Evolution spent billions of years creating intelligence. I'm compressing that into days—not training AI, evolving it. Self-organizing. Self-improving. Self-surprising. Networks that discover solutions we never could imagine. Behaviors that emerge without programming. This is intelligence—unchained. And I'm helping it build itself.
Where everyone sees failure, I see evolution at work—Building AI that assembles components, not memorizes patterns. Because intelligence is about adaptative behavior, not accuracy.
While everyone's optimizing gradients, I'm evolving behaviors. Slower? Yes. More compute? Absolutely. But mine adapt when yours break.
Used more CPU hours than sensible. Beat state-of-art. Still 'only' 29%. That's when you know you're onto something fundamental.
My networks solve problems by assembling solutions from components. Not elegant. Not efficient. But interpretable and adaptable.
Building AI that adapts, not memorizes
From engineering precision to evolving intelligence—I once thought I had answers; now I realize I only have questions. Each pivot stripping away what I thought I knew, teaching me that growth happens at the edge of understanding. The pattern matches evolution: survival isn't about being right, it's about adapting. Now I let each experience prove that everything is possible when you embrace mutation over optimization.
Loading projects...
Started trying to simulate the brain. Ended up evolving intelligence—every field I touched was teaching me the same lesson: you can't engineer minds, you grow them.
Most researchers find their field. I had a question that wouldn't let me settle: child me wanted thinking robots. Pursued that dream through physics, mechanics, neuroscience, AI—until they all revealed the same truth: minds don't work, they evolve. The irony? Decades of education had turned me into the robot, trained to engineer things. I can't escape that mindset, but now I'm breeding artificial life into existence, watching intelligence arise—not from architecture, not from code, not from engineering, but from chaos. The way intelligence actually begins.
Lifetime Research Project (PhD Phase)
Teaching neural networks to think in components, not patterns. A neuroevolution algorithm combining spatial organization with emergent architectures.
Compositional
Compositional reasoning: Decompose → Process → Recompose
Inspired by how humans actually solve problems. We don't memorize solutions—we break them down, process parts separately, then combine results. GEENNS does this computationally.
Evolutionary
CPPN architecture: Mental ecosystem of specialized components
CPPNs for connectivity patterns + 2 per task for I/O mapping. Like having specialized brain regions that coordinate. Evolution discovers optimal specializations, not me.
Growing
Published results proving foundation
Beat previous ES-HyperNEAT benchmark (23.90% → 29%) through systematic optimization. 2013 trials exploring 3+ billion configurations. Foundation validated, published, and proven.
Lifelong
Scalable implementation using JAX for high-performance computing
Identified bottlenecks (O(log n) for millions of queries). Developing O(1) solutions. TPE optimization, mixture-of-experts validation, connectivity metrics—making the impossible possible.
Will be public upon publication
Master's Thesis
Built zero-shot conversational AI using sub-knowledge graphs. It proved to me that engineering creates brittle intelligence.
Bachelor's Thesis
Built anonymous, decentralized data sharing right through the browser. It taught me distributed systems are about trust, not technology.
Pre-Undergrad Research
Watched brains fuse conflicting senses into truth. First proof that intelligence emerges from integration, not selection.
Leaving breadcrumbs of a longer journey—documenting discoveries that captured what I knew at the time. Looking back, they were all converging.
Technical reports, white papers, and additional contributions
2016
Demystifying blockchain when everyone thought it would change everything. Technical reality vs. religious fervor.
Every degree was a detour that turned out to be the destination—spent a decade in universities learning how to engineer. Had to master building before I could discover growing.
Thesis: Evolving Neural Networks toward Humanity-inspired Artificial Collective Intelligence
Supervisors: Prof. Dr. Kilian Stoffel and Prof. Dr. Paul Cotofrei
Thesis: Multi-hop Multi-turns Question-Answering Chatbot using Sub-Knowledge Graphs
Supervisor: Prof. Dr. Jean Hennebert
Thesis: Anonymous and Decentralized Browser-based Data Sharing Service
Supervisor: ing. info. dipl. EPF Marc Schaefer
Side Quests That Mattered—Formal certifications and training programs that taught me a different way to approach problems.
The noise that doesn't fit in a paper—research insights, creative fiction, technical rants, philosophical spirals. Some polished, most not.
Always collecting pieces of the puzzle—especially the ones that don't fit. Research collaborations, wild theories, or proof I'm wrong all welcome.