Papers of the day   All papers

Neural Additive Models: Interpretable Machine Learning with Neural Nets

Comments

nick frosst: my new paper with @rishabh_467 @geoffreyhinton, Rich Caruana and Xuezhou Zhang is out on arxiv today! It’s about interpretability and neural additive models. Don't have time to read the paper? Read this tweet thread instead :) https://arxiv.org/abs/2004.13912 1/7

11 replies, 276 likes


nick frosst: Check out the paper for more fun graphs and a bunch of weird tricks we needed to do to get these things to work. :) https://arxiv.org/abs/2004.13912 7/7

0 replies, 14 likes


Daisuke Okanohara: Neural additive models learn a linear combination of NN output that each NN uses a single input feature as input. This enables us to analyze the relationship between their input feature and the output. https://arxiv.org/abs/2004.13912

0 replies, 10 likes


Cyrille Combettes: Interesting paper showing that separating the architecture of a neural network into individual networks for each feature can still be very competitive while, most importantly, offering interpretability

0 replies, 10 likes


Sayak Paul: I wish more threads as this one existed. Maybe they exist, I need to dig them out!

0 replies, 5 likes


Maxwell Joseph 🍩: Neural additive models: interpretable machine learning with neural nets https://arxiv.org/abs/2004.13912 🤔 https://t.co/VuAyN90LoS

0 replies, 3 likes


akira: https://arxiv.org/abs/2004.13912 Research that interpret the output of the DNN by transforming each feature separately and then adding them together to. Overfitting is big problem, so it's important to do it with regularization. https://t.co/lcq6jBFKPl

0 replies, 2 likes


午後のarXiv: "Neural Additive Models: Interpretable Machine Learning with Neural Nets", Rishabh Agarwal, Nicholas Frosst, Xuezho… https://arxiv.org/abs/2004.13912

0 replies, 1 likes


Brundage Bot: Neural Additive Models: Interpretable Machine Learning with Neural Nets. Rishabh Agarwal, Nicholas Frosst, Xuezhou Zhang, Rich Caruana, and Geoffrey E. Hinton http://arxiv.org/abs/2004.13912

1 replies, 1 likes


ML and Data Projects To Know: 📙 Neural Additive Models: Interpretable Machine Learning with Neural Nets Authors: @A25Rishabh, @nickfrosst, Xuezhou Zhang, Rich Caruana, @geoff_hinton Paper: https://arxiv.org/abs/2004.13912 Thread below:

1 replies, 1 likes


Tomonari MASADA: [2004.13912] Neural Additive Models: Interpretable Machine Learning with Neural Nets https://arxiv.org/abs/2004.13912 https://t.co/ccoTqCDMxc

1 replies, 0 likes


cs.LG Papers: Neural Additive Models: Interpretable Machine Learning with Neural Nets. Rishabh Agarwal, Nicholas Frosst, Xuezhou Zhang, Rich Caruana, and Geoffrey E. Hinton http://arxiv.org/abs/2004.13912

1 replies, 0 likes


Content

Found on Apr 30 2020 at https://arxiv.org/pdf/2004.13912.pdf

PDF content of a computer science paper: Neural Additive Models: Interpretable Machine Learning with Neural Nets