למידה חישובית 2025
- 62 שאלות
- -- תגובות
- 0% הושלמו
- equalizer סטטיסטיקות
- share שתף
מנהלים:
Discuss, Learn and be Happy דיון בשאלות
help
brightness_4
brightness_7
format_textdirection_r_to_l
format_textdirection_l_to_r
Which evaluation metric should we choose in the spam detection problem? (מועד ב 2022)
1
| done | ||
Precision, the other metrics focus on recall. we don't care a lot about the false negative
מיין לפי
if the first few iterations of gradient descent increase the loss rather than decrease, then the most likely cause is that we have set the learning rate to too large a value (מועד ב 2022)
1
| done | ||
If alpha were small enough, the gradient descent should always successfully take a tiny, small downhill and decrease f(theta0, theta1) at least a little bit. if gradient descent instead increases the objective value, that means alpha is too large (or you have a bug in your code!)
מיין לפי
Gradient Descent is a supervised Machine Learning Technique (מועד ב 2022)
1
| done | ||
מיין לפי
What is the complexity of computing the ROC AUC given n samples? (מועד ב 2022)
1
| done | ||
מיין לפי
מי מהאפשרויות הבאות היא סיבה לבצע נורמליזציה של מאפיינים (features) בבעיית רגרסייה ליניארית? (מועד ב 2022)
1
| done |
Feature scaling speeds up gradient descent by avoiding many extra iterations that are required when one or more features take on much larger values than the rest
מיין לפי
In vanilla RNN architecture, there are three types of learned variables (מועד ב 2022)
1
| done | ||
מיין לפי
Which of the next can help reducing the variance of a model? (מועד ב 2022)
1
| done | ||
| done | ||
| done | ||
| done | ||
מיין לפי
What is the time complexity of decision tree training using the ID3 algorithm? Assume m attributes, n training instances, and the train depth is O(logn) (מועד ב 2022)
1
| done | ||
מיין לפי