Active Learning with Confidence
نویسندگان
چکیده
Active learning is a machine learning approach to achieving high-accuracy with a small amount of labels by letting the learning algorithm choose instances to be labeled. Most of previous approaches based on discriminative learning use the margin for choosing instances. We present a method for incorporating confidence into the margin by using a newly introduced online learning algorithm and show empirically that confidence improves active learning.
منابع مشابه
Active Learning with Connections to Confidence-rated Prediction
In the problem of active learning, we are given a set of unlabelled examples and the ability to query the labels of a subset of them, in an adaptive manner. The goal is to find a classifier with a target excess error, while querying as few labels as possible. In this report, we review several existing solutions to this problem: generalized binary search, disagreement-based active learning and m...
متن کاملConfidence-based Active Learning Methods for Machine Translation
The paper presents experiments with active learning methods for the acquisition of training data in the context of machine translation. We propose a confidencebased method which is superior to the state-of-the-art method both in terms of quality and complexity. Additionally, we discovered that oracle selection techniques that use real quality scores lead to poor results, making the effectivenes...
متن کاملActive Learning for Word Sense Disambiguation with Methods for Addressing the Class Imbalance Problem
In this paper, we analyze the effect of resampling techniques, including undersampling and over-sampling used in active learning for word sense disambiguation (WSD). Experimental results show that under-sampling causes negative effects on active learning, but over-sampling is a relatively good choice. To alleviate the withinclass imbalance problem of over-sampling, we propose a bootstrap-based ...
متن کاملBeyond Disagreement-Based Agnostic Active Learning
We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The main algorithms for this problem are disagreement-based active learning, which has a high label requirement, and margin-based active learning, which only app...
متن کاملActive participation of student s in teaching
Active participation of students in teaching is the one of the effective way of learning in science education according to large investigation. By this way students understand current level of knowledge, increasing the student’s eagerness and their attraction for learning. This study was designed to explore the effect of active student involvement in teaching and learning of the bacteriology in...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008