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: Computer Vision and Image × cancel
▸Browse by Topics
Topics
Showing 24 of 104 articles
Archive 2019Auto-Keras and AutoML
Google introduces Neural Architecture Search, abbreviated as NAS. NAS is essentially an algorithm that searches for the most optimal neural network to perform a specific task for your particular dataset.
Read
Archive 2018Intel this week unveiled the Neural Compute Stick 2 with VPU (Vision Processing Unit) for artificial intelligence
The Intel NCS 2 is suitable for testing deep neural networks, tuning them, and creating prototypes of the resulting devices. As you can see in the photo, it offers…
Read
Archive 2018Google Mocks Failed Photos. It Won't Happen to Them!
Anyone with a keen interest in mobile phones has likely noticed that Google is poking fun at Apple's iPhone in its campaigns this year. This time, it's a practical matter – how to avoid failed photos. The phone takes numerous shots, and AI selects the best one. This puts an end to unflattering grimaces.
Read
Archive 2018Are You Interested in How a Neural Network Works?
Its foundation is deep learning, which is why image recognition, chatbots, self-driving cars, and machine translation work! In this video, the amazing...
Read
Archive 2018Do You Like the Future?
Then you surely noticed the Future Port Prague 2018 on 6th-7th September https://www.futureportprague.com/. There were not only a number of Czech and foreign lectures on artificial intelligence. We also enjoyed several high-tech gadgets to try out. Here are a few exclusive photos fresh from the event :)
Read
Archive 2018Difficult to Distinguish Images
You may have encountered how neural networks learn to understand images. Using convolutional networks, transfer learning, autoencoders, and other algorithms, it is now possible to achieve remarkable results...
Read
Archive 2018Artificial Intelligence Will Not Transform Most Industries in the Foreseeable Future
According to Gartner's Vice President of Research, Alexander Linden, artificial intelligence will not significantly transform most industries in the foreseeable future. However, he expects AI to contribute significantly to...
Read
Archive 2018Artificial Intelligence is Already Part of the Curriculum in China
Did you know that Artificial Intelligence is already part of the curriculum in China? South China Morning writes about it. It is stated that there is even a high school textbook titled 'Foundations of Artificial Intelligence', with the main author being Tang Xiaoou, the chairman of SenseTime (the world's most valuable AI startup).
Read
Archive 2018Babelnet
I am currently studying NLP (natural language processing), which is the computational processing of natural language. It is a field that lies at the intersection of linguistics, computer science, and particularly artificial intelligence. For me…
Read
Archive 2018The 2nd Year of the Fair for Senior Programmers is Here!
The 2nd Year of the Fair for Senior Programmers is here! A brief introduction to artificial intelligence cannot be missed :) https://www.jobsdev.cz/ Live broadcast: https://youtu.be/08mg3Vgm604
Read
Archive 2018Still waiting
Those who have experienced the difference between CPU and GPU will understand :)
Read
Archive 2018Deep learning – winter is leaving
For AI enthusiasts, I have prepared another presentation. This time on the topic: Deep learning – winter is leaving. Come and take a look to unveil the secrets of AI magic. You can register here…
Read
Archive 2018Sequence Models
Ta dá! I have the fifth and final certificate in Deep Learning from Andrew NG himself – Sequence Modelling :) The great thing is that I managed to do it among...
Read
Archive 2018New Intro Photo
What do you think?
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 2018My First Diploma from the Tough Russian School!
And it’s done. My first diploma from the National Research University Higher School of Economics, which I affectionately refer to as the 'Russian School'. In half the time and…
Read
Archive 2018At Least 45 Startups Are Working on Chip Development for AI
There is now no doubt that artificial intelligence is the 'next big thing', promising the creation of a large and valuable market. It is no wonder then,…
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 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 2018The Second Part of the Trilogy on Autoencoders – Morphing and Finding Similar Images
This time, we aim to find the most similar image in the dataset. Simply encode a face into a matrix of a few numbers. Then, you look at which matrix of encoded numbers…
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
Archive 2018Advanced Machine Learning at the National Research University Higher School of Economics
I am currently studying advanced machine learning at the National Research University Higher School of Economics, which is a top Russian university for economics and ranks among...
Read