Name: Tobias Sterbak
Type: User
Bio: Data Scientist, Mathematician, Machine Learning Engineer, Open Source developer
Twitter: tobias_sterbak
Location: Berlin, Germany
Blog: https://tobiassterbak.com
Tobias Sterbak's Projects
An awesome README template to jumpstart your projects!
Python code for the post "Computing Homology"
Free, open source data set describing McDonalds Nutrition Facts for popular menu items in SQL, SQLite, JSON, Excel, OpenOffice Spreadsheet, Google Sheets, TSV, etc. Updated November 2015. :hamburger: :fries: :cookie: :cake:
Demo-Webseite der 29 Projekte der 10. Förderrunde des Prototype Funds.
A repository just to host comments for the blog.
Curated list of open-access/open-source/off-the-shelf resources and tools developed with a particular focus on German
GitPitch In 60 Seconds - A Very Short Tutorial
Keras community contributions
Contains an implementation of the attention mechanism and a keras text classifier wrapper.
Simple test time augmentation (TTA) for keras python library.
Scikit-learn compatible Kernel Entropy Component Analysis in Python
Just a phone app.
Scikit-learn compatible Locality Preserving Projections in Python
Here I post some code about and for machine learning
Documentation that simply works
Open source platform for the machine learning lifecycle
Contains notebooks and requirements for a workshop on NLP and Topic Modeling in 2022.
Particle Gibbs for Bayesian Additive Regression Trees
simplifies the process of creating and managing LLM workflows as a self-hosted solution.
Contains the slides and additional resources to my talk about explaining blackbox text classifiers at PyData2018 in Amsterdam
This repository contains the slides to my talk
This Repository contains the material for my tutorial "Managing the end-to-end machine learning lifecycle with MLFlow" at pyData/pyCon Berlin 2019.
This Repository contains the material for the tutorial "Introduction to MLOps with MLflow" held at pyData/pyCon Berlin 2022.
PyMTL (Python library for Multi-task learning) is a Python module implementing a Multi-task learning framework built on top of scikit-learn, SciPy and NumPy.
Extreme Learning Machine implementation in Python
Why Random Ferns? Because 10 lines of code [1].