I'm Johann Schmidt
I'm a Scientist.
I'm a Researcher.
I'm a Developer.
Welcome
based in Magdeburg, Germany.
Get in contactAbout Me
Let me introduce myself
I'm Johann Schmidt, PhD Student in Deep Learning
I work in the AILab of the Otto-von-Guericke University in Magdeburg, Germany as a researcher, where my daily business are deep neural network. My research focuses on fortifying these networks against vulnerabilities caused by variances in the input.
Take, for instance, an image classifier. It will break if issued with a rotated replicate of the training data. I develop solutions using the immense power of group theory. Join me on my quest to make neural nets exponentially more powerful and stable.
- Name:Johann Schmidt
- Email:johann.schmidt@ovgu.de
- Born:1995
- From:Magdeburg, Germany
10+
Years Coding Experience
30+
Students Supervised
100+
Sessions Moderated
7
Papers Published
Career
Resume
Education
2007 - 2014
A Levels
Privatgymnasium Tangermünde, Germany
During this shaping period, my fascination with electrical circuits, programming and math emerged, igniting a passion that continues to fuel my academic and professional pursuits.
2014 - 2018
Bachelor: Electrical Engineering
University of applied Science Magdeburg-Stendal, Germany
Although adept at designing electrical circuits, my true passion was unveiled in computer science - breathing life into these circuits.
Bachelor Thesis
Institut for Automation and Communication (ifak) e.V. Magdeburg, Germany
I developed a GUI for a clamp-on ultrasonic sensor system on an embedded controller in C, as well as analysed and evaluated the overall measurement system.
2018 - 2020
Master: Digital Engineering
Otto-von-Guericke University Magdeburg, Germany
I delved into advanced computer science courses, dedicating countless hours to self-study to bridge gaps in my knowledge. It was within the realm of deep learning that I found my niche—a domain where I finally felt at home.
Master Thesis
Fraunhofer Institute for Factory Operation and Automation IFF Magdeburg, Germany
I developed and integrated a vision-based human action recognition deep learning model for human-machine interaction in an industrial environment.
2020 - today
PhD in Deep Learning
Otto-von-Guericke University Magdeburg, Germany
I cultivated a robust expertise in deep learning, immersing myself in diverse research domains. I mentored students, refined scientific writing through conference publications, delivered presentations, and adeptly facilitated and guided small groups, cementing both theoretical and practical facets of the field.
PhD Thesis
AILab, Otto-von-Guericke University Magdeburg, Germany
I invent algorithms to efficiently search the Affine Group and canonicalize input signals of Deep Neural Networks boosting their stability when issued with out-of-distribution data.
Experience
2013 - 2016
Internships and Student Jobs
TCS AG Genthin, Bachmann GmbH Magdeburg, Enercon GmbH Magdeburg
I first came in touch with the development and assembling of electrical circuit boards. I analysed and evaluated of wind turbine data and helped with cabling of control cabinets of wind turbines.
2020 - 2022
SENECA
BMBF-funded Project
During this BMBF-funded project we supported a regional semi-conductor company (Tectron Worbis GmbH) by developing an AI to tackle an NP-hard scheduling problem.
2022 - 2022
AI-Engineering
BMBF-funded Project
We created a novel Bachelors study program teaching the theories of artificial engineering intertwined with practical applications in several engineering disciplines (hands-on and student-centred with OERs).
2022 - today
PASCAL
BMBF-funded Project
Currently, we are lifting traffic control to the 21st century by developing an AI-based traffic signal control system using real-time V2X data.
Papers
Publications
2021
Human Action Recognition as part of a Natural Machine Operation Framework
S. Bexten, J. Schmidt, C. Walter, and N. Elkmann
IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)
2021
NeuroEvolution of augmenting topologies for solving a two-stage hybrid flow shop
S. Lang, T. Reggelin, J. Schmidt, M. Müller, and A. Nahhas
Expert Systems with Applications
2021
Approaching Scheduling Problems via a Deep Hybrid Greedy Model and Supervised Learning
J. Schmidt and S. Stober
IFAC Symposium on Information Control Problems in Manufacturing
2023
Learning Continuous Rotation Canonicalization with Radial Beam Sampling
J. Schmidt and S. Stober
ArXiv
2024
Reviving Simulated Annealing: Lifting its Degeneracies for Real-Time Job Scheduling
J. Schmidt, B. Köhler, H. Borstell
The Hawaii International Conference on System Sciences (HICSS)
2024
Pursuing the Perfect Projection: A Projection Pursuit Framework for Deep Learning
J. Perschewski, J. Schmidt, S. Stober
International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM+)
2024
Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers
J. Schmidt and S. Stober
International Conference on Machine Learning (ICML)
2024
Image Canonicalisation in Log-Polar Space
J. Schmidt, S. Stober and others
Draft Phase
Coding
Languages
Fluent in German (native) and English (daily use), I seamlessly navigate international professional environments. My linguistic repertoire extends to multiple programming languages, acquired throughout my career. This diverse language skill set, both human and computer, enables me to adapt quickly to various technical challenges and communicate effectively across disciplines.
since 2020
Prototyping with Python
During my Master's program, I was introduced to Python, which quickly became an invaluable tool in my programming arsenal. Its intuitive syntax and extensive libraries allow me to quickly implement and test concepts, making it an ideal language for experimental work. I primarily leverage Python for rapid prototyping, especially when working on publications or exploring new ideas. While I have utilized Python's just-in-time (JIT) compilation to enhance performance in certain scenarios, I would still prefer to turn to low-level languages like C or C++ when speed is a critical factor.
2014-2018
Efficiency with C/C++ and Assembler
I self-taught C programming from Dirk Louis's book, meticulously coding every example to build a solid foundation from the ground up. During my Bachelor's, I solidified my knowledge by taking courses in Assembler, C, C++, and Software Engineering. This academic pursuit culminated in a project where I programmed a Rubik's Cube solver in C++, showcasing my ability to apply complex algorithms and problem-solving skills in a practical context.
2014-2021
App and Game Dev with C# and Java
Similar to C/C++ I self-taught Java from a book by Hans-Peter Habelitz. My primary motivation was to develop Android applications, leveraging Java's widespread use in mobile development. My exploration extended to mobile game development, where I challenged myself to create an Android game using C# and Unity (apps can be found on GitHub). While I found the experience engaging and instructive, I ultimately decided to refocus my efforts on areas more aligned with my long-term career goals.
since 2018
Web Dev with HTML, JS and many more
I possess fundamental skills in HTML and CSS, and have published several small games using JavaScript. My experience extends to working with Jekyll, Hexo, NodeJS, and Flask. Additionally, I supervised a web development project utilizing NextJS with a MySQL backend, Tailwind CSS, and Shibboleth SAML SSO, demonstrating my ability to manage complex, full-stack web applications.
since 2016
Unix-based Shells and Linux
I have been working with Unix-based systems since my Bachelor's degree, developing a solid foundation in shell interactions and command-line operations. My experience includes working with various Linux distributions, which has broadened my understanding of different environments. I've applied these skills in practical scenarios, such as running experiments on GPU clusters through remote connections, demonstrating my ability to utilize computing resources for research purposes.
Work Address
Otto-von-Guericke University, Universitätsplatz 2, Magdeburg, Germany
Institute of Intelligent and Cooperating Systems
Artificial Intelligence Lab, G29-022
johann.schmidt@ovgu.de