Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/lanl-ansi/mathoptai.jl
Embed trained machine learning predictors in JuMP
https://github.com/lanl-ansi/mathoptai.jl
artificial-intelligence jump-jl machine-learning neural-networks optimization
Last synced: 13 days ago
JSON representation
Embed trained machine learning predictors in JuMP
- Host: GitHub
- URL: https://github.com/lanl-ansi/mathoptai.jl
- Owner: lanl-ansi
- License: other
- Created: 2024-05-06T23:54:07.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-11-07T01:03:22.000Z (3 months ago)
- Last Synced: 2025-01-03T01:50:12.278Z (20 days ago)
- Topics: artificial-intelligence, jump-jl, machine-learning, neural-networks, optimization
- Language: Julia
- Homepage: https://lanl-ansi.github.io/MathOptAI.jl/
- Size: 1.49 MB
- Stars: 42
- Watchers: 7
- Forks: 1
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# MathOptAI.jl
[](https://github.com/lanl-ansi/MathOptAI.jl/actions?query=workflow%3ACI)
[](https://codecov.io/gh/lanl-ansi/MathOptAI.jl)
MathOptAI.jl is a [JuMP](https://jump.dev) extension for embedding trained AI,
machine learning, and statistical learning models into a JuMP optimization
model.
## License
MathOptAI.jl is provided under a BSD-3 license as part of the Optimization and
Machine Learning Toolbox project, O4806.
See [LICENSE.md](https://github.com/lanl-ansi/MathOptAI.jl/blob/main/LICENSE.md)
for details.
_Despite the name similarity, this project is not affiliated with
[OMLT](https://github.com/cog-imperial/OMLT), the Optimization and Machine
Learning Toolkit._
## Installation
Install `MathOptAI.jl` using the Julia package manager:
```julia
import Pkg
Pkg.add("MathOptAI")
```
## Getting started
Here's an example of using MathOptAI to embed a trained neural network from Flux
into a JuMP model. The vector of JuMP variables `x` is fed as input to the
neural network. The output `y` is a vector of JuMP variables that represents the
output layer of the neural network. The `formulation` object stores the
additional variables and constraints that were added to `model`.
```julia
julia> using JuMP, MathOptAI, Flux
julia> predictor = Flux.Chain(
Flux.Dense(28^2 => 32, Flux.sigmoid),
Flux.Dense(32 => 10),
Flux.softmax,
);
julia> #= Train the Flux model. Code not shown for simplicity =#
julia> model = JuMP.Model();
julia> JuMP.@variable(model, 0 <= x[1:28^2] <= 1);
julia> y, formulation = MathOptAI.add_predictor(model, predictor, x);
julia> y
10-element Vector{VariableRef}:
moai_SoftMax[1]
moai_SoftMax[2]
moai_SoftMax[3]
moai_SoftMax[4]
moai_SoftMax[5]
moai_SoftMax[6]
moai_SoftMax[7]
moai_SoftMax[8]
moai_SoftMax[9]
moai_SoftMax[10]
```
## Documentation
Documentation is available at
[https://lanl-ansi.github.io/MathOptAI.jl](https://lanl-ansi.github.io/MathOptAI.jl).
## Getting help
For help, questions, comments, and suggestions, please [open a GitHub issue](https://github.com/lanl-ansi/MathOptAI.jl/issues/new).
## Inspiration
This project is mainly inspired by two existing projects:
* [OMLT](https://github.com/cog-imperial/OMLT)
* [gurobi-machinelearning](https://github.com/Gurobi/gurobi-machinelearning)
Other works, from which we took less inspiration, include:
* [JANOS](https://github.com/INFORMSJoC/2020.1023)
* [MeLOn](https://git.rwth-aachen.de/avt-svt/public/MeLOn)
* [ENTMOOT](https://github.com/cog-imperial/entmoot)
* [reluMIP](https://github.com/process-intelligence-research/ReLU_ANN_MILP)
* [OptiCL](https://github.com/hwiberg/OptiCL)
* [PySCIPOpt-ML](https://github.com/Opt-Mucca/PySCIPOpt-ML)
The 2024 paper of López-Flores et al. is an excellent summary of the state of
the field at the time that we started development of MathOptAI.
> López-Flores, F.J., Ramírez-Márquez, C., Ponce-Ortega J.M. (2024). Process
> Systems Engineering Tools for Optimization of Trained Machine Learning Models:
> Comparative and Perspective. _Industrial & Engineering Chemistry Research_,
> 63(32), 13966-13979. DOI: [10.1021/acs.iecr.4c00632](https://pubs.acs.org/doi/abs/10.1021/acs.iecr.4c00632)