К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Getting Started with Machine Learning at the Edge on Arm · LearnSpace
Назад в каталог
courseraПрограммирование

Getting Started with Machine Learning at the Edge on Arm

Курс от Arm
Средний≈ 9.8 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

The age of machine learning has arrived! Arm technology is powering a new generation of connected devices with sophisticated sensors that can collect a vast range of environmental, spatial and audio/visual data. Typically this data is processed in the cloud using advanced machine learning tools that are enabling new applications reshaping the way we work, travel, live and play. To improve efficiency and performance, developers are now looking to analyze this data directly on the source device – usually a microcontroller (we call this ‘the Edge’). But with this approach comes the challenge of implementing machine learning on devices that have constrained computing resources. This is where our course can help! By enrolling in Machine Learning at the Edge on Arm: A Practical Introduction you’ll learn how to train machine learning models and implement them on industry relevant Arm-based microcontrollers. We’ll start your learning journey by taking you through the basics of artificial intelligence , machine learning and machine learning at the edge , and illustrate why businesses now need this technology to be available on connected devices. We’ll then introduce you to the concept of datasets and how to train algorithms using tools like Anaconda and Python. We'll then go on to explore advanced topics in machine learning such as artificial neural networks and computer vision. Along the way, our practical lab exercises will show you how you can address real-world design problems in deploying machine learning applications, such as speech and pattern recognition, as well as image processing, using actual sensor data obtained from the microcontroller. We'll also introduce you to the open source TensorFlow Python library, which is useful in the training and inference of deep neural networks. In the final module you’ll be able to apply what you’ve learned by implementing machine learning algorithms on a dataset of your choice. To be successful in the course, you should have an understanding of embedded systems, C language and Python. You will also need to purchase the ST DISCO-L475E development board used in the lab exercises of this course, which can be purchased directly from our technology partner STMicroelectronics: https://www.st.com/content/st_com/en/campaigns/educationalplatforms/iot-arm-edx-edu.html Through our vast ecosystem, Arm already powers a wide range of devices and applications that rely on machine learning at the edge. Be a part of this vibrant community of developers and start your machine learning journey by enrolling in our course today!

Навыки, которые вы освоите

Machine LearningConvolutional Neural NetworksTensorflowModel OptimizationFeature EngineeringArtificial Neural NetworksModel DeploymentData PreprocessingMachine Learning AlgorithmsComputer VisionArtificial Intelligence and Machine Learning (AI/ML)Data ProcessingEmbedded SoftwareImage AnalysisMachine Learning MethodsEmbedded SystemsDeep LearningApplied Machine LearningMicroarchitectureModel Training

Программа курса

6 модулей · 72 учебных материалов

01Module 1: An Overview of Machine Learning at the Edge8 материалов

Introductory Material

Welcome to the CourseЧтениеWelcome to Module 1ВидеоCourse OverviewЧтение

Knowledge Section

Introduce Artificial Intelligence, Machine Learning and Edge ML conceptsВидео

Учитесь у экспертов

Arm Education

Преподаватель курса

Getting Started with Machine Learning at the Edge on Arm
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 9.8 ч

6 модулей

Язык: Английский

Субтитры: Азербайджанский

Часть программы вашего университета
Assessment: Introduce Artificial Intelligence, Machine Learning and Edge ML conceptsЗадание
Explain the rise of Machine Learning at the Edge using constrained devices like micro-controllersВидео
Assessment: Explain the rise of Machine Learning at the Edge using constrained devices like micro-controllersЗадание

Closing Material

Module 1 Final AssessmentЗадание
02Module 2: Introduction to Machine Learning on Constrained Devices15 материалов

Introductory Material

Welcome to Module 2Видео

Knowledge Section

Identify the key features of machine learning as data scienceВидеоIdentify the key features of machine learning as data analysisЗаданиеOutline the feature extraction and the signal processing in the machine learning flowВидеоOutline the feature extraction and the signal processing in the machine learning flowЗаданиеOutline the feature extraction and the signal processing in the machine learning flowЗаданиеIllustrate the data sets, the training, and evaluation of Machine LearningВидеоIllustrate the data sets, the training, and evaluation of Machine LearningЗаданиеIdentify the constraints of machine learning on microcontrollersВидеоIdentify the constraints of machine learning on microcontrollersЗадание

Skills Section

Lab Project: Introduction to Machine Learning on Constrained DevicesЧтениеSV1 Lab Project: Introduction to Machine Learning on Constrained DevicesВидеоSV2 Lab Project: Introduction to Machine Learning on Constrained DevicesВидеоAssessment: Lab Project: Introduction to Machine Learning on Constrained DevicesЗадание

Closing Material

Module 2 Final AssessmentЗадание
03Module 3: Explain Artificial Neural Networks12 материалов

Introductory Material

Welcome to Module 3Видео

Knowledge Section

Explain Artificial Neural NetworksВидеоExplain Artificial Neural NetworksЗаданиеEvaluate the complexity of ANN and multi-layer perceptron in both training and inferenceВидеоEvaluate the complexity of ANN and multi-layer perceptron in both training and inferenceЗаданиеOutline the techniques to reduce complexity in particular QuantizationВидеоOutline the techniques to reduce complexity in particular QuantizationЗадание

Skills Section

Lab Project: Artificial Neural NetworksЧтениеSV1 Lab Project: Artificial Neural NetworksВидеоSV2 Lab Project: Artificial Neural NetworksВидеоAssessment: Lab Project: Artificial Neural NetworksЗадание

Closing Material

Module 3 Final AssessmentЗадание
04Module 4: Convolutional Neural Networks11 материалов

Introductory Material

Welcome to Module 4Видео

Knowledge Section

Explain Convolutional Neural Networks and deep learningВидеоAssessment: Explain Convolutional Neural Networks and deep learningЗаданиеIllustrate the audio processing with CNN with and without feature extractionsВидеоIllustrate the audio processing with CNN with and without feature extractionsЗаданиеOutline the different deep learning models and recent trends in the subjectВидеоOutline the different deep learning models and recent trends in the subjectЗадание

Skills Section

Lab Project: Convolutional Neural NetworksЧтениеSV1 Lab Project: Convolutional Neural NetworksВидеоAssessment: Lab Project: Convolutional Neural NetworksЗадание

Closing Material

Module 4 Final AssessmentЗадание
05Module 5: Computer Vision and Models11 материалов

Introductory Material

Welcome to Module 5Видео

Knowledge Section

Introduce the Arm CMSIS-NN libraryВидеоIntroduce the Arm CMSIS-NN libraryЗаданиеExplain image processing with CNN and other deep learning on Arm Cortex-M familyВидеоExplain image processing with CNN and other deep learning on Arm Cortex-M familyЗаданиеEvaluate the complexity of deep learningВидеоEvaluate the complexity of deep learningЗадание

Skills Section

SV1 Computer vision and modelsЧтениеSV1 Computer vision and modelsВидеоAssessment: Lab Project: Computer vision and modelsЗадание

Closing Material

Module 5 Final AssessmentЗадание
06Module 6: Optimizing Machine Learning on Constrained Devices15 материалов

Introductory Material

Welcome to Module 6Видео

Knowledge Section

Identify the constraints of the Arm Cortex-M family running deep learning. Evaluation of power consumption, latency, energy, memoryВидеоIdentify the constraints of the Arm Cortex-M family running deep learning. Evaluation of power consumption, latency, energy, memoryЗаданиеTiny machine learning optimization and quantizationВидеоTiny machine learning optimization and quantizationЗаданиеModel optimization and trade-offsВидеоModel optimization and trade-offsЗаданиеEvaluate and explain the floating-point vs fix-point implementationВидеоEvaluate and explain the floating-point vs fix-point implementationЗадание

Skills Section

SV1 Lab Project: Optimizing Machine Learning on constrained devicesЧтениеSV1 Lab Project: Optimizing Machine Learning on constrained devicesВидеоAssessment: Lab Project: Optimizing Machine Learning on constrained devicesЗадание

Closing Material

Module 6 Final AssessmentЗадание

Share your experience

Share your feedbackЧтениеCourse completion surveyPLUGIN