Overview
Embedded artificial intelligence (AI) will enable new, inexpensive, and low power AI solutions that are not possible using cloud-based AI technologies alone. The edge AI chip market is growing much faster than the overall chip market, with the number of edge AI chips to be sold in 2024 estimated to be 1.5 billion. Embedded AI requires knowledge and skills beyond traditional embedded systems, data science, and machine learning (ML). It requires knowledge of devices, sensors, and advanced, near real-time signal processing methods for video, audio, motion, or other signals. Specialized software tools and frameworks are required to develop embedded AI applications.
This program provides the knowledge and skills required to take advantage of this next major shift in technologies and the related growth in job demand. The program explores the specialized tools, frameworks, technologies, platforms, and methods used to create exciting new embedded AI devices. Study TinyML – the field of applying ML technologies to embed AI in resource-constrained devices. Discover how complex embedded AI applications work on smartphones, drones, and other devices that have constrained processing, memory, power, and other resources. Investigate the signal processing methods and ML models behind important applications that process video, audio, motion, and other signals. Explore how ML frameworks are used to create these applications and use these with embedded AI hardware in hands-on projects. Learn how to choose the right hardware, development tools, and software components for an application. Examine the tradeoffs needed to make decisions about the mix of AI processing that needs to be done on the device and in the cloud. Apply what you have learned and use cutting-edge devices, sensors, signal processing, TinyML methods, and embedded ML frameworks to create an embedded AI device.
Who Should Enroll
This program is ideal for those who wish to learn about the field of embedded AI, acquire the specialized skills needed to create embedded AI solutions, explore new uses, solve problems using constrained edge devices, gain competitive business advantage, and expand career options. The curriculum is designed for embedded systems professionals, software engineers, electrical engineers, computer engineers, computer scientists, data scientists, data engineers, and machine learning scientists.