✳flâneur — a map of the web's best reading
Feature Visualization
distill.pub · 5,786 words · saved by 1 readers
How neural networks build up their understanding of images
Feature Visualization Distill Feature Visualization How neural networks build up their understanding of images Feature visualization allows us to see how GoogLeNet , trained on the ImageNet dataset, builds up its understanding of images over many layers. Visualizations of all channels are available in the appendix . Authors Affiliations Chris Olah Google Brain Team Alexander Mordvintsev Google Research Ludwig Schubert Google Brain Team Published Nov. 7, 2017 DOI 10.23915/distill.00007 There is a growing sense that neural networks need to be interpretable to humans. The field of neural network
Explore this link on the map →saved by
related reading
- Feature Visualizationdistill.pub
- A Recipe for Training Neural Networkskarpathy.github.io
- Distill — Latest articles about machine learningdistill.pub
- Toy Models of Superpositiontransformer-circuits.pub
- The Building Blocks of Interpretabilitydistill.pub
- Zoom In: An Introduction to Circuitsdistill.pub
- Visualizing Neural Networks with the Grand Tourdistill.pub
- Home - colah's blogcolah.github.io
- Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
- A Recipe for Training Neural Networkskarpathy.github.io
- Inceptionism: Going Deeper into Neural Networksresearch.google
- Feature-wise transformationsdistill.pub