Projekty - Krzysztof Sopyła

Note to Polish readers, I’m sorry but all of my projects and tutorials are in English.

Goodwrite.pl – intelligent writing assistant for Polish
CoDoCzytania.pl – personal book advisor based on your mood.
https://bookscout.ai/ – AI-based service that pinpoints the best-matching content from around the world for book publishers

My best github repo:

awesome-nlp-polish – A curated list of resources dedicated to Natural Language Processing (NLP) in polish. Models, tools, datasets.
Pytorch neural networks tutorial – This repository contains easy to follow Pytorch tutorial for beginners and intermediate students. The goal is to introduce you to Pytorch on practical examples.
MNIST digit classification with scikit-learn and Support Vector Machine (SVM) algorithm – Project presents the well-known problem of MNIST handwritten digit classification. For the purpose of this tutorial, I will use Support Vector Machine (SVM) algorithm with raw pixel features. The solution is written in python with use of scikit-learn easy to use machine learning library.
Tensorflow MNIST Convolutional Network Tutorial – Neural nets for MNIST classification, simple single layer NN, 5 layer FC NN and convolutional neural networks with different architectures
Pandas+Seaborn tutorial on World bank GDP data for central and eastern Europe – Project analysis the gross domestic product (GDP) data for 10 central and eastern European countries. The analysis was prepared based on the World Bank Data, particularly the dataset World Development Indicators was utilized. This set contains many economic development indicators you can choose from.

Some of my projects:

Python Primal SVM – This project is python port of Matlab Primal SVM – fast linear SVM implementation by Olivier Chapelle http://olivier.chapelle.cc/primal/
pyKMLib – Python SVM with CUDA(GPU) support – multiclass CUDA SVM solver for sparse problems. KMLib child project.
KMLib – Kernel Machine Library with GPU SVM solver in .Net