Problem understanding: Kernel Method by N

This project aims of introducing the notion of Kernel method. This notion of kernel method is wide used in Machine Learning; It is utilized to model datasets that are non linearly separable. It is almost similar to the notion of Neural Networks, It allows to project the dataset in a space where the datasets are linearly Separable. In kernel Method, we utilize kernel trick procedure.

Kernel	RBF

Refer to this link to get the data.

Run the project

• Understand the Notion of Kernel Method.
• Be able to introduce the kernel trick on project 3 of the last week.
• Implement SVM with the Kernel methods.
• Play around with the different type of kernel in your datasets.
• Compare your results with another type of model, it can be Neural Networks on the same dataset.

Create virtual environment

$ conda create -n yourenvname

Activate your environment

$ conda activate yourenvname

Requirement installations

To run this, make sure to install all the requirements by:

$ conda install --file requirements.txt

Training the model

$ python3 main.py

Example of running models

$ python3 main.py

$ python3 main.py

Author

Mouhamadou Bamba DIOP

Abdou Niang

Fibi Annan Metiki

Gilda Rech