Boosting research with machine learning.

How Python supports the application of machine learning in specialist sciences.

Franziska Oschmann

Case Study Data Science Deep Learning Machine-Learning

See in schedule Download Slides

Within the last 20 years machine learning (ML) experienced a boost in its impact on our daily lives. With the help of supervised and unsupervised methods tasks like computer vision, recognition of speech or text have been revolutionized. Due to this high impact of ML ongoing research focuses on the constant improvement of these methods.
However, ML is not exclusively the subject of research, but can also be used as a tool for the investigation of research questions. For example, ML is used to uncover hidden patterns in experimental data not detectable with neither the human eye nor standard statistical methods or to train machines so that they can take over repetitive tasks like object recognition. The increasing usage of ML in research is also due to Python libraries such as keras or scikit-learn. These libraries have simplified the handling of ML methods and thus paved the way for the application of these methods in many different research fields.
This talk is intended to present examples for current applications of ML in research. These use cases deal with the automatic recognition of single neurons throughout a stack of histological images or the prediction of human arm movements based on EEG signals. Based on these use cases an overview of Python-based techniques for data preparation and data analysis applying different techniques ranging from standard ML methods to state-of-the-art implementations of deep neural networks will be given.

Type: Talk (30 mins); Python level: Beginner; Domain level: Beginner


Franziska Oschmann

Scientific IT Services, ETH Zürich

I am data scientist with an interest in tackling real world problems by applying theoretical models. After finishing my studies in Neuroscience I absolved a PhD in Computational Neuroscience where I investigated the generation of non-neuronal signals with the help of computational modeling. After finishing my PhD I started working as a data scientist at the Scientific IT Services at ETH and support scientists in the application of machine learning for their research projects.