Machine Learning

AI for log processing, cybersecurtiy and journalism ↓
Machine Learning

Machine Learning research in our center covers a number of topics and domains. We focus on ML in the field of log analysis and also explore its various applications in cybersecurity and journalism.

AI for Log Processing

A research cluster aroun Jan Drchal develops methods similar to those used in Natural Language Processing, but instead of human spoken languages, our focus on log messages. Our main interest lies in transforming them into forms appropriate for downstream ML tasks, i.e., log embeddings.

The results are highly applicable in many areas. We can help administrators understand the logs better by smart visualizations of the messages based on their clustering. We work on methods of log anomaly detection with Red Hat. We also develop log-based systems for the prediction of manufacturing process durations for Škoda Auto a.s.

AI in Journalism

AI in Journalism

What does the future of journalism look like with the introduction of artificial intelligence? Automatic generation of reports, verification of facts, search for articles confirming or refuting claims. These and other topics are explored by our researchers in the new TAČR project.

Research Results

Neural Power Unit

Neural Power Unit

In this paper accepted to NeurIPS 2020, we introduce the Neural Power Unit (NPU) that allows better extrapolation and helps to build more transparent models.

Hacking
human future