Andy BosyiA digital twin of terrain — 3D model from satellite imagesHypothesisDec 15, 2023Dec 15, 2023
Andy BosyiDocument Classification and Tagging with LLM and MLDocuments and databases can handle information, however, the difference is in the form. Documents and articles have unstructured but…Dec 15, 20232Dec 15, 20232
Andy BosyiChecking Document Outline with LLMLet’s solve the problem of an organization receiving multiple documents that should have the same information, but different formats, and…Dec 15, 20231Dec 15, 20231
Andy BosyiinTowards Data ScienceDifferentiable Programming — Inverse Graphics AutoEncoderLet’s consider handwritten character recognition using MNIST (EMNIST).Jul 26, 20191Jul 26, 20191
Andy BosyiinTowards Data ScienceActive Learning on MNIST — Saving on LabelingActive Learning is a semi-supervised technique that allows labeling less data by selecting the most important samples from the learning…Dec 18, 20181Dec 18, 20181
Andy BosyiinTowards Data ScienceVectorization of Raster to PolygonsI would never start writing any vectorization code if there was any free library. However, recently I was involved as a tech lead in an…May 11, 2018May 11, 2018
Andy BosyiinTowards Data ScienceThe Natural Ear for Digital Sound Processing — as an alternative to the Fourier TransformThis is a primitive prototype of the natural ear. Why I came to it and how it can be better than the Fast Fourier Transform (FFT) in…Jun 17, 2017Jun 17, 2017
Andy BosyiinTowards Data ScienceObject DetectionObject detection, especially recognition can be done using different technics, like a combination of OpenCV functions. For me, it was…Apr 1, 2017Apr 1, 2017