4. Modelling
After exploration of data, we need to look at different AI-enabled algorithms which can suitable for the project. We go through several models and select the ones which match the requirements. After choosing the model, we implement it. This is known as the Modelling stage of AI Project cycle.
Modelling is the process of selecting and implementing the suitable AI-enabled algorithms for the success of project.
Modelling refers to the developing and training an AI model.
Explanation
After exploration of data, we need an AI-enabled algorithms or AI models that helps to feed or store that data into the project/system. This models help to store the data and train the machine to work.
This could be done either by designing your own AI model or by using the pre-existing AI models.
AI Model
AI Model can be categorised as Rule Based AI Model (Model-driven AI Model) and Learning Based AI Model (Data-driven AI Model).
Rule-based AI Model: In Rule-based AI approach, the developer feeds the data along with the some ground rules as input to the AI model. This model then gets trained with these inputs and gives answers in the form of predictions. It is also known as Model-driven AI Model.
Learning-based AI Model: In Learning-based AI Approach, the developer feeds the data along with the answers to the AI Model. This model then designs its own algorithms and methodologies to match the data with answers and gives out the rules. It is also known as Data-driven AI Model.
Learning Based AI Model can be categorised as :