Fleet Intelligence

We work on the intersection of machine learning and distributed computing to build a new class of intelligent systems.

Hero Image
logo Cambridge.png
logo sibb.png
logo ki-verband.png
logo Oxford.png
logo aric.png
logo nvidia.png
logo kosmos.png
logo betterhr.png
logo claimsforce.svg
logo gaiax.png
logo ucl.png
logo ai-hamburg.png
logo agyleos.svg
logo agrigaia.png
logo Cambridge.png
logo sibb.png
logo ki-verband.png
logo Oxford.png
logo aric.png
logo nvidia.png
logo kosmos.png
logo betterhr.png
logo claimsforce.svg
logo gaiax.png
logo ucl.png
logo ai-hamburg.png
logo agyleos.svg
logo agrigaia.png

Industry Solutions

Predictive Maintenance

Companies train a shared predictive maintenance model for manufacturing machines using federated learning. Data stays private, only the learnings are shared to improve prediction quality and avoid cold-start challenges.

Chatbot

Chatbots can be trained across different user groups to improve response quality without disclosing individual conversations. Sensitive topics, such as HR-related questions, remain private but quality improves with every interaction.

Agriculture

Different agricultural machines use video and images to identify weed growth or water supply. Each machine processes this data offline due to limited internet availability, the learnings are then shared when farm Wi-Fi is available again.

USV

Unmanned Surface Vehicles are programmable water drones that can be equipped with different types of sensors for live data collection. The collected data can be used to monitor, for example, temperature, depth, or wildlife.

Healthcare

Healthcare data is naturally sensitive and distributed across many institutions. The only way to derive useful insights is to use the data where it is, without the need to centralize it beforehand.

Automotive

Gathering high-quality datasets for autonomous or assisted driving poses many challenges. Fleet learning approaches select rare high-value data samples without the need to collect vast amounts of low-value data beforehand.

Opportunities

We are building a world class team. If you're an exceptionally talented software engineer or machine learning researcher, we'd like to hear from you: Careers

For all other enquiries: Contact