Artificial Intelligence (AI)
Discuss current events in AI and technological innovations with Intel® employees
485 Discussions

Learn How to Deploy AI on Intel® Hardware with Intel® Edge AI Developer Certification Program

MaryT_Intel
Employee
0 0 2,742

Intel Edge AI Developer Certification courses are free

figure 1

Modern edge devices can handle increasingly sophisticated tasks, including high-performance AI for machine vision, predictive maintenance, and language processing. Knowing how to develop AI applications for the edge is a critical skill that will only get more valuable as AI proves its ability to transform every business sector it touches.

We’ve created an on-demand, self-paced, hands-on series of courses—the Intel® Edge AI Developer Certification Program—so you can learn how to put AI to work in real-world edge applications. All of the courses and learning materials are free, including your own account on the Intel® DevCloud for the Edge.

With DevCloud, you can access all our edge AI dev tools, deep learning inference sample applications, and Intel® hardware. It’s everything you need to start developing AI applications for the edge.

figure 2

Object detection can help prevent product loss in retail.
 

Don’t you need a degree in data science to work in AI?

Not when it comes to AI at the edge. At the edge, we deploy AI models that have already been trained. The data science of building a framework—like TensorFlow, PyTorch, or MXNet—and training models to recognize a specific object, sound, or phrase has already been done. Edge AI developers focus on deployment—the process of conversion, optimization, and app development that turns deep learning models into real-world smart applications.

For example, we can take an object detection model and combine it with an industrial control system to create a smart manufacturing robot that can inspect its own welds. Of course, deploying AI at the edge—where time, power, bandwidth, and electricity are all precious—has limitations and challenges.
 

figure 3

Deep learning inference can be used to inspect welds in real time.
 

How do you run AI on the lower-powered devices you find at the edge?

When most of us hear “AI,” we think huge data sets and massive computing power. But deep learning models can be trained for narrow edge applications, which reduce model size. Smaller models need less memory and less power and run much faster. Intel engineers have already done a lot of that work for you. Our Open Model Zoo has pretrained deep learning models for computer vision, natural language processing, and other edge AI deployments.
 

figure 4

Detecting safety gear helps protect workers, using minimal computing resources.
 

You can enhance inference performance even furtherby optimizing and tuning deep learning models with tools like the Intel® Distribution of OpenVINO™ toolkit. OpenVINO toolkit has plugins for every Intel® architecture, tools for balancing performance and accuracy, and the ability to change precision levels from FP32 to FP16 and int8. Optimizing deep learning models for edge AI is one of the first things we cover in the program.
 

What does the Intel Edge AI Developer Certification Program cover?

The program begins with hands-on activities that show you how deep learning inference works on Intel hardware. You’ll work with the same Intel® tools and services that edge developers and hardware manufacturers are using to prototype, test, and deploy AI solutions.

Topics in the edge AI foundations learning path include:
 

  • Building write once, deploy anywhere deep learning inference applications with the OpenVINO toolkit
  • Converting models developed in TensorFlow, MXNet, Kaldi, Caffe, ONNX, and other frameworks for Intel hardware
  • Benchmarking and optimizing models for specific Intel® processors and architectures
  • Creating inference engines that will load balance across mixed Intel hardware, including Intel® CPUs, integrated GPUs, VPUs, and FPGAs
  • Using Intel DevCloud for the Edge to develop and test edge AI applications

Once you’ve completed the introductory courses, you can move on to classes in fundamental deep learning use cases, including:
 

  • Object classification and retail loss prevention
  • Object detection and industrial worker safety
  • Style transfers and smart cities data augmentation

Each learning path features an instructional video, hands-on exercises with sample apps, and projects in which you develop your own working prototypes. Each path has a final assessment so you can make sure you’ve mastered the material. Classes, software, and an account on Intel DevCloud for the Edge are free. All you have to do is sign up.

New learning paths will be coming online so that you can continue to build your AI deployment skills, learn increasingly complex material, and stay ahead of the latest AI developments and trends.
 

Earn rewards as you learn

Every course you complete earns Chips that you can redeem for Intel merchandise.

Once you sign up for the program, you’ll have access to all the learning paths and a dashboard where you can track your progress. The program, including an Intel DevCloud for the Edge account, is free for you to use.
 

Certify your new Edge AI skills

After you complete the program, you can certify your new skills for USD 99. Certification gives you proof of your new skills that you can add to your résumé and include in your portfolio. You also get a digital badge you can pin to your social profiles. You can recertify every year by taking new classes in the latest Edge AI advances.


 

Intel Edge AI Developer Certification courses are free—just sign up!

The courses and materials are available at no cost. All you have to do is enroll. You only pay for certification, not for learning.
To get started, please visit the Intel Edge AI Certification page.

 

Notices and Disclaimers

Intel is committed to respecting human rights and avoiding complicity in human rights abuses. See Intel’s Global Human Rights Principles. Intel® products and software are intended only to be used in applications that do not cause or contribute to a violation of an internationally recognized human right.

Intel® technologies may require enabled hardware, software, or service activation.

No product or component can be absolutely secure. 

Your costs and results may vary.

© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.  
 

About the Author
Mary is the Community Manager for this site. She likes to bike, and do college and career coaching for high school students in her spare time.