Paul Foster
Talk: The future of deep learning is 8-bit: Building smart sensors
Using optimisation techniques, machine learning models can now run on small microcontrollers, enabling raw sensor data to be turned into actionable insights locally.
This technology is the perfect partner to LoRaWAN sensors, enabling just the event metadata to be transmitted.
Workshop: Building Smart Sensors – ML on MCU
Attendees will:
- Assemble a Gesture Pod which recognises movement gestures from MPU data
- Understand how to capture new gesture data, process it, and generate a new gesture model (there are follow-up steps to be completed post workshop)
Attendees will need to complete the pre-workshop steps documented here. and download the git repository from here.
About Paul
Since joining Microsoft in 1994, Paul Foster has worked across a wide range of sectors and customers, providing a mix of technical and strategic guidance around the creative use of technology in relation to their business needs.
Paul is currently a senior software engineer at Microsoft. Paul is currently focusing on the building of next generation sensor webs which automate the gathering of data from disparate sources, and how to enable the creative analysis of this data to start a new era of perception.
He is the initiator of The Things Network Norfolk community group. For a short-time Paul was a member of a high-wire flying trapeze circus troupe, is a keen roboticist and an international marathon runner.