Distilling Knowledge via Intermediate Classifiers

This repository is for numerical experiments with convolutional neural networks, in particular for testing initialization procedures. The training data is the CIFAR10 dataset and the CNN-architecture is the FitNet-1 from ROMERO, Adriana, et al. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550, 2014.

Summer research June 2020- September 2020. This repository contains code for the model and machine learning for growth control.