A Spline Theory of Deep Learning

By Randall Balestriero, Richard Baraniuk. 2018

116 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Minyoung Huh
2. Phillip Isola
3. Brian Cheung
4. Tongzhou Wang
5. Jun-Yan Zhu
6. Richard Zhang
7. Alexei A. Efros
8. Antonio Torralba

Citations in the corpus

• High Fidelity Visualization of What Your Self-Supervised Representation Knows About (2021, neutral): “Without loss of generality we consider a mapping f that is continuous piecewise affine (CPA), as is the case for most DNs(Balestriero & Baraniuk, 2018).”
• The Platonic Representation Hypothesis (2024, background): “Theoretically, Balestriero & Baraniuk (2018) showed that models with similar outputs ( e.g. , as a result of having high performance) also have similar internal activations.”