Introduction to On-Device AI
Offered By: DeepLearning.AI via Coursera
Course Description
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
As AI moves beyond the cloud, on-device inference is rapidly expanding to smartphones, IoT devices, robots, AR/VR headsets, and more. Billions of mobile and other edge devices are ready to run optimized AI models.
This course equips you with key skills to deploy AI on device:
1. Explore how deploying models on device reduces latency, enhances efficiency, and preserves privacy.
2. Go through key concepts of on-device deployment such as neural network graph capture, on-device compilation, and hardware acceleration.
3. Convert pretrained models from PyTorch and TensorFlow for on-device compatibility.
4. Deploy a real-time image segmentation model on device with just a few lines of code.
5. Test your model performance and validate numerical accuracy when deploying to on-device environments
6. Quantize and make your model up to 4x faster and 4x smaller for higher on-device performance.
7. See a demonstration of the steps for integrating the model into a functioning Android app.
Learn from Krishna Sridhar, Senior Director of Engineering at Qualcomm, who has played a pivotal role in deploying over 1,000 models on devices and, with his team, has created the infrastructure used by over 100,000 applications.
By learning these techniques, you’ll be positioned to develop and deploy AI to billions of devices and optimize your complex models to run efficiently on the edge.
Syllabus
- Untitled Module
- As AI moves beyond the cloud, on-device inference is rapidly expanding to smartphones, IoT devices, robots, AR/VR headsets, and more. Billions of mobile and other edge devices are ready to run optimized AI models. This course equips you with key skills to deploy AI on device: 1. Explore how deploying models on device reduces latency, enhances efficiency, and preserves privacy. 2. Go through key concepts of on-device deployment such as neural network graph capture, on-device compilation, and hardware acceleration. 3. Convert pretrained models from PyTorch and TensorFlow for on-device compatibility. 4. Deploy a real-time image segmentation model on device with just a few lines of code. 5. Test your model performance and validate numerical accuracy when deploying to on-device environments 6. Quantize and make your model up to 4x faster and 4x smaller for higher on-device performance. 7. See a demonstration of the steps for integrating the model into a functioning Android app. Learn from Krishna Sridhar, Senior Director of Engineering at Qualcomm, who has played a pivotal role in deploying over 1,000 models on devices and, with his team, has created the infrastructure used by over 100,000 applications. By learning these techniques, you’ll be positioned to develop and deploy AI to billions of devices and optimize your complex models to run efficiently on the edge.
Taught by
Krishna Sridhar
Related Courses
Business Considerations for 5G with Edge, IoT, and AILinux Foundation via edX Introduction to K3s
A Cloud Guru Advanced IoT Systems Integration and Industrial Applications
LearnQuest via Coursera AWS IoT: Developing and Deploying an Internet of Things
Amazon Web Services via edX AWS IoT Greengrass: Utilizing Data
Amazon Web Services via AWS Skill Builder