultation (RO) signals through the lower troposphere results in high phase acceleration and low signal to noise ratio signal. The excess Doppler estimation accuracy in lower troposphere is very important in receiving RO signals which can be estimated by sliding window spectral analysis. To do this, various frequency estimation methods such as MUSIC and ESPRIT can be adopt...
متن کاملA FUZZY-BASED SPEED CONTROLLER FOR IMPROVEMENT OF INDUCTION MOTOR'S DRIVE PERFORMANCE
Induction motors (IMs) are widely used in many industrial applications due to their robustness, low cost, simplicity and relative good efficiency. One of the major considerations for IMs is their speed control. PI (proportional-integrator) controllers are usually used as speed controller. Adjusting the gain of PI controller is time-consuming which needs thorough considerations. Hence, fuzzy con...
متن کاملReversible Logic Multipliers: Novel Low-cost Parity-Preserving Designs
Reversible logic is one of the new paradigms for power optimization that can be used instead of the current circuits. Moreover, the fault-tolerance capability in the form of error detection or error correction is a vital aspect for current processing systems. In this paper, as the multiplication is an important operation in computing systems, some novel reversible multiplier designs are propose...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- J. Artif. Intell. Res.
دوره 33 شماره
صفحات -
تاریخ انتشار 2008