Topics In Demand
Notification
New

No notification found.

The four key steps to AI project success (hint: it is not just modeling).
The four key steps to AI project success (hint: it is not just modeling).

488

0

With AI becoming more mainstream, there is an increasing demand to integrate AI into projects and applications. To make this happen, engineers need to develop critical AI skills. They should also understand how AI fits into their existing processes and systems.

Is AI just building models?

Engineers who are new to AI, tend to get into the modeling aspect as the starting point. However, it is important to understand that AI is not just modeling. It is a series of steps that includes data preparation, modeling, simulation and test, and deployment. When developing a system that incorporates an AI model, it is important to also ensure that the entire system performs well.

Figure 1. The four steps that engineers should consider for a complete, AI-driven workflow. © 1984–2022 The MathWorks, Inc.
Figure 1. The four steps that engineers should consider for a complete, AI-driven workflow. © 1984–2022 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.

 

Data Preparation

Taking raw data and making it useful for an accurate, efficient, and meaningful model is a critical step. In fact, it represents most of your AI effort.

Data preparation requires domain expertise, such as experience in speech and audio signals, navigation and sensor fusion, image and video processing, and radar and lidar. Engineers in these fields are best suited to determine what the critical features of the data are, which are unimportant, and what rare events to consider.

AI also involves prodigious amounts of data. Yet labeling data and images is tedious and time-consuming. Sometimes, you don’t have enough data.. Generating accurate synthetic data can improve your data sets. In both cases, automation is critical to meeting deadlines.

AI Modeling

Key factors for success in modeling AI systems are to:

  • Start with a framework that provides a strong set of customizable algorithms and prebuilt models for machine learning, deep learning, reinforcement learning, and other AI techniques
  • Use apps for productive design and analysis
  • Work in an open ecosystem where AI tools like MATLAB®, PyTorch™, and TensorFlow™ can be used together
  • Manage compute complexity with GPU acceleration and scaling to parallel and cloud servers and on-premise data centers

System Design

AI models exist within a complete system. In automated driving systems, AI for perception must integrate with algorithms for localization and path planning and controls for braking, acceleration, and turning.

AI used in automated driving scenario
AI used in automated driving scenario. © 2021–2022 The MathWorks, Inc.

 

Consider the AI in predictive maintenance for wind farms and autopilot controls for today’s aircraft.

Complex, AI-driven systems like these require integration and simulation.

Deployment

AI models need to be deployed to CPUs, GPUs, and/or FPGAs in your final product, whether part of an embedded or edge device, enterprise system, or in cloud environments. AI models running on the embedded or edge device provide the quick results needed in the field, while AI models running in enterprise systems and the cloud provide results from data collected across many devices. Frequently, AI models are deployed to a combination of these systems.

The deployment process is accelerated when you generate code from your models and target your devices. Using code generation optimization techniques and hardware-optimized libraries, you can tune the code to fit the low power and memory footprint profile required by embedded and edge devices or the high-performance needs of enterprise systems and the cloud.

The content has been originally published at mathworks.com.

All product and company names are trademarks™ or registered® trademarks of their respective holders.

Authors:

Paul Pilotte leads product management and marketing for MATLAB and Simulink solutions for AI, data science, machine learning, and deep learning focusing on industrial AI applications such as predictive maintenance, automated driving, robotics, IoT, and digital twins.  

Prashant Rao heads the Application Engineering team at MathWorks India and he is a regular contributor at industry forums, academic communities focusing on AI and analytics.

 


That the contents of third-party articles/blogs published here on the website, and the interpretation of all information in the article/blogs such as data, maps, numbers, opinions etc. displayed in the article/blogs and views or the opinions expressed within the content are solely of the author's; and do not reflect the opinions and beliefs of NASSCOM or its affiliates in any manner. NASSCOM does not take any liability w.r.t. content in any manner and will not be liable in any manner whatsoever for any kind of liability arising out of any act, error or omission. The contents of third-party article/blogs published, are provided solely as convenience; and the presence of these articles/blogs should not, under any circumstances, be considered as an endorsement of the contents by NASSCOM in any manner; and if you chose to access these articles/blogs , you do so at your own risk.


MathWorks develops MATLAB & Simulink - software that transforms the way engineers and scientists think and work.

© Copyright nasscom. All Rights Reserved.