Swim ESPTM is a streaming data analytics engine that applies machine learning in real-time, taking advantage of a distributed learning architecture to gain efficiency, ensure security and high availability, and to permit rapid and reliable dissemination of learned insights. Swim ESP is self-training and operates in real-time, training and learning continually from data streams.
Swim takes advantage of the price & performance benefits of Moore’s Law to deliver an affordable, easy to use, secure, and fault tolerant computational fabric that facilitates real-time decision making that naturally and efficiently aggregates and publishes relevant data to higher-order applications and services:
- A digital twin of each real-world object learns from contextually relevant data streams, simplifying the learning problem.
- By learning on devices, rather than the cloud, Swim enables revolutionary autonomous control decisions that are appropriate for robotics systems, aircraft, drones and other self-controlling vehicles, and other real-time control systems.
- Swim edge learning is self-training. Its algorithms continually check their hypotheses against real world data, training and adjusting for over fitting as needed. This avoids the need for machine learning experts in the field.
- Learned insights are available in real-time and in context, to permit smart, real-time control decisions.
- Swim runs on commodity edge hardware: Swim can learn as much on a device that costs $50 at the edge, as a solution costing $1000/month in the cloud.
- Swim uses learning to self-configure, self-secure and manage, reducing cost and complexity.
- Swim is secure by design, providing a guaranteed chain of custody for all data, and hardware security with auto-patching.
Learn how Swim ESP for Autonomous Vehicles implements Machine Learning at the edge to enable Swim Swarm to transform sensor data generated by UAVs from low-value data into low-overhead, high value insights capable of informing fast-timescale decisions by UAVs.