19 citations · 74 across the 13 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2017★ 2 cited
Semi-Supervised Learning via New Deep Network Inversion
Randall Balestriero, Vincent Roger, Herve G. Glotin +1
We exploit a recently derived inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework that applies to a wide range of systems and pr…
stat.ML2017★ 6 cited
Linear Time Complexity Deep Fourier Scattering Network and Extension to Nonlinear Invariants
Randall Balestriero, Herve Glotin
In this paper we propose a scalable version of a state-of-the-art deterministic time-invariant feature extraction approach based on consecutive changes of basis and nonlinearities,…