All stories

Does Adding One Neuron Help Real World Networks?

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 Hoskovec22/07/18

How to automatically read data from invoices using Rossum API: an example with Google Drive

Please note that this example is not relevant anymore. Our research programmer, Roman Sushkov, recently posted a neat example of how to use Rossum’s Data Extraction API in practice. We think

Roman Sushkov18/07/18

Why did we start Rossum?

Hear from Rossum’s Co-founder and Chief AI Architect Petr Baudis about our motivation behind the Rossum technology.

Petr Baudis13/07/18

The Future of Data Capture Systems (2/2): The Rossum Approach

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 Gogar10/07/18

The Future of Data Capture Systems (1/2): Imitating Human Behavior

Data capture for invoices ought to have been solved a long time ago! That’s what most people think, especially if they’ve never tried to actually do it. That’s what we

Petr Baudis22/06/18

Building Our Own Version of AlphaGo Zero

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 Baudis19/11/17

Towards Efficient Multi-GPU Training in Keras with TensorFlow

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 Zamecnik26/10/17

Data Hackathon at our Prague Lab

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 Baudis28/06/17

Rossum’s Training Data

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 Baudis26/06/17

The Rossum blog

View all

Does Adding One Neuron Help Real World Networks?

How to automatically read data from invoices using Rossum API: an example with Google Drive

Why did we start Rossum?

The Future of Data Capture Systems (2/2): The Rossum Approach

The Future of Data Capture Systems (1/2): Imitating Human Behavior

Building Our Own Version of AlphaGo Zero

Towards Efficient Multi-GPU Training in Keras with TensorFlow

Data Hackathon at our Prague Lab

Rossum’s Training Data

Platform

Must Read

Resources

Company

Document Types

Compare