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.
Filter articles▼
Tag Filter: Experiments × cancel
▸Browse by Topics
Topics
Showing 15 of 15 articles
Archive 2018And here we are at the end of the year, along with the evaluation of our Toxic competition. Thank you for your significant involvement in AI development.
During the test, you tried nearly 1500 attempts. And roughly 100 times you disagreed with the statements of our detector. It must be said that sometimes you found it hard to believe,…
Read
Archive 2018By tomorrow (31.12.2018) you can compete to catch our detector of insults and toxic words
Tomorrow we will ceremoniously draw one of you to receive a few symbolic prizes. 😊 PS. Don't forget to leave your contact details (email, or perhaps a screenshot...)
Read
Archive 2018Astronaut Chats with a 'Smart Robot' on the ISS and No One is Excited
CIMON, the new crew member of the International Space Station (ISS), is starting to get accustomed to weightlessness. And his colleagues are learning how to talk to him. The robot…
Read
Archive 2018Artificial Intelligence Created at a Catholic School Dresses Naked Girls in Bikinis
Researchers from the Pontifical Catholic University of Rio de Janeiro have developed software that scans risqué photographs of women and overlays bikinis on intimate areas. The scientists presented the tool…
Read
Archive 2018Artificial Intelligence Has Learned to Tell Jokes. However, They Are Truly Awful Groaners!
Janelle Shane is reportedly one of the world's leading experts on artificial intelligence. She is currently trying to teach machines to joke. How is she doing…
Read
Archive 2018A Message for AI Developers: Recently, I needed to update some libraries in Python, and in the process, TensorFlow stopped working through the GPU.
I am currently tackling a task in NLP, where I teach a computer to recognise various types of insults, slurs, coarse expressions, etc. It's about 70 MB of text...
Read
Archive 2018I'm Trying to Teach a Computer to Translate from English to Czech
I found a sample of about 7000 sentences that are in both languages. I’ll tell it to go through them 100 times and try to understand the words. I’ll make it easier...
Read
Archive 2018A New Kind of AI – Augmented Random Search
Recently, a phenomenal topic has emerged among AI researchers. A new kind of AI has been invented! The algorithm is so simple that you don't need any complex framework like TensorFlow to implement it…
Read
Archive 2018Stanford Question Answering Dataset (SQuAD)
Today I found a real treasure! The Stanford Question Answering Dataset (SQuAD) is a new dataset consisting of questions posed by the audience on a selection of Wikipedia articles…
Read
Archive 2018AI Can Describe Photos!
I have just completed the most complex homework in AI that I have ever done. Creating and training a model that can generate text descriptions from photos!…
Read
Archive 2018Take a Selfie and AI Will Find Your Doppelgänger in Famous Galleries.
Artificial intelligence in action. Take a selfie, and Google will find your doppelgänger in famous galleries. When I tried it this morning, I had mixed feelings. I was…
Read
Archive 2018A Bouquet of Four Experiments with Recurrent Neural Networks
Do you also enjoy conducting experiments? Take a look at my bouquet of four experiments from yesterday's exploration with recurrent neural networks (based on a fantastic Russian school). …
Read
Archive 2018The Conclusion of the Trilogy on Autoencoders or Genesis 2.0 – Right up to the Creation of the First Humans
In the beginning, there was chaos and noise. Epoch One. And the great Generator said: Let there be light! And there was light. And the Discriminator saw the light, that it was good…
Read
Archive 2018The First Part of the Trilogy on the Use of Autoencoders – Noise Reduction
This time focusing on noise reduction. First, I will contaminate the entire dataset with a large amount of colour noise. I will compress this damaged image (to 512 digits) and then decompress it again. The excess noise was…
Read
Archive 2018What is an Autoencoder and How Does it Compress Data?
I continue my study of artificial intelligence in the 'Russian school'. It's a tough but good school. It took me 10 minutes to solve the autoencoder task with an error rate of 6.7%, but it took three days of experimentation to tame the error size down to 5%.
Read