2.9k citations
- Rice UniversityUS10 papers
- Cornell UniversityUS9 papers
- University of Maryland, College ParkUS4 papers
- Carnegie Mellon UniversityUS2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Columbia UniversityUS2 papers
- IBM Research - Thomas J. Watson Research CenterUS2 papers
- Methodist HospitalUS2 papers
- Rensselaer Polytechnic InstituteUS2 papers
- Stanford UniversityUS2 papers
- Texas A&M UniversityUS2 papers
- The University of Texas Health Science Center at HoustonUS2 papers
5 papers · 1 filter
A Novel Deep Learning Pipeline for Retinal Vessel Detection in Fluorescein Angiography
Li Ding, Mohammad H. Bawany, Ajay E. Kuriyan +3
While recent advances in deep learning have significantly advanced the state of the art for vessel detection in color fundus (CF) images, the success for detecting vessels in fluor…
The Geometry of Deep Networks: Power Diagram Subdivision
Randall Balestriero, Romain Cosentino, Behnaam Aazhang +1
We study the geometry of deep (neural) networks (DNs) with piecewise affine and convex nonlinearities. The layers of such DNs have been shown to be {\em max-affine spline operators…
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
Joshua J. Michalenko, Ameesh Shah, Abhinav Verma +3
We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language. Specifically, we train a RNN on positi…
Sub-linear Memory Sketches for Near Neighbor Search on Streaming Data
Benjamin Coleman, Richard G. Baraniuk, Anshumali Shrivastava
We present the first sublinear memory sketch that can be queried to find the nearest neighbors in a dataset. Our online sketching algorithm compresses an N element dataset to a ske…
A novel approach to medical radioisotope production using inverse kinematics: a successful production test of the theranostic radionuclide 67Cu
G Souliotis, M Rodrigues, K Wang +7
A novel method for the production of important medical radioisotopes has been developed. The approach is based on performing the nuclear reaction in inverse kinematics, namely send…