A Transfer-Learning Approach to Exploit Noisy Information for Classification
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 101 === Generally qualitative condition (the accuracy of the data) and quantitative condition (the amount of data) of the data can significantly affect the quality of a supervised learning model. However, in real-world applications it might not be feasible to always as...
Main Authors: | Wei-Shih Lin, 林瑋詩 |
---|---|
Other Authors: | Shou-De Lin |
Format: | Others |
Language: | en_US |
Published: |
2013
|
Online Access: | http://ndltd.ncl.edu.tw/handle/28021491105145830579 |
Similar Items
-
A Framework Using Contrastive Learning for Classification with Noisy Labels
by: Madalina Ciortan, et al.
Published: (2021-06-01) -
Genetic Redundancies Enhance Information Transfer in Noisy Regulatory Circuits.
by: Guillermo Rodrigo, et al.
Published: (2016-10-01) -
NOISY IMAGE CLASSIFICATION USING HYBRID DEEP LEARNING METHODS
by: Sudipta Singha Roy, et al.
Published: (2018-02-01) - Classification techniques for noisy and imbalanced data
-
Robust Mote-Scale Classification of Noisy Data via Machine Learning
by: He, Jin
Published: (2015)