I am a data scientist and machine learning engineer that comes from project management and software development background. What I really like to do is study languages, as of 2021 I speak six of them (yes, all fluently), so no wonder that NLP (natural language processing) is one of my professional interests. You can see some of my work in the Data Science section of the site.

Another thing that fascinates me is visual arts, like for example Chinese brush calligraphy, and from here comes my interest in application of CNN (convolutional neural networks) and GAN (generative adversarial networks) to computer vision and art generation respectively. Two projects I have in the pipeline now are an automated calligraphy teacher and machine creation of original calligraphy artwork.

Last but not least, the bulk of my experience as project manager lies within financial industry and regulated markets. I implemented over fifteen large transformation programs for such companies as lululemon, Deutsche Bank, Scotiabank, General Electric and PokerStars, of which you can read on my Project Management page.

My latest projects:

WordAlign

Word alignment for Russian-Chinese bitext using BERT contextualized embeddings and further fine-tuning on unique parallel corpus

SwiftPredict

Ngram text prediction model for mobile keyboards that can be trained from scratch on a laptop, occupies only 219 MB RAM and provides suggestions within 22 msec

Ships detection in satellite imagery

96.77% F1 score score detecting ships in satellite imagery with imbalanced classes, using transfer learning with VGG16 and Inception v3 CNNs