Where Deep Learning Ends Deep Thinking Begins

Screening the Human Machine

We help people monitor, adapt and take decisions based on data and information. The ultimate goal is to help with early diagnosis and avoid the need for post-diagnosis treatments in the first place by actively collecting, transmitting, storing, and analysing personalised health information and producing continuous reports as an individual goes about daily life for detection of possible conditions based on the most recent research literature and knowledge about the immune system.

Research Leaders

The key to understanding and dealing with process complexity is simulation and monitoring. We have designed state-of-the-art methods to reprogram systems based on cutting-edge solid research. We have designed and implemented novel techniques for fast pre- and post-processing data to track essential information and provide decision-making with algorithmic analytics. Our techniques involve synthetic simulation, network modelling, dynamical systems, complexity indexes and algorithmic perturbation analysis, bridging research, science and industry. We are not only experts but pioneers and leaders in areas of machine and artificial intelligence and computational biology.

Human + Machine vs Disease

We aim at connecting academia and industry not only by way of introducing traditional tools from machine and deep learning in applications to achieve well-known super-human capabilities and results in areas such as classification but also by implementing completely new and more powerful approaches that current machine learning is unable to cope with, such as algorithmic inference finding ways to match processes to e.g. faults, like we do with biological markers for diseases. Based on solid research, a strong publication record, and a pioneering team, the technology developed, involved and translated is at the forefront of science. 

​Our technological pipeline involves performing massive in silico simulations that allow us to build a constant stream of artificial data that is tested against empirical observations to produce candidate generative models to be tested in a continuous model-data driven cycle. What is learned from both populations and individual cases is then used as knowledge and model-driven based solutions for detection and prediction.

---