Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.01772 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929418689052672 |
|---|---|
| author | Li, Yanjie Li, Weijun Yu, Lina Wu, Min Liu, Jinyi Li, Wenqiang Hao, Meilan Wei, Shu Deng, Yusong Zhang, Liping Dong, Xiaoli Qin, Hong Ning, Xin Zhang, Yugui Lu, Baoli Xu, Jian Li, Shuang |
| author_facet | Li, Yanjie Li, Weijun Yu, Lina Wu, Min Liu, Jinyi Li, Wenqiang Hao, Meilan Wei, Shu Deng, Yusong Zhang, Liping Dong, Xiaoli Qin, Hong Ning, Xin Zhang, Yugui Lu, Baoli Xu, Jian Li, Shuang |
| contents | Multilayer perception (MLP) has permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable facet of contemporary scientific research endeavors. However, MLP has obvious drawbacks. 1), The type of activation function is single and relatively fixed, which leads to poor `representation ability' of the network, and it is often to solve simple problems with complex networks; 2), the network structure is not adaptive, it is easy to cause network structure redundant or insufficient. In this work, we propose a novel neural network paradigm X-Net promising to replace MLPs. X-Net can dynamically learn activation functions individually based on derivative information during training to improve the network's representational ability for specific tasks. At the same time, X-Net can precisely adjust the network structure at the neuron level to accommodate tasks of varying complexity and reduce computational costs. We show that X-Net outperforms MLPs in terms of representational capability. X-Net can achieve comparable or even better performance than MLP with much smaller parameters on regression and classification tasks. Specifically, in terms of the number of parameters, X-Net is only 3% of MLP on average and only 1.1% under some tasks. We also demonstrate X-Net's ability to perform scientific discovery on data from various disciplines such as energy, environment, and aerospace, where X-Net is shown to help scientists discover new laws of mathematics or physics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01772 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure Li, Yanjie Li, Weijun Yu, Lina Wu, Min Liu, Jinyi Li, Wenqiang Hao, Meilan Wei, Shu Deng, Yusong Zhang, Liping Dong, Xiaoli Qin, Hong Ning, Xin Zhang, Yugui Lu, Baoli Xu, Jian Li, Shuang Artificial Intelligence Networking and Internet Architecture Multilayer perception (MLP) has permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable facet of contemporary scientific research endeavors. However, MLP has obvious drawbacks. 1), The type of activation function is single and relatively fixed, which leads to poor `representation ability' of the network, and it is often to solve simple problems with complex networks; 2), the network structure is not adaptive, it is easy to cause network structure redundant or insufficient. In this work, we propose a novel neural network paradigm X-Net promising to replace MLPs. X-Net can dynamically learn activation functions individually based on derivative information during training to improve the network's representational ability for specific tasks. At the same time, X-Net can precisely adjust the network structure at the neuron level to accommodate tasks of varying complexity and reduce computational costs. We show that X-Net outperforms MLPs in terms of representational capability. X-Net can achieve comparable or even better performance than MLP with much smaller parameters on regression and classification tasks. Specifically, in terms of the number of parameters, X-Net is only 3% of MLP on average and only 1.1% under some tasks. We also demonstrate X-Net's ability to perform scientific discovery on data from various disciplines such as energy, environment, and aerospace, where X-Net is shown to help scientists discover new laws of mathematics or physics. |
| title | A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure |
| topic | Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2401.01772 |