linear regression is a linear approach to modelling the relationship between a scalar response and one or more explanatory variables (also known as dependent and independent variables).
The NASA data set comprises different size NACA 0012 airfoils at various wind tunnel speeds and angles of attack. The span of the airfoil and the observer position were the same in all of the experiments.
This problem has the following inputs:
- Frequency, in Hertzs.
- Angle of attack, in degrees.
- Chord length, in meters.
- Free-stream velocity, in meters per second.
- Suction side displacement thickness, in meters.
The only output is:
- Scaled sound pressure level, in decibels.
(https://archive.ics.uci.edu/ml/datasets/Airfoil+Self-Noise#)
- Load the data
- Data Cleaning
- Model Design
- Intilized the weights and biase vector
- Model function
- Loss function
- Compute gradients
- Adjust weights and biases to reduce the loss
- Train the model using gradient descent
- Evaluate the Model performance base on RMSE
- Designed the Linear Regression From scratch
- Pythorch Bulid in Linear Regression
All the code and comments are listed in above jupyter notbooks for your understanding.