Assisting Main Task Learning by Heterogeneous Auxiliary Tasks with Applications to Skin Cancer Screening
نویسندگان
چکیده
In typical classification problems, high level concept features provided by a domain expert are usually available during classifier training but not during its deployment. We address this problem from a multitask learning (MTL) perspective by treating these features as auxiliary learning tasks. Previous efforts in MTL have mostly assumed that all tasks have the same input space. However, auxiliary tasks can have different input spaces, since their learning targets are different. Thus, to handle cases with heterogeneous input, in this paper we present a newly developed model using heterogeneous auxiliary tasks to help main task learning. First, we formulate a convex optimization problem for the proposed model, and then, we analyze its hypothesis class and derive true risk bounds. Finally, we compare the proposed model with other relevant methods when applied to the problem of skin cancer screening and public datasets. Our results show that the performance of the proposed method is highly competitive compared to other relevant methods.
منابع مشابه
L2 Vocabulary Learning and the Use of Reading Tasks: Manipulating the Involvement Load Index
As Schmidt (2008) states, deeper engagement with new vocabulary as induced by tasks clearly increases the chances of learning those words. This engagement is theoretically clarified by the involvement load hypothesis (ILH, Laufer and Hulstijn, 2001), based on which the involvement index of each task can be measured. The present study was designed to test ILH by evaluating the impact of 4 differ...
متن کاملL2 Vocabulary Learning and the Use of Reading Tasks: Manipulating the Involvement Load Index
As Schmidt (2008) states, deeper engagement with new vocabulary as induced by tasks clearly increases the chances of learning those words. This engagement is theoretically clarified by the involvement load hypothesis (ILH, Laufer and Hulstijn, 2001), based on which the involvement index of each task can be measured. The present study was designed to test ILH by evaluating the impact of 4 differ...
متن کاملWill my auxiliary tagging task help? Estimating Auxiliary Tasks Effectivity in Multi-Task Learning
Multitask learning often improves system performance for morphosyntactic and semantic tagging tasks. However, the question of when and why this is the case has yet to be answered satisfactorily. Although previous work has hypothesised that this is linked to the label distributions of the auxiliary task, we argue that this is not sufficient. We show that information-theoretic measures which cons...
متن کاملAssessing Task- based English Language Needs of Medicine Students: Are They Aligned with Pedagogical Tasks in EMS Courses?
Assessing learners’ present and real life language needs can contribute to learners’ active participation in learning processes. , Assessing learners’ task-based needs and aligning them with pedagogical tasks are significant in English for medical purpose (EMS) courses. The main objectives of the present study were to assess learners’ needs and to determine whether they are practiced in EMS cou...
متن کاملAn Efficient Genetic Algorithm for Task Scheduling on Heterogeneous Computing Systems Based on TRIZ
An efficient assignment and scheduling of tasks is one of the key elements in effective utilization of heterogeneous multiprocessor systems. The task scheduling problem has been proven to be NP-hard is the reason why we used meta-heuristic methods for finding a suboptimal schedule. In this paper we proposed a new approach using TRIZ (specially 40 inventive principles). The basic idea of thi...
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:
- Journal of machine learning research : JMLR
دوره 15 شماره
صفحات -
تاریخ انتشار 2011