This is support code for the lecture "Introduction to TensorFlow for Deep Learning", from the Data Mining course (Computer Engineering, Sapienza University of Rome).
The presentation explaining the underlying concepts is in the course Syllabus.
The lab takes 2.0 hours and takes you through the design and optimisation of a neural network for recognising handwritten digits, from the simplest possible solution all the way to a recognition accuracy above 99%. It covers dense and convolutional networks, as well as techniques such as learning rate decay and dropout.
Installation instructions here. The short version is: install Python3, then pip3 install tensorflow and matplotlib.
The most advanced advanced neural network in this repo achieves 99.3% accuracy on the MNIST dataset (world best is 99.7%) and uses a Convolutional Neural Network..
Original version: "Tensorflow and deep learning - without a PhD"