Published in Towards Data Science·Pinned5 Tips How to Bring Value to an AI Project Without Being a Data ScientistData Science Survival Guide for Non-Technical Colleagues — Compared to my previous articles, which were highly technical and meant mainly for fellow data scientists, I have this time decided to write an article aimed towards other team roles, that are often present in data science projects and we as data scientists cooperate with. Whether you are a product…Data Science7 min readData Science7 min read
Published in Towards Data Science·PinnedHow Many Neurons Should Your Neural Network Have?Systematically Tuning Your Model by Looking at Bias and Variance — As data scientists, we often face a lot of decisions when building a model, such as which model to use, how big it should be, how much data is needed, how many features to add or whether to use or not use regularization. …Machine Learning4 min readMachine Learning4 min read
Published in Towards AI·Feb 17, 2021How to Make a Model with Textual Input Benefit From User’s AgeEnriching Sequential LSTM Model with Non-Sequential Features — Sequence data can be found in various fields and use cases of Machine Learning, such as Time Series Forecasting, Bioinformatics, Speech Recognition, or Natural Language Processing. …Feature Engineering4 min readFeature Engineering4 min read
Published in Towards Data Science·Nov 21, 20201 to 5 Star Ratings — Classification or Regression?Finding out with an experiment. — Predicting a star rating (or any score rating in general) is a common task, often used in NLP to extract user feedback from open-text reviews without reading them, or in recommender systems to predict what rating would a user give to a movie he has never seen. The rating itself…Classification3 min readClassification3 min read
Published in Towards Data Science·Nov 11, 2020How to Label Training Data More EffectivelySaving Time and Effort With Active Learning — If you‘ve ever taken part in any machine learning project starting from scratch, you probably know that a significant amount of time is usually spent on labelling the data. The number and quality of labeled data often determines the next course of the project, as well as its final outcome. …Data Science5 min readData Science5 min read
Published in Towards Data Science·Oct 21, 2020Zero-Shot Learning the Alphabetic CharactersIs it possible to recognise alphabetic characters, which have not been provided during training? — In this article, I would like to explain and practically demonstrate an area of machine learning called zero-shot learning, which I find really fascinating. Let’s start with a little description of what it actually is: Zero-shot learning is a method of recognising categories, which have not been observed during training.Data Science5 min readData Science5 min read
