Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle
The plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain’s self-modifying abilities play an essential role in lea...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/13/8/1344 |
| _version_ | 1797522014429249536 |
|---|---|
| author | Arjun Magotra Juntae Kim |
| author_facet | Arjun Magotra Juntae Kim |
| author_sort | Arjun Magotra |
| collection | DOAJ |
| description | The plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain’s self-modifying abilities play an essential role in learning and adaptation. The artificial neural networks with neuromodulated plasticity are used to implement transfer learning in the image classification domain. In particular, this has application in image detection, image segmentation, and transfer of learning parameters with significant results. This paper proposes a novel approach to enhance transfer learning accuracy in a heterogeneous source and target, using the neuromodulation of the Hebbian learning principle, called NDHTL (Neuromodulated Dopamine Hebbian Transfer Learning). Neuromodulation of plasticity offers a powerful new technique with applications in training neural networks implementing asymmetric backpropagation using Hebbian principles in transfer learning motivated CNNs (Convolutional neural networks). Biologically motivated concomitant learning, where connected brain cells activate positively, enhances the synaptic connection strength between the network neurons. Using the NDHTL algorithm, the percentage of change of the plasticity between the neurons of the CNN layer is directly managed by the dopamine signal’s value. The discriminative nature of transfer learning fits well with the technique. The learned model’s connection weights must adapt to unseen target datasets with the least cost and effort in transfer learning. Using distinctive learning principles such as dopamine Hebbian learning in transfer learning for asymmetric gradient weights update is a novel approach. The paper emphasizes the NDHTL algorithmic technique as synaptic plasticity controlled by dopamine signals in transfer learning to classify images using source-target datasets. The standard transfer learning using gradient backpropagation is a symmetric framework. Experimental results using CIFAR-10 and CIFAR-100 datasets show that the proposed NDHTL algorithm can enhance transfer learning efficiency compared to existing methods. |
| first_indexed | 2024-03-10T08:20:36Z |
| format | Article |
| id | doaj.art-8d1281c15afe42dd8dd7fb410afe7ad7 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T08:20:36Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-8d1281c15afe42dd8dd7fb410afe7ad72023-11-22T09:59:45ZengMDPI AGSymmetry2073-89942021-07-01138134410.3390/sym13081344Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian PrincipleArjun Magotra0Juntae Kim1Department of Computer Science and Engineering, Dongguk University, 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaDepartment of Computer Science and Engineering, Dongguk University, 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaThe plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain’s self-modifying abilities play an essential role in learning and adaptation. The artificial neural networks with neuromodulated plasticity are used to implement transfer learning in the image classification domain. In particular, this has application in image detection, image segmentation, and transfer of learning parameters with significant results. This paper proposes a novel approach to enhance transfer learning accuracy in a heterogeneous source and target, using the neuromodulation of the Hebbian learning principle, called NDHTL (Neuromodulated Dopamine Hebbian Transfer Learning). Neuromodulation of plasticity offers a powerful new technique with applications in training neural networks implementing asymmetric backpropagation using Hebbian principles in transfer learning motivated CNNs (Convolutional neural networks). Biologically motivated concomitant learning, where connected brain cells activate positively, enhances the synaptic connection strength between the network neurons. Using the NDHTL algorithm, the percentage of change of the plasticity between the neurons of the CNN layer is directly managed by the dopamine signal’s value. The discriminative nature of transfer learning fits well with the technique. The learned model’s connection weights must adapt to unseen target datasets with the least cost and effort in transfer learning. Using distinctive learning principles such as dopamine Hebbian learning in transfer learning for asymmetric gradient weights update is a novel approach. The paper emphasizes the NDHTL algorithmic technique as synaptic plasticity controlled by dopamine signals in transfer learning to classify images using source-target datasets. The standard transfer learning using gradient backpropagation is a symmetric framework. Experimental results using CIFAR-10 and CIFAR-100 datasets show that the proposed NDHTL algorithm can enhance transfer learning efficiency compared to existing methods.https://www.mdpi.com/2073-8994/13/8/1344transfer learningasymmetric backpropagationconvolutional neural networksplasticityneuromodulation |
| spellingShingle | Arjun Magotra Juntae Kim Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle Symmetry transfer learning asymmetric backpropagation convolutional neural networks plasticity neuromodulation |
| title | Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle |
| title_full | Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle |
| title_fullStr | Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle |
| title_full_unstemmed | Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle |
| title_short | Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle |
| title_sort | neuromodulated dopamine plastic networks for heterogeneous transfer learning with hebbian principle |
| topic | transfer learning asymmetric backpropagation convolutional neural networks plasticity neuromodulation |
| url | https://www.mdpi.com/2073-8994/13/8/1344 |
| work_keys_str_mv | AT arjunmagotra neuromodulateddopamineplasticnetworksforheterogeneoustransferlearningwithhebbianprinciple AT juntaekim neuromodulateddopamineplasticnetworksforheterogeneoustransferlearningwithhebbianprinciple |