MLE School 2022 - Material for Hands-On III

Introduction to artificial neural networks: classifying handwritten numbers using Python and Tensorflow/Keras.

The goal of this workshop is to provide an insight into deep learning on the use case of detecting handwritten numbers. After an introduction to the basics of neural networks, a workflow for machine learning tasks is solved in groups. Therefore, Jupyter notebooks are provided to guide the course through ANN development with Tensorflow/Keras. Finally, the trained networks will be applied for the detection and recognition of handwritten text on images.

Getting started

To participate, a Laptop with an installation of Anaconda is the most useful choice. So please install it according to the instructions on their website.

Alternatively, a participation in Google Colab is possible.

COLAB Engl.

COLAB Germ.

For local participation, download the material from Github or opening a Terminal (Anaconda Promt on Windows) and copy the material via Git.

git clone https://github.com/BenBol/MLE-School.git

Navigate in the folder

cd MLE-School

and create a new environment

conda env create -f environment.yaml

or for an Apple Silicon Mac

conda env create -f environment_M1_Mac.yaml

Use the following command to activate the workshop environment.

conda activate MLE-Hands-On-III

Finally start jupyter notebook for participating in the excercise.

jupyter notebook

Removing the data

After the course, the environment can be deleted with

conda remove --name MLE-Hands-on-III  --all
conda clean --all