Fashionable Modelling with Flux
arXiv:1811.01457
Abstract
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 its capabilities. We present in this paper a framework named Flux that shows how further refinement of the core ideas of machine learning, built upon the foundation of the Julia programming language, can yield an environment that is simple, easily modifiable, and performant. We detail the fundamental principles of Flux as a framework for differentiable programming, give examples of models that are implemented within Flux to display many of the language and framework-level features that contribute to its ease of use and high productivity, display internal compiler techniques used to enable the acceleration and performance that lies at the heart of Flux, and finally give an overview of the larger ecosystem that Flux fits inside of.
References in corpus (4)
Cited by in corpus (26)
- Adaptive numerical simulations with Trixi.jl: A case study of Julia for scientific computing
- Finite element interpolated neural networks for solving forward and inverse problems
- Multiple shooting for training neural differential equations on time series
- Performance of Julia for High Energy Physics Analyses
- Learned multiphysics inversion with differentiable programming and machine learning
- Neural network enhanced measurement efficiency for molecular groundstates
- Inference of neutrino flavor evolution through data assimilation and neural differential equations
- Reverse engineering of one-qubit filter functions with dynamical invariants
- SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control
- Endogenous Macrodynamics in Algorithmic Recourse
- Equinox: neural networks in JAX via callable PyTrees and filtered transformations
- Closed-loop training of static output feedback neural network controllers for large systems: A distillation case study
- AP-Perf: Incorporating Generic Performance Metrics in Differentiable Learning
- Augmenting Neural Differential Equations to Model Unknown Dynamical Systems with Incomplete State Information
- Supervised Whole DAG Causal Discovery
- Optimal Transport Based Refinement of Physics-Informed Neural Networks
- A Physics-Constrained Neural Differential Equation Framework for Data-Driven Snowpack Simulation
- Manifold formation and crossings of ultracold lattice spinor atoms in the intermediate interaction regime
- Calibration tests beyond classification
- Machine learning accelerated particle-in-cell plasma simulations
- Chameleon: A Semi-AutoML framework targeting quick and scalable development and deployment of production-ready ML systems for SMEs
- Differentiate Everything with a Reversible Embeded Domain-Specific Language
- Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks
- Discovery of the Hidden State in Ionic Models Using a Domain-Specific Recurrent Neural Network
- SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning
- Minimizing Oracle-Structured Composite Functions