A brief review on multi-task learning

KH Thung, CY Wee - Multimedia Tools and Applications, 2018 - Springer
Abstract Multi-task learning (MTL), which optimizes multiple related learning tasks at the
same time, has been widely used in various applications, including natural language …

Transfer learning for wireless networks: A comprehensive survey

CT Nguyen, N Van Huynh, NH Chu… - Proceedings of the …, 2022 - ieeexplore.ieee.org
With outstanding features, machine learning (ML) has become the backbone of numerous
applications in wireless networks. However, the conventional ML approaches face many …

[PDF][PDF] 迁移学习研究进展

庄福振, 罗平, 何清, 史忠植 - 软件学报, 2014 - jos.org.cn
近年来, 迁移学习已经引起了广泛的关注和研究. 迁移学习是运用已存有的知识对不同但相关
领域问题进行求解的一种新的机器学习方法. 它放宽了传统机器学习中的两个基本假设:(1) …

A survey on multi-task learning

Y Zhang, Q Yang - IEEE transactions on knowledge and data …, 2021 - ieeexplore.ieee.org
Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to
leverage useful information contained in multiple related tasks to help improve the …

A survey on transfer learning

SJ Pan, Q Yang - IEEE Transactions on knowledge and data …, 2009 - ieeexplore.ieee.org
A major assumption in many machine learning and data mining algorithms is that the
training and future data must be in the same feature space and have the same distribution …

Hyperspectral classification based on lightweight 3-D-CNN with transfer learning

H Zhang, Y Li, Y Jiang, P Wang… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL)
models have been proposed and shown promising performance. However, because of very …

[PDF][PDF] Algorithms for learning kernels based on centered alignment

C Cortes, M Mohri, A Rostamizadeh - The Journal of Machine Learning …, 2012 - jmlr.org
This paper presents new and effective algorithms for learning kernels. In particular, as
shown by our empirical results, these algorithms consistently outperform the so-called …

Multi-task feature learning

A Argyriou, T Evgeniou, M Pontil - Advances in neural …, 2006 - proceedings.neurips.cc
We present a method for learning a low-dimensional representation which is shared across
a set of multiple related tasks. The method builds upon the wellknown 1-norm regularization …

Convex multi-task feature learning

A Argyriou, T Evgeniou, M Pontil - Machine learning, 2008 - Springer
We present a method for learning sparse representations shared across multiple tasks. This
method is a generalization of the well-known single-task 1-norm regularization. It is based …

Covariant quantum kernels for data with group structure

JR Glick, TP Gujarati, AD Corcoles, Y Kim, A Kandala… - Nature Physics, 2024 - nature.com
The use of kernel functions is a common technique to extract important features from
datasets. A quantum computer can be used to estimate kernel entries as transition …