Patterns, not programs
Instead of hard-coding rules, ML fits functions to examples and generalizes to new data.
A calm, modern space for exploring machine learning, bioinformatics, and cancer biology — with room for playful curiosity.
Studying Bioinformatics at Universität Potsdam · I love ML.
Instead of hard-coding rules, ML fits functions to examples and generalizes to new data.
Split wisely; tune on validation; keep a clean test set. Reliable evaluation beats lucky results.
Too simple misses patterns; too complex memorizes noise. The sweet spot generalizes best.
From raw reads to tidy tables: QC → alignment → quantification → normalization → interpretation.
Understanding shared characteristics like uncontrolled proliferation and evasion of growth suppressors.
Investigating mutations, copy number variations, and epigenetic modifications driving cancer development.
Developing treatments that block specific molecular pathways crucial for cancer cell survival and growth.
From foundation models to self-supervised learning, ML continues to push boundaries across various domains.
Quantum ideas (like superposition and entanglement) inspire models that may help with small, high-dimensional data. Hardware is early, but the playground is exciting.
I’m studying Bioinformatics at Universität Potsdam and I love machine learning. This site shares approachable ideas and small demos without overwhelming detail.
Say hello: contact@eltonugbogu.com