Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
TinyML with Wio Terminal
Role Play
Rating: 2.8 out of 5(5 ratings)
3,117 students

TinyML with Wio Terminal

Deploy machine learning models on embedded systems using Wio Terminal and TinyML for real-time, offline inference.
Role Play
Created byEducational Engineering Team, Educational Engineering, Ashraf Said AlMadhoun
Last updated 2/2026
English
English [Auto],

What you'll learn

  • This course is designed to teach you how to use TinyML
  • The course will teach you how to collect data from sensors, control robots and 3D printers, and analyze data
  • Learn the basics of machine learning with TinyML
  • You will also learn how to visualize your data with Wio Terminal
  • You'll be able to handle a variety of datasets in order to improve your predictive skills
  • You'll also learn about neural networks, matrix operations, decision trees, and more
  • Learn the fundamentals of making predictions with supervised and un
  • Improve your analytical skills by working on real world datasets built by professionals
  • TinyML will help you decide faster, easier and more accurately than ever before.

Course content

5 sections • 31 lectures • 2h 59m total length

  • Section Intro0:58
  • Introduction12:25

    Learn how tinyml enables on-device learning on the Wio Terminal, using deep learning on microcontrollers, and train and deploy models with Edge Impulse and TensorFlow Lite for Microcontrollers.

  • Exploring TinyML with Wio Terminal
  • Project 1 Recognizing Gestures With Light Sensor Theory And Data Colle5:14

    Train and deploy a simple neural network to classify rock-paper-scissors gestures with a single light sensor, covering data collection, Edge Impulse workflow, and underfitting and overfitting.

  • Code0:08
  • Lesson 1 Practical13:57

    Set up the tinyml workflow on the Wio Terminal by installing the Arduino IDE, configuring board manager, and loading the necessary boards. Optional TensorFlow with Conda enables local model experiments.

  • Gesture Recognition with Light Sensors
  • Project 1 Recognizing Gesture With Light Sensor Model Training And Depl9:20

    Train a lightweight gesture recognition model using a light sensor with edge impulse, learning data collection, cleaning, pre-processing, and a simple fully connected network, then deploy to Arduino for inference.

  • Lesson 1 Practical Continue13:40

    Connect to the edge impulse platform on a Wio Terminal, sign up, and build your first machine learning model with guided data acquisition and sampling.

  • Practical0:08
  • Project II Classifying Hand Gesture With Accelerometer Theory And Data6:09

    Classify hand gestures with a three axis accelerometer and machine learning, collecting labeled data via Arduino IDE and the Edge Impulse dashboard for robust gesture recognition.

  • Project II Classifying Hand Gesture With Accelerometer Model Training A10:53

    Train a neural network on accelerometer data using windowed spectral analysis and butterworth filtering to extract spectral features, classifying three gestures including idle and shake, for on-device deployment.

  • Recognizing and Classifying Gestures Using Sensors
  • Project III Audio Scene Recognition With Microphone Theory And Data Col9:10

    Explore audio scene recognition using microphone theory and data collection, train and deploy an edge impulse classifier, and learn Fourier transforms, spectrograms, cepstral coefficients, and the Mel scale.

  • Project III Audio scene Recognition with Microphone Model and Training10:17

    Develop audio scene recognition on the Wio Terminal by training a compact convolutional neural network using mel frequency energy features, deploying inference with DMA and ADC on embedded hardware.

  • Project IV People Counting With Ultrasonic sensor Theory and Data Colle5:23

    Count people with ultrasonic sensors on the Wio Terminal by theory and data collection, measuring distance with pulse-echo and storing data in Azure IoT Central for cloud visualization.

  • Project IV People Counting With Ultrasonic Sensor Model Training and De14:36

    Train an ultrasonic sensor based people counting model, comparing convolutional and fully connected layers, use pooling to reduce compute, and deploy with continuous inference on the Wio Terminal.

  • Understanding Audio Scene Recognition and People Counting Models
  • Project V Intelligent Meteostation With BME280 Theory and Data Collect5:55

    Build an intelligent meteostation with the BME280 and TensorFlow for microcontrollers to predict weather and precipitation for the next 24 hours using a multi-output convolutional neural network and Chorus API.

  • Project V Intelligent Meteostation With BME280 Model Training and Depl6:48

    Train and deploy a BME280-based meteostation on the Wio Terminal using TensorFlow Lite for Microcontrollers, with 8-bit quantization and a two-output weather model.

  • Student Project5:57

    Explore student-led tinyml projects using Edge Impulse and TensorFlow Lite for microcontrollers, from water sensors and keyword detection to offline EKG analysis and fall detection, inspiring hands-on invention.

  • Understanding Weather Monitoring with BME280 and Project Development
  • Exploring Gesture Recognition and Sensor-Based Projects
  • Summary0:25
  • Reading Material0:28

Requirements

  • You need to buy the Wio Terminal if you want to apply the practical experiments
  • No prior coding experience needed
  • Hardware (board, modules)
  • Arduino IDE
  • willingness to learn
  • No prior knowledge required
  • Software(possible platform or language)

Description

This course focuses on practical deployment of machine learning models on edge devices using Wio Terminal and TinyML. You will learn how to prepare data, train compact models, convert them into efficient formats, and deploy them on low-power microcontrollers for fast, offline decision-making.

The course is structured to help engineers, developers, and students create intelligent embedded systems without requiring cloud connectivity.

What is TinyML? TinyML refers to machine learning models that are optimized to run on low-power, small-footprint devices like MCUs. TinyML is cost-effective, allowing more individuals to train their models. Compatible with Arduino, Raspberry Pi, and other IoT devices, TinyML is the only platform that lets you know when you're making a mistake.

What is Wio Terminal? Wio Terminal is a device that makes it easy to interface with sensors and other hardware. It's a desktop application for quickly publishing your site without needing any knowledge of programming languages. You'll learn the basics of creating websites and interfacing with hardware.

Key Concepts Covered

  • Introduction to TinyML and Wio Terminal hardware architecture

  • Collecting and preprocessing data for embedded model training

  • Model training using TensorFlow Lite

  • Converting and quantizing models for microcontroller deployment

  • Uploading models to the Wio Terminal and running inferences

  • Optimizing performance for real-time response

  • Implementing use cases such as gesture recognition, sound classification, or anomaly detection

What You’ll Build

  • A fully working TinyML inference system on Wio Terminal

  • A data collection pipeline tailored for embedded hardware

  • A real-time sensor-based ML project (e.g., motion classification or sound response)

  • Model loading and activation code in Arduino-compatible environment

Try It Now! Get started with the Wio Terminal course and save time by identifying the best possible option every time!

Target Audience

  • Embedded developers entering machine learning

  • Engineers interested in edge computing

  • Students and researchers working on smart devices

  • Makers with an interest in low-power AI

  • Professionals seeking to implement ML without relying on the cloud

Prerequisites

  • Basic Python programming

  • Familiarity with Arduino IDE and embedded hardware

  • Access to a Wio Terminal

  • Installation of Arduino libraries and TensorFlow Lite environment (guided in the course)

Course Outcomes

  • Create TinyML applications that run efficiently on Wio Terminal

  • Understand the workflow from model training to deployment

  • Implement lightweight models using TensorFlow Lite Micro

  • Integrate ML inference into real-world sensing applications

  • Work with onboard sensors like accelerometer, microphone, and display

What’s Included

  • Step-by-step video tutorials

  • Source code, libraries, and model files

  • Downloadable datasets and templates

  • Full documentation for reproducibility

  • Certificate of Completion

Instructor Bio

The Educational Engineering Team, with over 250,000 enrolled learners, specializes in applied microcontroller training. Led by Ashraf, the team provides clear, practical instruction in embedded systems, automation, and applied AI. Their experience with Wio Terminal and TinyML allows them to deliver direct-to-device machine learning deployment strategies.

Start Deploying Machine Learning at the Edge

Use TinyML and Wio Terminal to develop efficient, real-time AI solutions that operate without cloud dependency. Build embedded intelligence using industry-standard tools.

Enroll Now – Apply TinyML on Wio Terminal

Who this course is for:

  • This course is designed for beginners who want to learn more about machine learning.
  • The course is designed for anyone who would like to learn some basic programming skills.
  • This course is perfect for anyone wanting to get started in Machine Learning!
  • It is also good for people who want to get more out of their smartphone by taking advantage of things they plug into their computer.

Report abuse