process-intelligence-research/ReLU_ANN_MILP
With this package, you can generate mixed-integer linear programming (MIP) models of trained artificial neural networks (ANNs) using the rectified linear unit (ReLU) activation function. At the moment, only TensorFlow sequential models are supported. Interfaces to either the Pyomo or Gurobi modeling environments are offered.
This tool helps researchers and engineers who work with optimization problems. It takes a pre-trained TensorFlow neural network that uses ReLU activation functions and converts it into a mixed-integer linear programming (MILP) model. This allows you to embed the complex behavior of your neural network directly into larger optimization problems, providing a structured way to find optimal solutions.
No commits in the last 6 months.
Use this if you need to incorporate the decision-making or functional approximation of a trained ReLU neural network into a larger mathematical optimization model.
Not ideal if you need to train neural networks or are looking for a tool to solve general non-linear optimization problems directly without neural network embedding.
Stars
64
Forks
6
Language
Python
License
MIT
Category
Last pushed
Aug 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/process-intelligence-research/ReLU_ANN_MILP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.