Page 267 - AI Ver 3.0 Class 11
P. 267
Evaluation
The designed and tested model is now to be checked for its real-world
execution. The AI model is now given test cases and test data to check,
to see if it works accurately in real life and uncovers the errors that might
have been left hidden in the modelling and training phase. The trained
and tested model is then reformed based on the unprecedented outputs
that are encountered during evaluation phase. Sometimes the defined
parameters need tunings and adjustments to suit the problem in hand.
Deployment
After the modelling and evaluation phase, the AI model is deployed or implemented
in real-life scenarios. The model is then integrated with existing systems. The new
application is then utilised and upgraded as, and when some unprecedented
scenarios cause some undesirable results. The model could be working dynamically
in an online environment as well as offline, like reporting things to the manager.
Understanding the nature of a problem provides insight into the components and
attributes of the yet-to-be-implemented solutions. A good understanding of a
problem, guides future decisions to make at the later project stages, especially decisions such as determining if an AI
solution is even feasible. At the core of every AI model, is "finding patterns in data". If the data shows no patterns, then
most probably, the problem cannot be solved using AI.
A successful problem-defining process requires a basic analysis and evaluation of the project-related problems, their
reasons and methods. Finding the right problem definition is usually an iterative process. It can reveal more questions
and points to consider that would have been ignored without the problem definition process. The questions below
serve as a reference point for a thorough analysis of the problem and the problems that surround it. Just spending time
answering the following questions can save you weeks and months working on problems that proved impossible for
previously unknown reasons:
• What is the problem that needs to be resolved?
• Why do you need a solution to your problem?
• How should we work on the solution to the problem?
• Which aspects of the problem does the AI model solve?
• How do I need to interact with the solution to the problem?
• Which category of data will be involved? (Classification)
• How much or how many? (Regression)
• Can the data be grouped? (Clustering)
• Is there any unusual pattern in the data? (Anomaly Detection)
• Which option should be given to the customer? (Recommendation)
It is essential to determine which of these questions you’re asking and in what way answering them helps solve your
problem.
Introduction to Capstone Project 265

