__ __ __ /'\_/`\ __ /\ \ /\ \ /\ \ /\ \/\_\ _ __\ \ \/'\ ___ \ \ \ __\ \ \___ ___ \ \ \__\ \/\ \/\`'__\ \ , < / __`\ \ \ \ __ /'__`\ \ _ `\ /' _ `\ \ \ \_/\ \ \ \ \ \/ \ \ \\`\ /\ \L\ \ \ \ \L\ \/\ __/\ \ \ \ \/\ \/\ \ \ \_\\ \_\ \_\ \_\ \ \_\ \_\ \____/ \ \____/\ \____\\ \_\ \_\ \_\ \_\ \/_/ \/_/\/_/\/_/ \/_/\/_/\/___/ \/___/ \/____/ \/_/\/_/\/_/\/_/

Start Scrolling . . .

Hi, i’m a computer vision and AI enthusiast with a passion for exploring both the impressive strengths and the amusing weaknesses of intelligent systems. I recently completed my studies in computer science; I’m married and a proud father of two. I enjoy synth music, pen & paper role-playing, and the collectible card game "Magic: The Gathering".

During my final year I contributed to a research project on AI-assisted automated weed control in grassland. The goal is to reduce the need for herbicides by using deep learning to detect invasive plants and then remove them in an environmentally friendly way. My work focused on creating training data — from real field images to synthetic data and generative methods — and on training and evaluating neural networks for reliable plant detection. In my thesis, I developed a pre-trained deep learning model that can be fine-tuned to various target plants using few-shot learning based on general grassland knowledge.

to the KIhUG Project --- download my Thesis here

• Android App for mushroom classification GitHub
• Retro dxBall game - A.I. autoplay GitHub
• Puzzlebox solver - Brute Force GitHub

Reach me at lehn.mirko@gmail.com