Transfer learning in genetic programming

Dinh, Thi Thu Huong; Chu, Thi Huong; Nguyen, Quang Uy

doi:10.1109/cec.2015.7257018

Cited by 39 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Chen et al [13] investigated the combination of GP with gradient descent for transfer learning in symbolic regression. Further, Dinh et al [15] proposed transfer learning in GP by using the learnt knowledge from the source domain to initialize the population of GP on the target domain in three different ways, which are copying the full trees, using the sub-trees, and copying the best trees in each generation. The results on symbolic regression problems showed that the subtree transferring strategy outperformed the other two.…”

Section: B Transfer Learning In Genetic Programmingmentioning

confidence: 99%

“…Furthermore, "when to transfer" and "how to transfer" are two key parts in GP with transfer learning. However, regarding "when to transfer", most existing GP [15] with transfer learning methods focus on transferring knowledge only at the initialization of the GP learning/evolution process, which does not fully utilise the extracted useful knowledge. Regarding "how to transfer", existing methods [15] often transfer an evolved tree from the source domain to the target domain as a whole tree, which may not be promising, but the evolved tree might be very useful if it is used as subtree to form a new tree/solution for the target problem.…”

Section: Introductionmentioning

confidence: 99%

“…However, regarding "when to transfer", most existing GP [15] with transfer learning methods focus on transferring knowledge only at the initialization of the GP learning/evolution process, which does not fully utilise the extracted useful knowledge. Regarding "how to transfer", existing methods [15] often transfer an evolved tree from the source domain to the target domain as a whole tree, which may not be promising, but the evolved tree might be very useful if it is used as subtree to form a new tree/solution for the target problem. Recently, Iqbal et al [16] presented a transfer learning method in GP that successfully utilizes the extracted knowledge at the initialization process as well as the mutation process in GP to learn image classification tasks in the same domain.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cross-Domain Reuse of Extracted Knowledge in Genetic Programming for Image Classification

Iqbal

Xue

Al-Sahaf

et al. 2017

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

Genetic programming (GP) is a well-known evolutionary computation technique, which has been successfully used to solve various problems, such as optimisation, image analysis and classification. Transfer learning is a type of machine learning approach that can be used to solve complex tasks. Transfer learning has been introduced to genetic programming to solve complex Boolean and symbolic regression problems with some promise. However, the use of transfer learning with genetic programming has not been investigated to address complex image classification tasks with noise and rotations, where GP cannot achieve satisfactory performance, but GP with transfer learning may improve the performance. In this paper, we propose a novel approach based on transfer learning and genetic programming to solve complex image classification problems by extracting and reusing blocks of knowledge/information, which are automatically discovered from similar as well as different image classification tasks during the evolutionary process. The proposed approach is evaluated on three texture data sets and three office data sets of image classification benchmarks, and achieves better classification performance than the state-of-the-art image classification algorithm. Further analysis on the evolved solutions/trees shows that the proposed approach with transfer learning can successfully discover and reuse knowledge/information extracted from similar or different problems to improve its performance on complex image classification problems.

show abstract

Section: B Transfer Learning In Genetic Programmingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cross-Domain Reuse of Extracted Knowledge in Genetic Programming for Image Classification

Iqbal

Xue

Al-Sahaf

et al. 2017

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

show abstract

“…Although both EAs and TL have received considerable attention in their own areas, few researchers in EAs studied the methods by introducing TL for difficult problem optimisation. For example, TL was introduced in Genetic Programming (GP) by taking some solutions (such as the best, middle and the worst) as the knowledge feature from the source optimisation problem to target optimisation problems by replacing some randomly generated solutions (Kocer and Arslan, 2010) or by transferring good individuals or subindividuals (sub-tree in GP) to the target problems (Dinh et al, 2015). However, both of these studies only focused on the issue in TL: 'what to transfer', but the other two issues 'how to transfer' and 'when to transfer' were not studied.…”

Section: Introductionmentioning

confidence: 99%