Advanced Learning Algorithms

Question 1

What is a neural network?

Question 2

How is a neural network structured?

Question 3

What is forward propagation?

Question 4

What is backward propagation?

Question 5

What are activation functions, and why are they important in neural networks?

Question 6

What are some commonly used activation functions?

Question 7

How do you choose the right activation function for a given problem?

Question 8

When should you use the sigmoid function?

Question 9

When should you use the ReLU activation function?

Question 10

What is the difference between linear regression and a neural network with linear activation functions?

Question 11

What is the difference between binary classification and multiclass classification?

Question 12

What is the softmax regression algorithm, and how is it used in multiclass classification?

Question 13

What is the cross-entropy loss function, and how is it used in the context of softmax regression?

Question 14

What is the indicator function used in the cost equation for Softmax regression?

Question 15

How can numerical instability issues be mitigated when using the softmax activation function?

Question 16

What are logits in the context of machine learning, and how are they used in the SparseCategoricalCrossentropy loss function?

Question 17

What is multi-label classification, and how does it differ from single-label classification?

Question 18

How can a neural network be trained for multi-label classification?

Question 19

What is the Adam algorithm, and how is it used in optimization for machine learning?

Question 20

How can you evaluate a models performance in machine learning?

Question 21

How can you diagnose whether an algorithm has high bias or high variance?

Question 22

What is regularization in machine learning?

Question 23

How does L2 regularization prevent overfitting in a model?

Question 24

How can regularization control both high bias and high variance in a model?

Question 25

Why is it useful to compare an algorithms performance to that of a human or competing algorithms?

Question 26

How can learning curves help diagnose whether an algorithm is suffering from high bias or high variance?

Question 27

How can you debug a learning algorithm that is suffering from high bias or high variance?

Question 28

What are precision and recall, what are they used for?

Question 29

When is accuracy not the most appropriate metric to use when evaluating the performance of a machine learning algorithm?

Question 30

Define the F1 score

Question 31

What is a precision recall curve, and what is the significance of the area under the curve?

Question 32

How are precision and recall calculated?

Question 33

What is the difference between true positives and false positives?

Question 34

How do precision and recall provide more insight into the performance of a model on imbalanced datasets?

Question 35

What are some limitations or weaknesses of using precision and recall as error metrics?