Statistical Mechanics of Deep Linear Neural Networks: The Backpropagating Kernel Renormalization
Sign Up to like & getrecommendations! Published in 2021 at "Physical Review X"
DOI: 10.1103/physrevx.11.031059
Abstract: The groundbreaking success of deep learning in many real-world tasks has triggered an intense effort to understand theoretically the power and limitations of deep learning in the training and generalization of complex tasks, so far… read more here.
Keywords: deep linear; neural networks; linear neural; statistical mechanics ... See more keywords
Dynamic Imaging Using Deep Bi-Linear Unsupervised Representation (DEBLUR)
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Medical Imaging"
DOI: 10.1109/tmi.2022.3168559
Abstract: Bilinear models such as low-rank and dictionary methods, which decompose dynamic data to spatial and temporal factor matrices are powerful and memory-efficient tools for the recovery of dynamic MRI data. Current bilinear methods rely on… read more here.
Keywords: imaging using; deep linear; factor matrices; representation ... See more keywords
The loss surface of deep linear networks viewed through the algebraic geometry lens
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2021.3071289
Abstract: By using the viewpoint of modern computational algebraic geometry, we explore properties of the optimization landscapes of the deep linear neural network models. After clarifying on the various definitions of "flat" minima, we show that… read more here.
Keywords: algebraic geometry; number; linear networks; minima ... See more keywords