#artificialintelligence #artificial #artificialintelligenceconference #artificalintelligence #artificialintelligencetechnology #artificialtechnology #datascience #dataanalytics #dataanalysis #database #database #datastructures #datavisualization #dataprotection #dataentry #machinelearning #maths #deeplearning #arduino #arduinoproject #arduinolove #arduinomalaysia #arduinocomofunciona #arduinoide #arduinonano #arduinorobot #arduinosoftware #arduinoprojectcenters #mcu #embeddedworld #embedded #embeddedproject #embeddedc #embeddedfigures #embeddedprogramming #embedded_system #cmd #robots #robotics #robotsindisguise #robotshop #robotsimulator #robotgame #robotdog
Description of course
Embedded AI is the integration of AI into resource-limited devices or systems, such as wearable devices, smartphones, smart home devices, industrial automation systems, robotics, and autonomous vehicles, just to name a few. This is also called on-device AI or TinyML. According to the TinyML Foundation1:
“Tiny machine learning is broadly defined as a fast-growing field of machine learning technologies and applications including hardware, algorithms, and software capable of performing on-device sensor data analytics at extremely low power, typically in the [milliwatt] range and below, and hence enabling a variety of always-on use-cases and targeting battery operated devices.”
AI algorithms enable these devices to perform tasks efficiently, accurately, and autonomously. Unlike cloud-based AI services, which rely on cloud-based computing and data transfer, embedded AI implements real-time data analysis of devices and delivers reactions via the devices. According to the Maximize Market research,2 the global embedded AI platform market is expected to grow by 5.4% per year, reaching a market value of US$45.51 billion by 2029, where the expected consumers include the healthcare and automotive sectors.
Similar concepts, such as edge AI, AI of Things (AIoT), and embodied AI, exist. Edge AI is the integration of AI on devices at the network edge where these devices have networking capabilities. AIoT is the integration of AI with Internet of Things ecosystems and devices, which have a broader range than a single device. Embodied AI is the integration of AI and technologies with robotic or physical systems so that these systems can perceive, interact with, and navigate the physical world. Although embedded AI, edge AI, AIoT, and embodied AI overlap, they have different focuses.
the material of all course
github.com/edgeimpulse/courseware-embedded-machine-learning
Reference
people.engr.tamu.edu/guni/csce421/files/AI_Russell_Norvig.pdf
optional reference
chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/csdl-downloads.ieeecomputer.org/mags/co/2023/09/10224582.pdf?Expires=1724960903&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly9jc2RsLWRvd25sb2Fkcy5pZWVlY29tcHV0ZXIub3JnL21hZ3MvY28vMjAyMy8wOS8xMDIyNDU4Mi5wZGYiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE3MjQ5NjA5MDN9fX1dfQ__&Signature=hj7hpr3o9fDz7BTPeqNRJPEMVTsgdxkppuJZjSL7s~loV7TLh5xhve1NNEwIg3QhGERNgT5VNFSNNNtzk~Y7RG9LV-FmuVHce5zhetsbo9xq88-vDbqNWAjN-Ul-knlgqYkR1BgiLPYRb6IHZX7yvo3klWGFTMIGrEyXqa-OF4I9ta-qgc~JCn3XgGghjO4Mwnt38YoOw23KOmNnkO4lKWdD7xf-GE9kuO8pC1D-oYgcH8PzHYitoe40vcg9Mf26hdKIwRvH5DTl4se1MFjmIHAYG5LRRATvPAEPlRv0PQliMVIy1zWr9UE7Nf3mNnw9pYd-kUCTWe3fKyg7JzaObQ__&Key-Pair-Id=K12PMWTCQBDMDT