3. TinyML is a branch of machine learning and embedded systems
research that looks into the types of models that can be run on
small, low-power devices like microcontrollers
TinyML
Prepare data Train model
(80% data)
Validate model
(20% data)
Deploy model Inference at
the Edge (MCU)
Tests pass
Tests fails
With AutoML tools, it can't get simpler
4. Edge Impulse is the edge AI platform for enterprise teams building
innovative products. Optimize your models and deploy to any edge device
with ease. Accelerate product development while minimizing risks
TinyML project in 5 minutes
edgeimpulse.com
Faster developments
Automate model deployments
5. Define your problem
01
Setup your hardware (collects
data and/or deployment
02
Test your model
05
Deploy your model to a
microcontroller
06
Create dataset
03
Train your model
04
Celebrate!
07
Complete project flow
edgeimpulse.com
8. edgeimpulse.com
Edge Impulse
documentation on how to
setup Arduino Nano 33
BLE Sense
Respond to your voice
Keyword spotting
documentation
Scan me!
Link here
Scan me!
Link here
Public Edge Impulse
project
GitHub repository
Scan me!
Link here
Scan me!
Link here