AI Is More Than a Model: Four Steps to Complete Workflow Success

AI Is More Than a Model: Four Steps to Complete Workflow Success

The key element for success in practical AI implementation is uncovering any issues early on and knowing what aspects of the workflow to focus time and resources on for the best results—and it’s not always the most obvious steps.

Sponsored Post.

Engineers are increasingly looking to successfully integrate AI into projects and applications while attempting to climb their own AI learning curve. To tackle AI, engineers start with wanting to understand what AI is and how it fits into their current workflow, which might not be as straightforward as it seems. A simple search of “What is AI?” yields millions of results on Google, with varying degrees of technical and relevant information.

So, what is AI to engineers?

Most of the focus on AI leans heavily on the AI model, which drives engineers to quickly dive into the modeling aspect of AI. After a few starter projects, engineers quickly learn that AI is not just modeling, but rather a complete set of steps that includes data preparation, modeling, simulation and test, and deployment.

Figure 1. The four steps that engineers should consider for a complete, AI-driven workflow. © 1984–2020 The MathWorks, Inc.

Engineers using machine learning and deep learning often expect to spend a large percentage of their time developing and fine-tuning AI models. Yes, modeling is an important step in the workflow, but the model is not the end of the journey. The key element for success in practical AI implementation is uncovering any issues early on and knowing what aspects of the workflow to focus time and resources on for the best results—and it’s not always the most obvious steps.

Two important asides to consider before diving into the complete workflow:

  1. Most often, AI is only a small piece of a larger system, and it needs to work correctly in all scenarios with all other working parts of the end product, including other sensors and algorithms such as control, signal processing, and sensor fusion.
  2. Engineers in this scenario already have the skills to be successful incorporating AI. They have inherent knowledge about the problem, and with tools for data preparation and designing models, they can get started even if they’re not AI experts, allowing them to leverage their existing areas of expertise.

The AI-Driven Workflow

Now we can dive into the four steps for the AI-driven complete workflow and better understand how each step plays its own critical role in successfully implementing AI into a project.

Step 1: Data Preparation

Data preparation is arguably the most important step in the AI workflow: Without robust and accurate data as input to train a model, projects are more likely to fail. If an engineer gives the model “bad” data, he or she will not get insightful results—and will likely spend many hours trying to figure out why the model is not working.

To train a model, you should begin with clean, labeled data, as much as you can gather. This may also be one of the most time-consuming steps of the workflow. When deep learning models do not work as expected, many often focus on how to make the model better—tweaking parameters, fine-tuning the model, and multiple training iterations. However, engineers would be better served focusing on the input data: preprocessing and ensuring correct labeling of the data being fed into a model to ensure that the data can be understood by the model.

One example of the importance of data preparation is from construction machinery and equipment company, Caterpillar, which takes in high volumes of field data from various machines. This plethora of data is necessary for accurate AI modeling, but the sheer volume of data can make the data cleaning and labeling process even more time intensive than usual. To streamline that process, Caterpillar uses automatic labeling and integration with MATLAB to quickly develop clean, labeled data for input into machine learning models, providing more promising insights from field machinery. The process is scalable and gives users the flexibility to use their domain expertise without having to become experts in AI.

Step 2: AI Modeling

Once the data is clean and properly labeled, it’s time to move on to the modeling stage of the workflow, which is where data is used as input, and the model learns from that data. The goal of a successful modeling stage is creating a robust, accurate model that can make intelligent decisions based on the data. This is also where deep learning, machine learning, or a combination thereof comes into the workflow as engineers decide what will be the most accurate, robust result.

At this stage, regardless of deciding between deep learning (neural networks) or machine learning models (SVM, decision trees, etc.), it’s important to have direct access to many algorithms used for AI workflows, such as classification, prediction, and regression. You may also want to use a variety of prebuilt models developed by the broader community as a starting point or for comparison.

Using flexible tools, like MATLAB and Simulink, offers engineers the support needed in an iterative environment. While algorithms and prebuilt models are a good start, they’re not the complete picture. Engineers learn how to use these algorithms and find the best approach for their specific problem by using examples, and MATLAB provides hundreds of examples for building AI models across multiple domains.

AI modeling is an iterative step within the complete workflow, and engineers must track the changes they are making to the model throughout this step. Tracking changes and recording training iterations, with tools like Experiment Manager, is crucial as it helps explain the parameters that lead to the most accurate model and create reproducible results.

Step 3: Simulation and Test

AI models exist within a larger system and must work with all other pieces in the system. Consider an automated driving scenario: Not only do you have a perception system for detecting objects (pedestrians, cars, stop signs), but this has to integrate with other systems for localization, path planning, controls, and more. Simulation and testing for accuracy are key to validating that the AI model is working properly, and everything works well together with other systems, before deploying a model into the real world.

To build this level of accuracy and robustness prior to deployment, engineers must ensure that the model will respond the way it is supposed to, no matter the situation. Questions you should ask in this stage include:

  • What is the overall accuracy of the model?
  • Does the model perform as expected in each scenario?
  • Does it cover all edge cases?

Trust is achieved once you have successfully simulated and tested all cases you expect the model to see and can verify that the model performs on target. By using tools like Simulink, engineers can verify that the model works as desired for all the anticipated use cases, avoiding redesigns that are costly both in money and time.

Step 4: Deployment

Once you are ready to deploy, the target hardware is next—in other words, readying the model in the final language in which it will be implemented. This step typically requires design engineers to share an implementation-ready model, allowing them to fit that model into the designated hardware environment.

That designated hardware environment can range from desktop to the cloud to FPGAs, and MATLAB can handle generating the final code in all scenarios. These types of flexible tools will offer engineers the leeway to deploy their model across a variety of environments without having to rewrite the original code.

Take the example of deploying a model directly to a GPU: Automatic code generation eliminates coding errors that could be introduced through manual translation and provides highly optimized CUDA code that will run efficiently on the GPU.

Johanna Pingel is a Product Marketing Manager at MathWorks. She focuses on machine and deep learning applications and making AI practical, entertaining, and achievable. She joined the company in 2013, specializing in image processing and computer vision applications with MATLAB.

To learn more about the topic covered in this blog, see the examples below or email me at

  • What is Artificial Intelligence (AI)? (overview): Learn the three things you need to know about artificial intelligence.
  • Deep Learning Onramp (online tutorial): Learn how to use deep learning techniques in MATLAB for image recognition.
  • Operationalize Your AI (Gartner Report): Find out the best practices for AI DevOps and key challenges technology leaders face in moving AI and machine learning models to production.

Author: Shantun Parmar

36 thoughts on “AI Is More Than a Model: Four Steps to Complete Workflow Success

  1. I needed to post you that little bit of observation to say thanks once again for your personal magnificent pointers you’ve featured in this article. It is quite remarkably generous of people like you to give openly just what a number of us might have marketed as an e book to end up making some dough for themselves, most notably given that you could possibly have done it if you ever decided. The guidelines also acted like a fantastic way to be sure that other individuals have similar dreams just like my own to grasp a whole lot more in terms of this issue. I’m sure there are many more fun occasions ahead for individuals that go through your blog post.

  2. Thanks for your whole work on this website. My niece takes pleasure in working on research and it is simple to grasp why. We all notice all relating to the powerful ways you render vital tips and tricks via your website and therefore welcome response from website visitors on this theme while our own simple princess is without question understanding so much. Take pleasure in the rest of the year. Your performing a very good job.

  3. My spouse and i got now glad that Ervin could deal with his investigations through the ideas he got out of the web page. It’s not at all simplistic to just choose to be giving freely key points that many other people have been selling. And we also fully grasp we have got the website owner to be grateful to for that. The entire explanations you have made, the simple site menu, the friendships you can give support to foster – it’s got many fantastic, and it’s really facilitating our son and the family imagine that the issue is entertaining, and that is particularly indispensable. Thank you for everything!

  4. I am glad for writing to make you know what a nice encounter our princess went through visiting yuor web blog. She realized too many things, with the inclusion of what it is like to possess an incredible teaching style to make the rest without problems understand various very confusing topics. You undoubtedly surpassed visitors’ expected results. Thanks for supplying those warm and helpful, trustworthy, revealing not to mention unique tips on your topic to Tanya.

  5. Link exchange is nothing else however it is only placing
    the other person’s web site link on your page at appropriate place
    and other person will also do same in support of you.

  6. Great post. I was checking constantly this blog
    and I’m inspired! Very helpful info specifically the closing part 🙂 I handle such info much.
    I used to be seeking this certain information for a long
    time. Thanks and best of luck.

  7. Spot on with this write-up, I seriously think this site needs a great
    deal more attention. I’ll probably be back again to see more, thanks for the

  8. hello there and thank you for your information – I’ve definitely
    picked up something new from right here. I did however expertise several
    technical points using this website, as I experienced to reload the site lots of times previous
    to I could get it to load correctly. I had been wondering if
    your web host is OK? Not that I am complaining, but sluggish loading instances times will very frequently affect your placement in google and could damage your high-quality score if
    ads and marketing with Adwords. Well I’m adding this RSS to my
    email and can look out for a lot more of your respective fascinating content.
    Ensure that you update this again very soon.

  9. I think that what you composed was very reasonable. However, what about this?
    suppose you added a little content? I am not saying your content isn’t solid.,
    however what if you added a post title that makes people want more?
    I mean AI Is More Than a Model: Four Steps to Complete Workflow Success – Cooding Dessign is a
    little plain. You could glance at Yahoo’s front page
    and see how they write article headlines to grab viewers
    to click. You might try adding a video or a pic or two to get readers excited
    about what you’ve written. Just my opinion, it might
    make your blog a little livelier.

Leave a Reply

Your email address will not be published.