Peeking into the Neural Network Black Box
If you have ever come in touch with neural networks, you are probably familiar with the black box problem [1, 2]. Compared to many other algorithms from the glass box
Go to the content | Go to main menu
Show tags
If you have ever come in touch with neural networks, you are probably familiar with the black box problem [1, 2]. Compared to many other algorithms from the glass box
Antonin HoskovecDecember 6, 2018
In tensorflow, there are many usable features for tasks besides just for learning. One worth mentioning is the function for rendering framed rects for given boundingboxes that can be used
Martin HolecekNovember 28, 2018
Our researcher, Tonda Hoskovec, has long been thinking about the behavior of neural network training in the case of non-convex tasks with many local minima. This makes training difficult or
Antonin HoskovecJuly 22, 2018
This is the second part of our special founders blog post on data capture technology and how Rossum represents a radically different approach to the whole problem of information extraction
Tomas GogarJuly 10, 2018
At Rossum, we are building artificial intelligence for understanding of documents. Our main line of attack lies in supervised machine learning, the most efficient approach to make neural networks achieve
Petr BaudisNovember 19, 2017
At Rossum, we are training large neural network models daily on powerful GPU servers and making this process quick and efficient is becoming a priority for us. We expected to
Bohumir ZamecnikOctober 26, 2017
At Rossum, we just talked about how critical data is for machine learning and for us specifically. At the same time, we’d like to think we are doing some pretty
Petr BaudisJune 28, 2017
Every Machine Learning project needs training data, gathering this training data is pivotal for the project success and for many challenging problems, it’s not a simple matter either. Well, Rossum’s
Petr BaudisJune 26, 2017