Hello friend!
About me
I’m a 28 y.o. the woman from Kazakhstan. As a bachelor’s degree, I finished Kazakhstan Department of Moscow State University named after M.V.Lomonosov, Mathematics faculty with an honor degree. At the end of my bachelor’s degree, I met a topic related to Data Science and completed the first course of Data Science in the Russian language. That was the point where my relationships with Data Science started. I passed exams by winning the Olympiad to HSE University to Computer Science faculty to Master’s Data Science (DS) program. I am fond of courses of theoretical and provable parts of DS because it correlates with my Bachelor’s degree. I learned a lot of applications and last researched approaches to complex data (such as graphs). While my education at HSE I started my first job as a Researcher at the IITP RAS lab “Data analysis in neurosciences”. It combined my two passions: computer science and neuroscience. My academic experience included participation in the MICСAI conference with poster and oral speech. You can find my papers in the Publication chapter. However, I liked the experience of growing my hard skills, so I started my first commercial job at Constanta. I wanted to develop my skill in the area of Computer Vision and the task I worked with at Constanta included real-time video segmentation and recognition, tracking and detection. I have had a great experience and learnt a lot of practical skills (hard and soft). My path led me to a startup called Halbestunde. It is an app that helps junior musicians to read notes and detect mistakes in their play. As far as it is a startup I had to make a lot of management and infrastructural work: settings for git-flow, setting for work-flow, defining the technical task, etc. Startups have their aesthetics, yet I wanted to see what it is like to work in a big company. While my interview processes and test tasks I had experience not only with computer vision tasks but with audio. I joined the Department of smart voice assistant Marusya at VK company.
About my projects
- Commercial projects
- Automatic systems for cybersports: Segmentation and OCR of information in-game
- Automatic tracking, detection and recognition of players in physical basketball
- Audio classification of noisy and denoising (Neurolab test task)
- Notes recognition: from photos, pdfs, etc
- Classification of ID cards (test task for Revolut, got an offer)
- Detection of mistakes in audio with reference
- Endpoint detector in phrases to the fast replay of voice assistant
- Academic
- Optimization of parameters for LDDMM registration model task base:
- Straight forward approach
- Template approach
- Diffeomorphical Transformer (like Spatial Transformer Network)
- Optimization of parameters for LDDMM registration model task base:
Skills
Python, PyTorch, PyCharm, Docker, Make, Bash, DVC, Hydra, HDFS, etc. see my CV