Blog
The Oldest AI Blog in the Czech Republic
We have been writing about artificial intelligence since 2017. 1000+ articles, thousands of pages of thoughts, experiments, and reflections. No sensationalism, no ads.
Tag Filter: algorithm × cancel
▸Browse by Topics
Topics
Showing 10 of 10 articles
Archive 2021How to Run 30 Machine Learning Models with Just a Few Lines of Code?
Sometimes it is difficult, or at least time-consuming, to choose the right algorithm for your task and dataset. Thanks to libraries like scikit-learn, we can create models…
Read
Archive 2021Learning Under Supervision (Semi-Supervised Learning)
Traditional machine learning (ML) divides the universe into algorithms that learn with a teacher (‘supervised learning’) and without a teacher (‘unsupervised learning’), but as is often the case…
Read
Archive 2019Karen Hao analysed nearly 17,000 studies on artificial intelligence and wrote an article on where he believes AI is heading
• The biggest shift was the transition from expert systems (knowledge-based systems) to machine learning in the early 2000s. The word “logic” is increasingly less used in research…
Read
Archive 2019New AI Clones Your Voice from Just 5 Seconds of Audio Recording!
New research introduces us to AI that converts text to speech (TTS). The algorithm is traditionally based on a neural network. Upon closer inspection, it consists of 3 main components…
Read
Archive 2019Artificial Intelligence Can Make Scientific Discoveries!
In the July issue of Nature, you will read about how scientists from the American Lawrence Berkeley National Laboratory used a simple Word2Vec algorithm to analyse a large number of...
Read
Archive 20193 libraries that will help you interpret your model
A dry definition tells us that model interpretability is the ability to approve and interpret the decisions of a predictive model, allowing for transparency in the decision-making process. Simply put...
Read
Archive 2019The Third Year of the Data Science Olympics!
So, what do you think of the latest Olympics? In case anyone missed it, at the end of May, the third year of the Data Science Olympics took place...
Read
Archive 2019I bring bad news. We have improved the Czech and English emotion detector!
We have modernised the algorithms, so you can now see which words the neural network places greater weight on (the AI attention button in the bottom right). We also used much larger and more diverse datasets for training...
Read
Archive 2019The End of Politicians' Lies? Artificial Intelligence Will Soon Be Able to Verify Their Statements in Real Time
Scientists from Duke University have created a tool that could find application, for instance, in the American presidential elections in 2020. It should be able to...
Read
Archive 2018A New Challenge!
Recently, an interesting competition took place on Kaggle (https://www.kaggle.com/c/jigsaw-toxic-comment-classificatio…) to create a detector capable of recognising insults, toxic and obscene remarks, and so forth – the Toxic Comment Classification Challenge….
Read