LearnViz CompSci
Home / Learn / Mobile, Embedded & IoT / Edge AI and TinyML

Advanced Topic 36 of 50 Mobile, Embedded & IoT

Edge AI and TinyML

Running machine learning on tiny devices.

How it works

Edge AI runs machine-learning inference on devices instead of the cloud, and TinyML targets microcontrollers with kilobytes of memory and milliwatts of power. Models are shrunk using quantization to 8-bit integers, pruning, knowledge distillation and efficient architectures such as MobileNet, then converted to formats such as TensorFlow Lite for Microcontrollers, ONNX or Edge Impulse deployments, and executed with optimized kernels or accelerators such as NPUs. Typical models do keyword spotting, anomaly detection, gesture recognition and visual wake words.

Where it is used

Always-on voice triggers, predictive maintenance on vibration sensors, wearables, smart cameras and agricultural monitoring use on-device inference to save bandwidth, preserve privacy and cut latency.

Common pitfall

Accuracy drops with quantization and small models, and the memory and compute budgets are tight. Training data must match deployed sensor conditions or accuracy collapses. Model updates in the field need infrastructure. Profile latency and energy on the target hardware, use representative data and monitor drift.

Where it fits in the course

Edge AI and TinyML is topic 36 of 50 in Mobile, Embedded & IoT, rated Advanced. It follows Edge Computing. The next topic is Embedded Linux.

Practice and explore

How to study this topic

  1. Read the explanation above and restate the definition in your own words.
  2. Open the interactive lesson and answer its mini quiz.
  3. Read the common pitfall, then write a short example that avoids it.
  4. Check your understanding in the Mobile, Embedded & IoT quiz, and revisit the topic if you miss a question.

Frequently asked questions

What is Edge AI and TinyML?
Running machine learning on tiny devices. It belongs to Mobile, Embedded & IoT and is an advanced-level topic.
Where do people use Edge AI and TinyML?
Always-on voice triggers, predictive maintenance on vibration sensors, wearables, smart cameras and agricultural monitoring use on-device inference to save bandwidth, preserve privacy and cut latency.
What is the most common mistake with Edge AI and TinyML?
Accuracy drops with quantization and small models, and the memory and compute budgets are tight.
What should I learn before this topic?
Start with Edge Computing, the topic just before it in Mobile, Embedded & IoT.
How can I practice it?
Answer the mini quiz in the interactive lesson, then take the Mobile, Embedded & IoT quiz.
Is Edge AI and TinyML hard to learn?
It is an Advanced topic. Expect to read the explanation more than once and to connect it with earlier topics. Working through a small example by hand helps most.
How long does it take to learn Edge AI and TinyML?
Most learners can read the explanation and finish the interactive lesson in under an hour. Fluency comes from applying the idea, so plan a few short practice sessions with the quiz.
Which topics are related to Edge AI and TinyML?
Edge Computing, Embedded Linux, Zigbee and LoRa are closely connected. The full list is in the related topics section of this page.
What should I study after Edge AI and TinyML?
Continue with Embedded Linux, the next topic in Mobile, Embedded & IoT.

Related topics