Transfer learning using computational intelligence
read more
Citations
A Comprehensive Survey on Transfer Learning
Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks
Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks.
A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis
Deep Model Based Domain Adaptation for Fault Diagnosis
References
Fuzzy sets
Sample Selection Bias as a Specification Error
A Survey on Transfer Learning
Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
Machine learning in automated text categorization
Related Papers (5)
Frequently Asked Questions (20)
Q2. What are the two phases of learning a Bayesian network from data?
To learn a Bayesian network from data, one needs to consider two important phases: structure learning and parameter learning, respectively.
Q3. What is the main purpose of the self-training method?
Self-training methods have been applied to domain adaptation on Natural Language Processing (NLP) tasks including parsing [18-21]; part-of-speech tagging [22]; conversation summarization [23]; entity recognition [22, 24, 25]; sentiment classification [26]; spam detection [22]; cross-language document classification [27, 28]; and speech act classification [29].
Q4. What are the main reasons why researchers take fuzzy systems into account for transfer learning more and more?
Since many real world applications have noisy and uncertainty in data, researchers take fuzzy systems into account for transfer learning more and more.
Q5. What are the main applications of transfer learning?
Transfer learning approaches with the support of computational intelligence methods such as neural network, Bayesian network, and fuzzy logic have been applied in real-world applications.
Q6. What is the fundamental motivation for transfer learning in the field of machine learning?
The fundamental motivation for transfer learning in the field of machine learning focuses on the need for lifelong machine learning methods that retain and reuse previously learned knowledge.
Q7. What is the main limitation of multi-task network structure learning algorithms?
The main limitation of such multi-task network structure learning algorithms lies in the assumption that all pairs of tasks are equally related, which violates the truth that different pairs of tasks can differ in their degree of relatedness.
Q8. What is the main purpose of transfer learning?
Research on transfer learning has been undertaken since 1995 under a variety of names: learning to learn; life-long learning; knowledge transfer; meta learning; inductive transfer; knowledge consolidation; context sensitive learning and multi-task learning [9].
Q9. What is the advantage of fuzzy logic in knowledge transfer?
Using fuzzy techniques in similarity measurement and label production, the authors revealed the advantage of fuzzy logic in knowledge transfer where the target domain lacks critical information and involves uncertainty and vagueness.
Q10. How did Zou et al. achieve this?
By applying salient feature detection and tracking in videos to simulate fixations and smooth pursuit in human vision, Zou et al. [102] successfully implemented an unsupervised learning algorithm in a self-taught learning setting.
Q11. What are the main reasons why neural network has been widely used for transfer learning?
Of the computational intelligence methods, neural network has been extensively used for transfer learning, mainly in computer vision and image processing domain.
Q12. What is the purpose of transfer learning?
Transfer learning has emerged in the computer science literature as a means of transferring knowledge from a source domain to a target domain.
Q13. What is the main reason why neural network has been widely used in transfer learning?
The main reason why neural network has been widely used in transfer learning is that it doesn’t have I.I.D. assumption on data while almost all stochastic techniques have.
Q14. What is the main difference between fuzzy logic and classical transductive transfer learning?
The two primary elements within fuzzy logic, the linguistic variable and the fuzzy if-then rule, are able to mimic the human ability to capture imprecision and uncertainty within knowledge transfer.
Q15. What is the main reason why the research paper is a summary of transfer learning?
From the summary of transfer learning, it is concluded that transfer learning with the use computational intelligence, as an emerging research topic, starts playing an important role in almost all kinds of application.
Q16. What is the problem in the representation learning camp for images?
Chopra et al. [51] argued that in the representation learning camp for images, existing deep learning approaches could not encode the distributional shift between the source and target domains.
Q17. What is the cost of retraining a prediction model?
As a result, once the feature space or the feature distribution of the test data changes, the prediction models cannot be used and must be rebuilt and retrained from scratch using newly-collected training data, which is very expensive and sometimes not practically possible.
Q18. What is the problem of reusing English lowercase digits?
Authors [50] also considered a problem of classifying images of English lowercase a-to-z by reusing fine-tuned features of English handwritten digits 0-to-9.
Q19. How did they extend a previously constructed algorithm?
Koçer and Arslan [97] introduced the use of genetic algorithm and transfer learning by extending a previously constructed algorithm.
Q20. What is the main reason for the lack of labeled training data?
since learning-based models need adequate labeled data for training, it is nearly impossible to establish a learning-based model for a target domain which has very few labeled data available for supervised learning.