Search Results for author: Alan Edelman

Found 15 papers, 12 papers with code

Locally Regularized Neural Differential Equations: Some Black Boxes Were Meant to Remain Closed!

1 code implementation3 Mar 2023 Avik Pal, Alan Edelman, Chris Rackauckas

Implicit layer deep learning techniques, like Neural Differential Equations, have become an important modeling framework due to their ability to adapt to new problems automatically.

Backpropagation through Back Substitution with a Backslash

1 code implementation23 Feb 2023 Alan Edelman, Ekin Akyurek, Yuyang Wang

This paper has three contributions: (i) it is of intellectual value to replace traditional treatments of automatic differentiation with a (left acting) operator theoretic, graph-based approach; (ii) operators can be readily placed in matrices in software in programming languages such as Julia as an implementation option; (iii) we introduce a novel notation, ``transpose dot'' operator ``$\{\}^{T_\bullet}$'' that allows for the reversal of operators.

Continuous Deep Equilibrium Models: Training Neural ODEs faster by integrating them to Infinity

1 code implementation28 Jan 2022 Avik Pal, Alan Edelman, Christopher Rackauckas

Additionally, we address the question: is there a way to simultaneously achieve the robustness of implicit layers while allowing the reduced computational expense of an explicit layer?

High-performance symbolic-numerics via multiple dispatch

4 code implementations9 May 2021 Shashi Gowda, Yingbo Ma, Alessandro Cheli, Maja Gwozdz, Viral B. Shah, Alan Edelman, Christopher Rackauckas

We showcase how this can be used to optimize term construction and give a 113x acceleration on general symbolic transformations.

Vocal Bursts Intensity Prediction

Accelerating Simulation of Stiff Nonlinear Systems using Continuous-Time Echo State Networks

no code implementations7 Oct 2020 Ranjan Anantharaman, Yingbo Ma, Shashi Gowda, Chris Laughman, Viral Shah, Alan Edelman, Chris Rackauckas

Modern design, control, and optimization often requires simulation of highly nonlinear models, leading to prohibitive computational costs.

Signal Enhancement for Magnetic Navigation Challenge Problem

1 code implementation23 Jul 2020 Albert R. Gnadt, Joseph Belarge, Aaron Canciani, Glenn Carl, Lauren Conger, Joseph Curro, Alan Edelman, Peter Morales, Aaron P. Nielsen, Michael F. O'Keeffe, Christopher V. Rackauckas, Jonathan Taylor, Allan B. Wollaber

It is difficult to separate the Earth magnetic anomaly field, which is crucial for navigation, from the total magnetic field reading from the sensor.

Universal Differential Equations for Scientific Machine Learning

8 code implementations13 Jan 2020 Christopher Rackauckas, Yingbo Ma, Julius Martensen, Collin Warner, Kirill Zubov, Rohit Supekar, Dominic Skinner, Ali Ramadhan, Alan Edelman

In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets."

BIG-bench Machine Learning

A Differentiable Programming System to Bridge Machine Learning and Scientific Computing

2 code implementations17 Jul 2019 Mike Innes, Alan Edelman, Keno Fischer, Chris Rackauckas, Elliot Saba, Viral B. Shah, Will Tebbutt

Scientific computing is increasingly incorporating the advancements in machine learning and the ability to work with large amounts of data.

BIG-bench Machine Learning

Circuitscape in Julia: High Performance Connectivity Modelling to Support Conservation Decisions

2 code implementations8 Jun 2019 Ranjan Anantharaman, Kimberly Hall, Viral Shah, Alan Edelman

Connectivity across landscapes influences a wide range of conservation-relevant ecological processes, including species movements, gene flow, and the spread of wildfire, pests, and diseases.

Vocal Bursts Intensity Prediction

TabulaROSA: Tabular Operating System Architecture for Massively Parallel Heterogeneous Compute Engines

no code implementations14 Jul 2018 Jeremy Kepner, Ron Brightwell, Alan Edelman, Vijay Gadepally, Hayden Jananthan, Michael Jones, Sam Madden, Peter Michaleas, Hamed Okhravi, Kevin Pedretti, Albert Reuther, Thomas Sterling, Mike Stonebraker

In this context, an operating system can be viewed as software that brokers and tracks the resources of the compute engines and is akin to a database management system.

Distributed, Parallel, and Cluster Computing Databases Operating Systems Performance

Accelerated Convolutions for Efficient Multi-Scale Time to Contact Computation in Julia

1 code implementation28 Dec 2016 Alexander Amini, Berthold Horn, Alan Edelman

Efficient computation of convolutions is critical to artificial intelligence in real-time applications, like machine vision, where convolutions must be continuously and efficiently computed on tens to hundreds of kilobytes per second.

Julia: A Fresh Approach to Numerical Computing

1 code implementation6 Nov 2014 Jeff Bezanson, Alan Edelman, Stefan Karpinski, Viral B. Shah

Bridging cultures that have often been distant, Julia combines expertise from the diverse fields of computer science and computational science to create a new approach to numerical computing.

Mathematical Software

Julia: A Fast Dynamic Language for Technical Computing

2 code implementations24 Sep 2012 Jeff Bezanson, Stefan Karpinski, Viral B. Shah, Alan Edelman

Dynamic languages have become popular for scientific computing.

Programming Languages Computational Engineering, Finance, and Science D.3.2

Matrix Models for Beta Ensembles

4 code implementations25 Jun 2002 Ioana Dumitriu, Alan Edelman

This paper constructs tridiagonal random matrix models for general ($\beta>0$) $\beta$-Hermite (Gaussian) and $\beta$-Laguerre (Wishart) ensembles.

Mathematical Physics Mathematical Physics Probability Representation Theory

Cannot find the paper you are looking for? You can Submit a new open access paper.