A 3D ray traced biological neural network learning model
Abstract Training large neural networks on big datasets requires significant computational resources and time. Transfer learning reduces training time by pre-training a base model on one dataset and transferring the knowledge to a new model for another dataset. However, current choices of transfer l...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-06-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-48747-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850179707203485696 |
|---|---|
| author | Brosnan Yuen Xiaodai Dong Tao Lu |
| author_facet | Brosnan Yuen Xiaodai Dong Tao Lu |
| author_sort | Brosnan Yuen |
| collection | DOAJ |
| description | Abstract Training large neural networks on big datasets requires significant computational resources and time. Transfer learning reduces training time by pre-training a base model on one dataset and transferring the knowledge to a new model for another dataset. However, current choices of transfer learning algorithms are limited because the transferred models always have to adhere to the dimensions of the base model and can not easily modify the neural architecture to solve other datasets. On the other hand, biological neural networks (BNNs) are adept at rearranging themselves to tackle completely different problems using transfer learning. Taking advantage of BNNs, we design a dynamic neural network that is transferable to any other network architecture and can accommodate many datasets. Our approach uses raytracing to connect neurons in a three-dimensional space, allowing the network to grow into any shape or size. In the Alcala dataset, our transfer learning algorithm trains the fastest across changing environments and input sizes. In addition, we show that our algorithm also outperformance the state of the art in EEG dataset. In the future, this network may be considered for implementation on real biological neural networks to decrease power consumption. |
| format | Article |
| id | doaj-art-80c5b7bb13c348719e2f76215d75bb9a |
| institution | OA Journals |
| issn | 2041-1723 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-80c5b7bb13c348719e2f76215d75bb9a2025-08-20T02:18:25ZengNature PortfolioNature Communications2041-17232024-06-0115111610.1038/s41467-024-48747-7A 3D ray traced biological neural network learning modelBrosnan Yuen0Xiaodai Dong1Tao Lu2Department of Electrical and Computer Engineering, University of VictoriaDepartment of Electrical and Computer Engineering, University of VictoriaDepartment of Electrical and Computer Engineering, University of VictoriaAbstract Training large neural networks on big datasets requires significant computational resources and time. Transfer learning reduces training time by pre-training a base model on one dataset and transferring the knowledge to a new model for another dataset. However, current choices of transfer learning algorithms are limited because the transferred models always have to adhere to the dimensions of the base model and can not easily modify the neural architecture to solve other datasets. On the other hand, biological neural networks (BNNs) are adept at rearranging themselves to tackle completely different problems using transfer learning. Taking advantage of BNNs, we design a dynamic neural network that is transferable to any other network architecture and can accommodate many datasets. Our approach uses raytracing to connect neurons in a three-dimensional space, allowing the network to grow into any shape or size. In the Alcala dataset, our transfer learning algorithm trains the fastest across changing environments and input sizes. In addition, we show that our algorithm also outperformance the state of the art in EEG dataset. In the future, this network may be considered for implementation on real biological neural networks to decrease power consumption.https://doi.org/10.1038/s41467-024-48747-7 |
| spellingShingle | Brosnan Yuen Xiaodai Dong Tao Lu A 3D ray traced biological neural network learning model Nature Communications |
| title | A 3D ray traced biological neural network learning model |
| title_full | A 3D ray traced biological neural network learning model |
| title_fullStr | A 3D ray traced biological neural network learning model |
| title_full_unstemmed | A 3D ray traced biological neural network learning model |
| title_short | A 3D ray traced biological neural network learning model |
| title_sort | 3d ray traced biological neural network learning model |
| url | https://doi.org/10.1038/s41467-024-48747-7 |
| work_keys_str_mv | AT brosnanyuen a3draytracedbiologicalneuralnetworklearningmodel AT xiaodaidong a3draytracedbiologicalneuralnetworklearningmodel AT taolu a3draytracedbiologicalneuralnetworklearningmodel AT brosnanyuen 3draytracedbiologicalneuralnetworklearningmodel AT xiaodaidong 3draytracedbiologicalneuralnetworklearningmodel AT taolu 3draytracedbiologicalneuralnetworklearningmodel |