Zulu: An Interactive Learning Competition
نویسندگان
چکیده
Active language learning is an interesting task for which theoretical results are known and several applications exist. In order to better understand what the better strategies may be, a new competition called Zulu (http://labh-curien.univ-st-etienne.fr/zulu/) is launched: participants are invited to learn deterministic finite automata from membership queries. The goal is to obtain the best classification rate from a fixed number of queries.
منابع مشابه
Implementing Kearns-Vazirani Algorithm for Learning DFA Only with Membership Queries
Two algorithms for learning dfa with membership queries are described. Both of them are based on Kearns and Vazirani’s version of Angluin’s L∗. Our algorithms tied in the third place in the Zulu competition.
متن کاملFrom ZULU to RERS - Lessons Learned in the ZULU Challenge
This paper summarizes our experience with the ZULU challenge on active learning without equivalence queries, presents our winning solution, investigates the character of ZULU’s rating approach, and discusses how this approach can be taken further to establish a framework for the systematic investigation of domain-specific, scalable learning solutions for practically relevant application. In par...
متن کاملA standard Interactive Multimedia eBook Generator Engine for e-Learning Process
Introduction: Using standard authoring tools is essential to promote E-Learning in teaching-learning process. Learning content in medical sciences often consists of multimedia elements. On the other hand, it is frequently required to revise and update the medical content. Hence, access to the authoring tools that can encompass multimedia elements and allow easy content revision is helpful in e-...
متن کاملInteractive Learning and Students’ Competences in Teaching Literature
Studies have shown that in everyday school activities the predominating forms of learning are characterized by individualism and competition. Such atmosphere of individualism and competition can hardly have a positive influence on the development and stimulation of students’ competence in teaching literature. The focus of interactive learning is not only on cognitive competences, which the trad...
متن کاملContrastive Hebbian Learning in the Continuous Hopfield Model
This pape.r shows that contrastive Hebbian, the algorithm used in mean field learning, can be applied to any continuous Hopfield model. This implies that non-logistic activation functions as well as self connections are allowed. Contrary to previous approaches, the learning algorithm is derived without considering it a mean field approximation to Boltzmann machine learning. The paper includes a...
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 2009