Alexander Cloninger

Provable approximation properties for deep neural networks

We discuss approximation of functions using deep neural nets. Given a function

Efficient 2D MRI relaxometry using compressed sensing.

f

DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network

on a

Describing the performance of U.S. hospitals by applying big data analytics

d

Hildreth's algorithm with applications to soft constraints for user interface layout

-dimensional manifold

2D sparse sampling algorithm for ND Fredholm equations with applications to NMR relaxometry

\Gamma \subset \mathbb{R}^m

Multimodal Data Fusion via Graph- and Operator-based Techniques

, we construct a sparsely-connected depth-4 neural network and bound its error in approximating

Deep Survival: A Deep Cox Proportional Hazards Network.

f

Function Weighted Metric Discovery for Unreliable Functions

. The size of the network depends on dimension and curvature of the manifold

Bigeometric Organization of Deep Nets

\Gamma