Page 219 - Ai_417_V3.0_C9_Flipbook
P. 219
What is Deployment?
The deployment phase is the last stage of the AI project cycle and is used when the AI model is put into use in
a real-world setting. This involves integrating the model into existing systems or applications, such as creating
Application Programming Interfaces (APIs) or embedding it directly into software. It also includes setting up the
necessary infrastructure, like servers or cloud services, to support the model. Once integrated, the model needs
to be able to process new data and provide predictions. Monitoring tools are established to track the model’s
performance and ensure it works correctly. Logging and reporting are also important to capture data on how
the model is performing and to identify any issues that might arise. This phase is crucial for making the AI model
functional and useful for end-users.
Deployment of an AI project is an essential phase in bringing the created AI solution into practical use. The
following are some of the primary reasons why AI project deployment is relevant:
• Deployment converts theoretical models into actual tools that are capable of being used in real-world
circumstances, bringing the AI solution into practice.
• By deploying the AI solution, organisations may assess its success, productivity, and relevance in real-world
scenarios.
• Deployment is required for end users to communicate with the AI solution.
• Deployment enables the AI solution to grow and be implemented in a variety of situations or places.
• Deployed AI solutions can provide considerable social and financial advantages by increasing productivity,
lowering costs, and efficiently tackling crucial concerns.
The deployment process for AI models involves several key steps:
1. Validating and testing the AI model: This phase ensures the performance of the AI model in real-world
situations that meet the expectations. This involves evaluating the accuracy, performance, and reliability of the
AI model.
2. Integration with current systems: After testing and validating the AI model, it must be integrated with the
existing systems and infrastructure of the organisation by linking the AI model to data sources, APIs, and other
software systems.
3. Monitoring and maintaining the deployed AI model: After deployment, it is necessary to track the
performance of the AI model to guarantee it remains effective. Monitoring and maintaining the deployed
AI model includes various tasks, such as evaluating its performance, identifying and fixing any errors, and
upgrading the model if required.
Some examples of successful AI projects that have been deployed in various industries include as self-driving cars,
medical diagnosis systems, and chatbots.
Case Study: Preventive Blindness
Problem: Prevent Loss of Vision and Delay in Report Generation
Diabetic Retinopathy (DR) is a severe complication of diabetes that affects the blood vessels in the retina. This
condition can lead to blurred vision and eventually blindness if not detected and treated promptly. Given that
approximately 537 million adults aged 20-79 are living with diabetes, addressing the timely detection of DR is
crucial. However, the lack of qualified doctors and delays in generating medical reports exacerbate the risk of
undiagnosed and untreated Diabetic Retinopathy.
AI Reflection, Project Cycle and Ethics 217

