AI Research Focuses on Network Topology Optimization
Current methods primarily focus on adjusting weights within a fixed structure. A trending topic on Zhihu discusses the limitations of current machine learning neural network training, which optimizes weights for a fixed topology.
Topics
Developing
- 862d Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore.
- 862d Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
- 862d Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est.
- 862d Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium.
Sources · 7 independent
Zhihu Trending
“为什么神经网络训练时只能改变权重而不能改变网络的拓扑结构？. #19 trending on Zhihu. Heat: 63 万热度. 现有的机器学习神经网络训练过程中都是对一个固定的拓扑结构来优化权重，似乎没看到能够改变网络结构的训练方法。理论上不同的网络拓扑结构可以适应不同的问题，所以是否有可能存在训练方法能够改变网络结构，类似大脑中突触的建立过程？”
Zhihu Trending
“为什么神经网络训练时只能改变权重而不能改变网络的拓扑结构？. #19 trending on Zhihu. Heat: 63 万热度. 现有的机器学习神经网络训练过程中都是对一个固定的拓扑结构来优化权重，似乎没看到能够改变网络结构的训练方法。”
Unlock the full story
Get a Pro subscription or above to see the live story progression and the full list of independent sources confirming each event as they happen.
Log in to upgrade