Challenge: Implementing Linear Regression
Oppgave
Swipe to start coding
You are provided with a dataset that contains information about the number of hours students studied and their corresponding test scores. Your task is to train a linear regression model on this data.
- Convert these columns into PyTorch tensors, and reshape them to ensure they are 2D with shapes
[N, 1]
. - Define a simple linear regression model.
- Use MSE as the loss function.
- Define
optimizer
as SGD with the learning rate equal to0.01
. - Train the linear regression model to predict test scores based on the number of hours studied. At each epoch:
- Compute predictions on
X_tensor
; - Compute the loss;
- Reset the gradient;
- Perform backward pass;
- Update the parameters.
- Compute predictions on
- Access the model's parameters (weights and bias).
Løsning
Alt var klart?
Takk for tilbakemeldingene dine!
Seksjon 2. Kapittel 4
single
Spør AI
Spør AI
Spør om hva du vil, eller prøv ett av de foreslåtte spørsmålene for å starte chatten vår
Awesome!
Completion rate improved to 5
Challenge: Implementing Linear Regression
Sveip for å vise menyen
Oppgave
Swipe to start coding
You are provided with a dataset that contains information about the number of hours students studied and their corresponding test scores. Your task is to train a linear regression model on this data.
- Convert these columns into PyTorch tensors, and reshape them to ensure they are 2D with shapes
[N, 1]
. - Define a simple linear regression model.
- Use MSE as the loss function.
- Define
optimizer
as SGD with the learning rate equal to0.01
. - Train the linear regression model to predict test scores based on the number of hours studied. At each epoch:
- Compute predictions on
X_tensor
; - Compute the loss;
- Reset the gradient;
- Perform backward pass;
- Update the parameters.
- Compute predictions on
- Access the model's parameters (weights and bias).
Løsning
Alt var klart?
Takk for tilbakemeldingene dine!
Awesome!
Completion rate improved to 5Seksjon 2. Kapittel 4
single