2019Seeded transfer learning for regression problems with deep learning.pdf
论文摘要:相关但不同领域的数据分布差异是知识适应的长期问题。提出了一种新的源域知识变换方法,使其与目标函数相适应。该方法利用深度学习方法和目标域有限样本对源域数据集进行变换。它将目标域的有限样本作为启动源知识转移的种子。采用不同的计算智能模型和不同的数据集进行了综合实验。结果表明,使用该方法训练的预测模型与仅使用源知识或深度学习特征训练的相同模型相比,表现出最佳的性能。实验表明,在总共18个实验中,使用所提方法训练的模型在14个实验中至少比基线方法好50%
用户评论
推荐下载
-
Python Machine Learning Machine Learning and Deep Learning
Python Machine Learning Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow
103 2018-12-25 -
Unsupervised Feature Learning and Deep Learning
机器学习经典书籍UnsupervisedFeatureLearningandDeepLearning英文
35 2019-09-03 -
MATLAB Deep Learning With Machine Learning
MATLAB Deep Learning With Machine Learning, Neural Networks and Artificial Intelligence Phil Kim ■■C
92 2018-12-21 -
Learning Deep and Wide A Spectral Method for Learning Deep Networks
提出了多光谱神经网络(MSNN)来学习多列深度神经网络的特征,并将倒数第二层次判别流形嵌入到紧凑的表示中。
22 2021-04-21 -
Deep learning deep portfolios
We explore the use of deep learning hierarchical models for problems in financial prediction and cla
75 2019-03-17 -
Semantic Autoencoder for Zero Shot Learning.pdf
零样本学习论文-
17 2020-12-17 -
A brief introduction to weakly supervised learning.pdf
Supervisedlearningtechniquesconstructpredictivemodelsbylearningfromalargenumberoftraining examples,
18 2020-05-14 -
Python Real World Machine Learning.pdf
PythonRealWorldMachineLearning.pdf
25 2020-05-23 -
matrix vector derivatives for machine learning.pdf
机器学习中的矩阵向量求导,主要包括:符号表示、导数定义、常用公式(向量求导的链式法则+实值函数对向量求导+向量数乘求导公式+矩阵迹求导+矩阵求导的链式法则+行列式和逆矩阵求导),例子。
22 2020-03-14 -
Matching Networks for One Shot Learning.pdf
Abstract:Learningfromafewexamplesremainsakeychallengeinmachinelearning.Despiterecentadvancesinimport
16 2019-09-14
暂无评论