Skip to content

可视化AI模型CNN和Transformer

发表: at 04:00

gif

https://poloclub.github.io/

https://github.com/poloclub

Scalable. Interactive. Interpretable. At Georgia Tech, we innovate scalable, interactive, and interpretable tools that amplify human’s ability to understand and interact with billion-scale data and machine learning models. Our current research thrusts: human-centered AI (interpretable, fair, safe AI; adversarial ML); large graph visualization and mining; cybersecurity; and social good (health, energy).

image image

CNN 卷积神经网络的可视化

https://poloclub.github.io/cnn-explainer/

https://arxiv.org/abs/2004.15004

https://github.com/poloclub/cnn-explainer

image image

Transformer 神经网络的可视化

https://poloclub.github.io/transformer-explainer/

https://arxiv.org/abs/2408.04619

https://github.com/poloclub/transformer-explainer


上篇文章
EasyTier + ZeroTier助你异地组网无忧
下篇文章
NumPy 聚合函数中 axis 参数的维度变换详解