Arseni Ivanov
M.Sc Computer Engineering
Computer Vision
Machine Learning
Edge AI
TinyML
Neuromorphic compute
About Me
My name is Arseni Ivanov, a 26-year-old M.Sc in Computer Engineering graduate from Lund University. I am passionate about compute, machine learning, cognition and cognitive neuroscience. I especially like the intersection of the brain and artificial neural networks, which I think will transform both compute and life sciences.
Outside of my academic pursuits, I enjoy working on personal projects, such as applying innovative methodologies to Spiking Neural Networks. My programming knowledge and industry experience have equipped me with the skills to plan and execute machine learning projects from start to finish. Currently, I work with Images and PIR signals, exploring and developing ways to differentiate them by the object of cause. This knowledge has potential applications in other fields, such as EEG-signal analysis, and I am eager to continue expanding my expertise in the realm of neuroscience and biomimicry.
When I'm not working on projects or deepening my understanding of the latest advancements in my field, I enjoy cooking, learning languages and dancing.
Projects
Quantization of Deep Neural Networks to facilitate self-correction of
weights on Phase Change Memory-based analog hardware
My paper on an alternative technique to handle weight drift on analog PCM hardware by binning the weights during training for the least amount of loss. Implemented in python using IBM's aihwkit.
Peer-to-Peer Augmented Reality Chess
Augmented reality chess written in C++ using OpenCV and Aruco library for plane estimation/camera motion, the frame is then ported as a texture into OpenGL for graphics rendering. The communication between the two players runs one each peers machine as a separate thread using a TCP network socket which decouples it from the graphics rendering.
Perfect eyebrows
Contract work for Brazilian website Della & Delle. Estimate perfect eyebrows for the user using standard beauty metrics developed by plastic surgerons in the 80s using facecam/photo. Created in dlib + OpenCV.