Search Results for author:
Found 5 papers, 2 papers with code
slimTrain -- A Stochastic Approximation Method for Training Separable Deep Neural Networks
In the absence of theoretical guidelines or prior experience on similar tasks, this requires solving many training problems, which can be time-consuming and demanding on computational resources.
Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection
To solve the optimization problem more efficiently, we propose the use of variable projection (VarPro), a method originally designed for separable nonlinear least-squares problems.
Non-negative Tensor Patch Dictionary Approaches for Image Compression and Deblurring Applications
Building on that work, in this paper, we use of non-negative tensor patch-based dictionaries trained on other data, such as facial image data, for the purposes of either compression or image deblurring.
Stable Tensor Neural Networks for Rapid Deep Learning
To exemplify the elegant, matrix-mimetic algebraic structure of our $t$-NNs, we expand on recent work (Haber and Ruthotto, 2017) which interprets deep neural networks as discretizations of non-linear differential equations and introduces stable neural networks which promote superior generalization.
Image classification using local tensor singular value decompositions
From linear classifiers to neural networks, image classification has been a widely explored topic in mathematics, and many algorithms have proven to be effective classifiers.
