Which of the following statements about bias and variance are true? (Select TWO correct answers) A. High bias models are typically underfit. B. Overfitting tends to lead to models with high variance and low bias. C. You can usually optimize both bias and variance simultaneously by choosing a more complex model. D. You can usually optimize both bias and variance simultaneously by choosing better hardware with GPUs.

The correct answers are:

A. High bias models are typically underfit. B. Overfitting tends to lead to models with high variance and low bias.

Explanation:

A. High bias models are typically underfit. This is true because high bias in a model is a sign of underfitting. This means the model is too simple and does not capture the complexity of the data well enough, leading to high error on training and test data.

B. Overfitting tends to lead to models with high variance and low bias. This is also true. Overfitting occurs when a model is too complex and captures the noise along with the underlying pattern in data. It performs well on training data but poorly on unseen data. This is a sign of high variance and low bias.

C. You can usually optimize both bias and variance simultaneously by choosing a more complex model. This is not necessarily true. While a more complex model might reduce bias, it could also increase variance (overfitting). The goal is to find a good balance between bias and variance, which often involves tuning model complexity, but not necessarily always increasing it.

D. You can usually optimize both bias and variance simultaneously by choosing better hardware with GPUs. This is not true. While better hardware might speed up computation, it does not directly affect the bias-variance tradeoff. This tradeoff is more about the model selection and the complexity of the model, not the hardware used to run the computations.