Educational implementation of neuroevolutionary SANE-algorithm Designed to Adjust the Weight Parameters of a Single-Layer Feedforward Neural Network.
Project was made within course of Neuroevolutionary Computing in Tomsk Polytechnic University.
For working of algorithm and neural net model:
- numpy=1.16.4
- matplotlib=3.1.0
- scikit-learn=0.23.2
- Training single-layer network using SANE-algorithm
- Visualisation of training metrics
- Saving the best models of models
- Logging metric values in the learning process, saving hyperparameter values
SANE can be used to evolve single-layer feedforward neural network that consists of a single hidden
layer.
Used algorithm can be found in this paper.
- Install required packages.
- You can use train.py to train model.