ICML 2020

Are Neural Nets Modular? Inspecting Their Functionality Through Differentiable Weight Masks

Jul 15, 2020

|

74 views

Róbert Csordás

Interpretability

Machine Learning

Details

Spotlight presentation of our paper "Are Neural Nets Modular? Inspecting Their Functionality Through Differentiable Weight Masks". Presented on ICML 2020 Workshop on Human Interpretability in Machine Learning (https://sites.google.com/view/whi2020/home). Link to the paper: http://people.idsia.ch/~csordas/are_neural_networks_modular.pdf. For code, check https://github.com/xdever/modules.

Category: ICML 2020

Comments

loading...

Reactions (0) | Note

📝 No reactions yet

Be the first one to share your thoughts!

Reactions(0)

Note

loading...

Recommended

ICAPS 2014: Aijun Bai on "Thompson Sampling Based Monte-Carlo Planning in POMDPs"

ICAPS | Jul 3, 2014

ICAPS 2014: Satish Kumar on "A Tree-Based Algorithm for Construction Robots"

ICAPS | Jul 16, 2014

ICAPS 2014: Peter Ondruska on "The Route Not Taken: Driver-Centric Estimation..."

ICAPS | Jul 21, 2014

ICAPS 2014: Franc Ivankovic on "Optimal Planning with Global Numerical State Constraints"

ICAPS | Jul 23, 2014

ICAPS 2014: Enrico Scala on "Plan Repair for Resource Constrained Tasks via Numeric Macro Actions"

ICAPS | Jul 23, 2014