Neuromodulated Dopamine Plastic Networks for Heterogeneous Transfer Learning with Hebbian Principle
| Autor: | Juntae Kim, Arjun Magotra |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Physics and Astronomy (miscellaneous)
Computer science General Mathematics 02 engineering and technology transfer learning Convolutional neural network 03 medical and health sciences 0302 clinical medicine Discriminative model convolutional neural networks 0202 electrical engineering electronic engineering information engineering Computer Science (miscellaneous) QA1-939 Artificial neural network business.industry Image segmentation Backpropagation Hebbian theory Chemistry (miscellaneous) Principles of learning plasticity neuromodulation asymmetric backpropagation 020201 artificial intelligence & image processing Artificial intelligence business Transfer of learning 030217 neurology & neurosurgery Mathematics |
| Zdroj: | Symmetry, Vol 13, Iss 1344, p 1344 (2021) Symmetry Volume 13 Issue 8 |
| ISSN: | 2073-8994 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|