Machine Learning

See also Course material, Other LABS, Course projects


9. Artificial Neural Networks

PART I: First play with the google play groud to better understand what the Artificial Neural Networks can do.

PART II: Prediction of a categorical variable with 2 levels

We have collected gene expression levels for 4654 genes on 97 early-stage breast cancer samples. After surgical removal of the tumour, some unfortunately relapsed within 5 years (label=+1), while other did not (label=0).
The goal of the lab in to improve prediction of relapse given gene expressions using neural networks.

1. Fit a neural network model on the most predictive genes (or on PCA).
2. Try different architectures.
3. Compare the models using ROC curves.

Codes: CancerRelapse_ANN.R, CancerRelapse_ANN.py,