Machine Learning for Edge Computing with ARM

This module provides an introduction to Artificial Intelligence, Machine Learning, and Edge ML fundamentals. Students will learn about core concepts and principles of these technologies and their applications in embedded systems.

This module explores essential machine learning components including datasets, data analysis, and algorithm training. Students will learn how to work with data and train machine learning algorithms using tools like Anaconda and Python.

This module covers the fundamentals of Artificial Neural Networks in constrained environments. Students will learn about neural network architecture, implementation, and optimization for embedded systems.

This module introduces Convolutional Neural Networks (CNN) and their applications. Students will learn about CNN architecture, deep learning principles, and implementation techniques.

This module focuses on implementing computer vision applications using CNNs. Students will learn how to deploy and optimize computer vision models using CMSIS-NN on microcontrollers.

This module addresses the challenges of deploying sophisticated machine learning models on resource-constrained microcontrollers. Students will learn various optimization techniques to reduce model size, computational requirements, and power consumption while maintaining acceptable accuracy. The module likely covers quantization, pruning, knowledge distillation, and efficient architecture design. Students may apply these techniques to optimize a machine learning model for deployment on the ST DISCO-L475E board using a dataset of their choice.