On the role of update constraints and text-types in iterative learning

详细信息    查看全文

• 作者：Sanjay Jain^a ; ¹ ; ^{sanjay@comp.nus.edu.sg" class="auth_mail" title="E-mail the corresponding author} ; Timo Kö ; tzing^b ; ^{timo.koetzing@uni-jena.de" class="auth_mail" title="E-mail the corresponding author} ; Junqi Ma^a ; ^{ma.junqi@nus.edu.sg" class="auth_mail" title="E-mail the corresponding author} ; Frank Stephan^c ; ² ; ^{fstephan@comp.nus.edu.sg" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Inductive inference ; Iterative learning ; Learning constraints ; Decisive learning ; Conservative learning
• 刊名：Information and Computation
• 出版年：2016
• 出版时间：April 2016
• 年：2016
• 卷：247
• 期：Complete
• 页码：152-168
• 全文大小：526 K

文摘

The present work investigates the relationship of iterative learning with other learning criteria such as decisiveness, caution, reliability, non-U-shapedness, monotonicity, strong monotonicity and conservativeness. Building on the result of Case and Moelius that iterative learners can be made non-U-shaped, we show that they also can be made cautious and decisive. Furthermore, we obtain various special results with respect to one-one texts, fat texts and one-one hypothesis spaces.