Machine Learning in Physics: Glass Identification Problem
Wednesday, February 9, 2022
Machine Learning in Physics: Glass Identification Problem - Apply machine learning techniques to solve physics problems
Gasmi Haithem
New
What you'll learn
- Learn how to use and manipulate different machine learning libraries and tools to classify the different types of glass.
- Visualize you data features with several types of plots such as : Bar plots and Scatter plots with the help of data Viz tools like: Matplotlib and Seaborn.
- Build a good sense of exploring and analysing your data from the plotted graphs.
- Get insights from data analysis that will help you solve the problem with the most convenient way.
- Understand the different steps of Data Preprocessing like : checking the missing data, standardization and scaling, spliting the dataset).
- Build and Train multiple State-of- the-art classification models like : Logistic Regression, KNN, Decision Tree and Random Forest Classifiers
- Learn how to evalute your models/classifiers with different metrics.
- Fine-tune different parameters to boost the performance of your models.
- Learn how to set and read a confusion matrix in order to make comparisons between the actual values and the predicted values.
Requirements
- Familiar with foundational python programming concepts.
- A very basic background of machine learning will help
Description
Move your ML skills from theory to practice in one of the most interesting fields " Physics"?
In this course you are going to solve the glass identification problem where you are going to build and train several machine learning models in order to classify 7 types of glass( 1- Building windows float-processed glass / 2- Building windows non-float-processed glass / 3- Vehicle windows float-processed glass / 4- Vehicle windows non-float-processed-glass / 5- Containers glass / 6- Tableware glass / 7- Headlamps glass).
Through this course, you will learn how to deal with a machine learning problem from start to end:
1 - You will learn how to import, explore, analyse and visualize your data.
2- You will learn the different techniques of data preprocessing like : data cleaning, data scaling and data splitting in order to feed the most convenient format of data to your models.
3- You will learn how to build and train a set of machine learning models such as : Logistic Regression, Support Vector Machine (SVM), Decision Trees and Random Forest Classifiers.
4- You will learn how to evaluate and measure the performance of your models with different metrics like: accuracy-score and confusion matrix.
5- You will learn how to compare between the results of your models.
6- You will learn how to fine-tune your models to boost their performance.
After completing this course, you will gain a bunch of skillset that allows you to deal with any machine learning problem from the very first step to getting a fully trained performent model.
Who this course is for:
- Machine Learning students who want to excel their skills in machine learning with real world problems in physics.
- Any machine learning learner who wants to go from theory to practice machine learning in different industries such as physics.