Visualizing Convolutional Neural Networks using Lucid

Опубликовано 6 декабря 2019, 17:08

In this episode of AI Adventures, Yufeng introduces Lucid, a tool for a collection of infrastructure and tools for research in neural network interpretability. Learn about feature activations and how they can be used to better understand what different parts of a convolutional neural network is looking for!

Lucid library on GitHub: goo.gle/2PgACph

Two distill.pub articles for more details:
goo.gle/feature-visualization
goo.gle/building-blocks

Check out the rest of the Cloud AI Adventures playlist: goo.gl/UC5usG

Subscribe to get all the episodes as they come out: goo.gl/S0AS51

Product: Lucid, TensorFlow, Colab; fullname:Yufeng Guo;

#AIAdventures