Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/141249
Title: LANGUAGE LEARNING OF INDUCTIVE INFERENCE MACHINES WITH MEMORY LIMITATION
Authors: MA JUNQI
Keywords: inductive inference, machine learning, memory limitation, language learning
Issue Date: 4-Aug-2017
Citation: MA JUNQI (2017-08-04). LANGUAGE LEARNING OF INDUCTIVE INFERENCE MACHINES WITH MEMORY LIMITATION. ScholarBank@NUS Repository.
Abstract: Inductive inference is a machine learning model inspired by learning activities in real life, in which the learner keeps accepting inputs from the environment while giving conjectures about the learning target continuously without knowing whether the conjectures are correct. Such learning process is successful if the conjectures made by the learner converge to the correct learning target. This thesis investigates the properties of inductive inference with memory limitation in two topics. The first topic introduces priced learning, an inductive inference model implicitly constrains the memory usage by adding a cost on each memory update based on a given price function, while requiring a successful priced learner not take infinite cost during the whole learning process. The learning capacity of priced learning is proved between iterative learning and set-driven learning. The second topic reviews some variants of iterative learning model, showing that the decisiveness is unrestrictive under the iterative learning framework.
URI: http://scholarbank.nus.edu.sg/handle/10635/141249
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
MaJQ.pdf569.85 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

16
checked on Aug 16, 2018

Download(s)

5
checked on Aug 16, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.