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.

The process of selecting and implementing the model which match the requirements of a project is known as the "Modelling".

TYPES OF AI Model

AI Models

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.

rule-based-approach

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.

principal-based-approach

Machine Learning (ML)

Machine Learning allows the computers to learn from the experiences by its own to improve the performance and predict the output without being explicitly programmed.
The popular applications of Machine Learning are Email spam filtering, product recommendations, online fraud detection, etc.

How does Machine Learning work ?
The working of machine learning models can be understood by the example of identifying the image of a cat or dog. To identify this, the ML model takes images of both cat and dog as input, extracts the different features of images such as shape, height, nose, eyes, etc., applies the classification algorithm, and predict the output. Consider the below image:

working-of-machine-learning

Deep Learning (DL)

Deep Learning is the study in which machines are trained on its own by examing the algorithms and rules. It focuses on Artificial Neural Network (ANN).
Some popular applications of deep learning are self-driving cars, language translation, natural language processing, etc.

How Deep Learning Works ?
We can understand the working of deep learning with the same example of identifying cat vs. dog. The deep learning model takes the images as the input and feed it directly to the algorithms without requiring any manual feature extraction step. The images pass to the different layers of the artificial neural network and predict the final output.

working-of-deep-learning