Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle
Transfer learning algorithms have been widely studied for machine learning in recent times. In particular, in image recognition and classification tasks, transfer learning has shown significant benefits, and is getting plenty of attention in the research community. While performing a transfer of kno...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/16/5631 |
| _version_ | 1797558249290989568 |
|---|---|
| author | Arjun Magotra Juntae Kim |
| author_facet | Arjun Magotra Juntae Kim |
| author_sort | Arjun Magotra |
| collection | DOAJ |
| description | Transfer learning algorithms have been widely studied for machine learning in recent times. In particular, in image recognition and classification tasks, transfer learning has shown significant benefits, and is getting plenty of attention in the research community. While performing a transfer of knowledge among source and target tasks, homogeneous dataset is not always available, and heterogeneous dataset can be chosen in certain circumstances. In this article, we propose a way of improving transfer learning efficiency, in case of a heterogeneous source and target, by using the Hebbian learning principle, called Hebbian transfer learning (HTL). In computer vision, biologically motivated approaches such as Hebbian learning represent associative learning, where simultaneous activation of brain cells positively affect the increase in synaptic connection strength between the individual cells. The discriminative nature of learning for the search of features in the task of image classification fits well to the techniques, such as the Hebbian learning rule—neurons that fire together wire together. The deep learning models, such as convolutional neural networks (CNN), are widely used for image classification. In transfer learning, for such models, the connection weights of the learned model should adapt to new target dataset with minimum effort. The discriminative learning rule, such as Hebbian learning, can improve performance of learning by quickly adapting to discriminate between different classes defined by target task. We apply the Hebbian principle as synaptic plasticity in transfer learning for classification of images using a heterogeneous source-target dataset, and compare results with the standard transfer learning case. Experimental results using CIFAR-10 (Canadian Institute for Advanced Research) and CIFAR-100 datasets with various combinations show that the proposed HTL algorithm can improve the performance of transfer learning, especially in the case of a heterogeneous source and target dataset. |
| first_indexed | 2024-03-10T17:28:41Z |
| format | Article |
| id | doaj.art-a8b6bb5bda414b15a36f88f434c70595 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T17:28:41Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a8b6bb5bda414b15a36f88f434c705952023-11-20T10:06:22ZengMDPI AGApplied Sciences2076-34172020-08-011016563110.3390/app10165631Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning PrincipleArjun Magotra0Juntae Kim1Department of Computer Engineering, Dongguk University, 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaDepartment of Computer Engineering, Dongguk University, 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaTransfer learning algorithms have been widely studied for machine learning in recent times. In particular, in image recognition and classification tasks, transfer learning has shown significant benefits, and is getting plenty of attention in the research community. While performing a transfer of knowledge among source and target tasks, homogeneous dataset is not always available, and heterogeneous dataset can be chosen in certain circumstances. In this article, we propose a way of improving transfer learning efficiency, in case of a heterogeneous source and target, by using the Hebbian learning principle, called Hebbian transfer learning (HTL). In computer vision, biologically motivated approaches such as Hebbian learning represent associative learning, where simultaneous activation of brain cells positively affect the increase in synaptic connection strength between the individual cells. The discriminative nature of learning for the search of features in the task of image classification fits well to the techniques, such as the Hebbian learning rule—neurons that fire together wire together. The deep learning models, such as convolutional neural networks (CNN), are widely used for image classification. In transfer learning, for such models, the connection weights of the learned model should adapt to new target dataset with minimum effort. The discriminative learning rule, such as Hebbian learning, can improve performance of learning by quickly adapting to discriminate between different classes defined by target task. We apply the Hebbian principle as synaptic plasticity in transfer learning for classification of images using a heterogeneous source-target dataset, and compare results with the standard transfer learning case. Experimental results using CIFAR-10 (Canadian Institute for Advanced Research) and CIFAR-100 datasets with various combinations show that the proposed HTL algorithm can improve the performance of transfer learning, especially in the case of a heterogeneous source and target dataset.https://www.mdpi.com/2076-3417/10/16/5631Hebbian learningplasticitytransfer learningimage classificationconvolutional neural networks |
| spellingShingle | Arjun Magotra Juntae Kim Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle Applied Sciences Hebbian learning plasticity transfer learning image classification convolutional neural networks |
| title | Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle |
| title_full | Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle |
| title_fullStr | Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle |
| title_full_unstemmed | Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle |
| title_short | Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle |
| title_sort | improvement of heterogeneous transfer learning efficiency by using hebbian learning principle |
| topic | Hebbian learning plasticity transfer learning image classification convolutional neural networks |
| url | https://www.mdpi.com/2076-3417/10/16/5631 |
| work_keys_str_mv | AT arjunmagotra improvementofheterogeneoustransferlearningefficiencybyusinghebbianlearningprinciple AT juntaekim improvementofheterogeneoustransferlearningefficiencybyusinghebbianlearningprinciple |