What is Artificial Intelligence?
AI is a computer or system designed to be intelligent: to perceive its environment, make decisions and take action.
For Engineers there is a lot to consider beyond the broad definition of artificial intelligence (AI) and more importantly how to implement it. The result will obviously vary from application to application, but building a successful AI system involves navigating the entire workflow and focusing on more than training an AI model.
What does AI mean to Engineers?
AI means data preparation. At the centre of most AI applications is data. It turns out that data preparation is one of the most critical ingredients to AI success. Without data preparation, you stand to spend a lot of time looking at mediocre AI results and wondering: why?
Data preparation is more than just having a lot of data or even preprocessing all of the data to be consistent. This is about human insight… what makes data good? Its about considering augmenting data sets with synthetic data and more samples and its about getting to clean-labelled data faster by automating the time you spend labelling.
AI means modelling
Yes, we said AI is more than just a model…you still need to build the best model possible.
When choosing your AI system, you need to consider the following
Your choice of Algorithm
Are you looking at Machine Learning or Deep Learning. Maybe it is a combination of both. Starting with a complete set of algorithms and pre-built modes, you are already ahead of the game; taking advantage of the broader work in the AI community and not starting from scratch.
Tuning your model
Here is where you take your time to find the optimal set parameters that will get you to the most robust & accurate model. Getting to an accurate model takes time. Adding more hardware can significantly speed-up the time to train models with all combination of parameters and input data.
AI means system design
The model is not the result; it is part of a complex system. Take for example a robot with the job of delivering packages. Adding AI to the robot means that the AI must co-exist with all other pieces fluidly. You have perception, localization and path planning using multiple sensors. You have physical sensors to control speed and direction handling.These pieces work together to create a complete working system and it has to work perfectly in all scenarios. Simulation is how it all comes together. Not only will simulation verify that all the pieces work together correctly, it will ensure that the pieces work together in a way you expect in every scenario. Simulation will help you test edge cases and test millions of scenarios that would otherwise be too time-intensive. It also helps you validate your model works correctly before deploying to hardware.
AI means deployment
You have trained your model, tested your system. It’s time to get AI out into the world. Since a wide range of applications use AI, there are a wide range of deployment requirements. From ECUs and Cars to Edge systems and chemical plants to enterprise systems in manufacturing or cloud-based streaming systems to collect data from multiple locations. You can integrate AI into any part of these systems so you need AI to provide flexibility to deploy to all possible platforms.
When incorporating AI
There is a lot to consider when incorporating AI into systems. As Engineers, it is important to focus on more than just building a model but rather the entire AI workflow.
