130 citations · 428 across the 6 of their papers we have counts for
6 papers
Functional or imperative? On pleasant semantics for differentiable programming languages
Michael Innes
In machine learning (ML), researchers and engineers seem to be at odds. System implementers would prefer models to be declarative, with detailed type information and semantic restr…
A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
Mike Innes, Alan Edelman, Keno Fischer +4
Scientific computing is increasingly incorporating the advancements in machine learning and the ability to work with large amounts of data. At the same time, machine learning model…
DiffEqFlux.jl - A Julia Library for Neural Differential Equations
Chris Rackauckas, Mike Innes, Yingbo Ma +3
DiffEqFlux.jl is a library for fusing neural networks and differential equations. In this work we describe differential equations from the viewpoint of data science and discuss the…
A Comparison of Automatic Differentiation and Continuous Sensitivity Analysis for Derivatives of Differential Equation Solutions
Yingbo Ma, Vaibhav Dixit, Mike Innes +2
Derivatives of differential equation solutions are commonly for parameter estimation, fitting neural differential equations, and as model diagnostics. However, with a litany of cho…
Fashionable Modelling with Flux
Michael Innes, Elliot Saba, Keno Fischer +6
Machine learning as a discipline has seen an incredible surge of interest in recent years due in large part to a perfect storm of new theory, superior tooling, renewed interest in…
Don't Unroll Adjoint: Differentiating SSA-Form Programs
Michael Innes
This paper presents reverse-mode algorithmic differentiation (AD) based on source code transformation, in particular of the Static Single Assignment (SSA) form used by modern compi…