I'm a Swiss researcher in Machine Learning and Artificial Intelligence, working at the intersection of dynamical systems, reservoir computing, self-supervised learning, and simulation-based inference.
My work combines theoretical and applied machine learning, scientific computing, and visual tools for research and education. I focus on models that are understandable, controllable, and grounded in physical or dynamical principles, with a strong commitment to free and open-source AI (FOSAI & FOSS).
- Reservoir Computing (RC) & Echo State Networks (ESN)
- Self-Supervised Learning (SSL): contrastive and regularized learning (JEPA)
- Physics-informed, neural operators for simulation-based inference (SBI)
- Visual computing & generative effects for arts and education
- Artificialis: a YouTube channel exploring artificial intelligence through code, mathematics, and critical thinking, without ignoring its philosophical, artistic, and social dimensions.
- EchoTorch: a Python toolkit for Reservoir Computing and Echo State Network experimentation built on top of PyTorch.
- Pixel Prism: a Python library for mathematical education with advanced visual effects and symbolic mathematics.
- Hyperion: an educational deep learning stack aimed at demystifying modern ML systems.
- DeckPilot – customizable Stream Deck interface for scripting and automation
- Tempest – CUDA-accelerated engine for full waveform inversion and scientific modeling
- boardGPT – lightweight experiments around training/fine-tuning GPT-like models on structured games and languages for AGI.
- PostDoc Researcher in Machine Learning & AI
- Experience across academia, applied research, and open-source development
- Strong background in Python, C++, CUDA, and scientific ML tooling
- my website
- X / Twitter: @nschaetti / @Artificialis1
- The Artificialis YouTube Channel