Which regularization technique adds a penalty equivalent to the absolute value of the magnitude of coefficients?
- Elastic Net
- L1 Regularization
- L2 Regularization
- Ridge Regularization
L1 Regularization, also known as Lasso, adds a penalty equivalent to the absolute value of coefficients. This helps in feature selection by encouraging some coefficients to become exactly zero.
Loading...
Related Quiz
- Why might a deep learning practitioner use regularization techniques on a model?
- In the context of Q-learning, what does the 'Q' stand for?
- A finance company wants to analyze sequences of stock prices to predict future market movements. Given the long sequences of data, which RNN variant would be more suited to capture potential long-term dependencies in the data?
- What is the primary objective of Generative Adversarial Networks (GANs)?
- RNNs are particularly suitable for tasks like ________ because of their ability to handle sequences.