**Click to Read Paper**

Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks

Dec 02, 2017

Urs Köster, Tristan J. Webb, Xin Wang, Marcel Nassar, Arjun K. Bansal, William H. Constable, Oğuz H. Elibol, Scott Gray, Stewart Hall, Luke Hornof, Amir Khosrowshahi, Carey Kloss, Ruby J. Pai, Naveen Rao

Dec 02, 2017

Urs Köster, Tristan J. Webb, Xin Wang, Marcel Nassar, Arjun K. Bansal, William H. Constable, Oğuz H. Elibol, Scott Gray, Stewart Hall, Luke Hornof, Amir Khosrowshahi, Carey Kloss, Ruby J. Pai, Naveen Rao

* 14 pages, 5 figures, accepted in Neural Information Processing Systems 2017

**Click to Read Paper**

Unsupervised Threshold for Automatic Extraction of Dolphin Dorsal Fin Outlines from Digital Photographs in DARWIN (Digital Analysis and Recognition of Whale Images on a Network)

Feb 18, 2012

Scott A. Hale

Feb 18, 2012

Scott A. Hale

**Click to Read Paper**

Dictionary-Free MRI PERK: Parameter Estimation via Regression with Kernels

Oct 06, 2017

Gopal Nataraj, Jon-Fredrik Nielsen, Clayton Scott, Jeffrey A. Fessler

This paper introduces a fast, general method for dictionary-free parameter estimation in quantitative magnetic resonance imaging (QMRI) via regression with kernels (PERK). PERK first uses prior distributions and the nonlinear MR signal model to simulate many parameter-measurement pairs. Inspired by machine learning, PERK then takes these parameter-measurement pairs as labeled training points and learns from them a nonlinear regression function using kernel functions and convex optimization. PERK admits a simple implementation as per-voxel nonlinear lifting of MRI measurements followed by linear minimum mean-squared error regression. We demonstrate PERK for $T_1,T_2$ estimation, a well-studied application where it is simple to compare PERK estimates against dictionary-based grid search estimates. Numerical simulations as well as single-slice phantom and in vivo experiments demonstrate that PERK and grid search produce comparable $T_1,T_2$ estimates in white and gray matter, but PERK is consistently at least $23\times$ faster. This acceleration factor will increase by several orders of magnitude for full-volume QMRI estimation problems involving more latent parameters per voxel.
Oct 06, 2017

Gopal Nataraj, Jon-Fredrik Nielsen, Clayton Scott, Jeffrey A. Fessler

* submitted to IEEE Transactions on Medical Imaging

**Click to Read Paper**