Online transfer learning by leveraging multiple source domains

Wu, Qingyao; Zhou, Xiaoming; Yan, Yuguang; Wu, Hanrui; Min, Huaqing

doi:10.1007/s10115-016-1021-1

Cited by 47 publications

(32 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in real-world applications, we can easily collect auxiliary data from multiple source domains. Therefore, the studies of multi-source domains transfer learning have gradually attracted the interest of researchers [13,14,15,16,17,18,19,20,21,22,23,24,25]. It can transfer knowledge from multiple source domains to learning tasks of the target domain compared to previous transfer learning algorithms with single domains [26].…”

Section: Related Workmentioning

confidence: 99%

“…Recently, machine learning algorithms of transfer learning with multi-source domains have been proposed. Yao et al [22] extended the boosting framework and proposed MultiSource-TrAdaBoost and TaskTrBoost; Sun et al [23] proposed a two-stage domain adaptive method that combines weights of data on marginal probability differences (first phase) and conditional probability differences (second phase) from multiple source and target domains; Duan et al [24] proposed a multi-source domains adaptation method DAM; [25] proposed a new online transfer learning algorithm by using labeling data from multiple source domains to seek to improve classification performance in target domain; Ding et al [26] attempted to use the incomplete multi-source domains to carry out effective knowledge transfer, and proposed an incomplete multi-source transfer learning to improve knowledge transfer in two directions; In [27], Jun et al explored two problems of domain adaptation and proposed the A-SVM algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Source Deep Transfer Neural Network Algorithm

Xue

et al. 2019

Sensors

View full text Add to dashboard Cite

Transfer learning can enhance classification performance of a target domain with insufficient training data by utilizing knowledge relating to the target domain from source domain. Nowadays, it is common to see two or more source domains available for knowledge transfer, which can improve performance of learning tasks in the target domain. However, the classification performance of the target domain decreases due to mismatching of probability distribution. Recent studies have shown that deep learning can build deep structures by extracting more effective features to resist the mismatching. In this paper, we propose a new multi-source deep transfer neural network algorithm, MultiDTNN, based on convolutional neural network and multi-source transfer learning. In MultiDTNN, joint probability distribution adaptation (JPDA) is used for reducing the mismatching between source and target domains to enhance features transferability of the source domain in deep neural networks. Then, the convolutional neural network is trained by utilizing the datasets of each source and target domain to obtain a set of classifiers. Finally, the designed selection strategy selects classifier with the smallest classification error on the target domain from the set to assemble the MultiDTNN framework. The effectiveness of the proposed MultiDTNN is verified by comparing it with other state-of-the-art deep transfer learning on three datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-Source Deep Transfer Neural Network Algorithm

Xue

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…The first study of online transfer learning based on multi-source domains is literature [Ge, Gao and Zhang (2013)]. After that, Wu et al [Wu, Zhou, Yan et al (2017)] also proposed a method of transfer learning in multiple source domains, which adjust transferred weight of each source domain to obtain an ensemble classifier. Wu et al ] also introduced multiple sources which are homogeneous or heterogeneous.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis Method based on Kmeans and Online Transfer Learning

Wu¹,

Liu²,

Wang³

et al. 2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Sentiment analysis is a research hot spot in the field of natural language processing and content security. Traditional methods are often difficult to handle the problems of large difference in sample distribution and the data in the target domain is transmitted in a streaming fashion. This paper proposes a sentiment analysis method based on Kmeans and online transfer learning in the view of fact that most existing sentiment analysis methods are based on transfer learning and offline transfer learning. We first use the Kmeans clustering algorithm to process data from one or multiple source domains and select the data similar to target domain data to establish the classifier, so that the processed data does not negatively transfer the data in the target domain. And then create a new classifier based on the new target domain. The source domain classifier and target domain classifier are combined with certain weights by using the homogeneous online transfer learning method to achieve sentiment analysis. The experimental results show that this method has achieved better performance in terms of error rate and classification accuracy.

show abstract

“…To tackle with this problem, the robot can reuse its previously obtained prior knowledge when it learns new objects with fewer training samples or even one (tactile transfer learning). Although there are many research studies proposing various transfer learning strategies in visual categorization, [38][39][40][41][42][43][44][45][46][47] reinforcement learning, 48 data mining, [49][50][51] brain computer interface, 52 and deep learning, 53 to the best of our knowledge, in the tactile learning domain, it is only our previous work which proposed a tactile transfer learning method for object texture discrimination (Kaboli et al 55,56 ). In our previous work, a robotic hands re-used its learned texture models from the prior objects to discriminate among new in-hand objects via their textural properties with a few training samples or even one.…”

Section: Related Workmentioning

confidence: 99%

Active Tactile Transfer Learning for Object Discrimination in an Unstructured Environment Using Multimodal Robotic Skin

Kaboli

Feng

Cheng

2018

Int. J. Human. Robot.

View full text Add to dashboard Cite

In this paper, we propose a probabilistic active tactile transfer learning (ATTL) method to enable robotic systems to exploit their prior tactile knowledge while discriminating among objects via their physical properties (surface texture, stiffness, and thermal conductivity). Using the proposed method, the robot autonomously selects and exploits its most relevant prior tactile knowledge to efficiently learn about new unknown objects with a few training samples or even one. The experimental results show that using our proposed method, the robot successfully discriminated among new objects with [Formula: see text] discrimination accuracy using only one training sample (on-shot-tactile-learning). Furthermore, the results demonstrate that our method is robust against transferring irrelevant prior tactile knowledge (negative tactile knowledge transfer).

show abstract

Online transfer learning by leveraging multiple source domains

Cited by 47 publications

References 20 publications

Multi-Source Deep Transfer Neural Network Algorithm

Multi-Source Deep Transfer Neural Network Algorithm

Sentiment Analysis Method based on Kmeans and Online Transfer Learning

Active Tactile Transfer Learning for Object Discrimination in an Unstructured Environment Using Multimodal Robotic Skin

Contact Info

Product

Resources

About