Practical aspects of Deep Learning >> Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
1.If you have 10,000,000 examples, how would you split the train/dev/test set?
1 point
2.The dev and test set should:
1 point
3.If your Neural Network model seems to have high bias, what of the following would be promising things to try? (Check all that apply.)
1 point
4.You are working on an automated check-out kiosk for a supermarket, and are building a classifier for apples, bananas and oranges. Suppose your classifier obtains a training set error of 0.5%, and a dev set error of 7%. Which of the following are promising things to try to improve your classifier? (Check all that apply.)
1 point
5.What is weight decay?
1 point
6.What happens when you increase the regularization hyperparameter lambda?
1 point
7.With the inverted dropout technique, at test time:
1 point
8.Increasing the parameter keep_prob from (say) 0.5 to 0.6 will likely cause the following: (Check the two that apply)
1 point
9.Which of these techniques are useful for reducing variance (reducing overfitting)? (Check all that apply.)
1 point
10.Why do we normalize the inputs xx?
1 point
Related Questions & Answers:
- Practical aspects of deep learning Practical aspects of deep learning >> Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization 1. If you have 10,000,000 ... Read more...
- Regression Regression >> Machine Learning with Python Regression TOTAL POINTS 15 1.Multiple Linear Regression is appropriate for: 3 points Predicting ... Read more...
- What is statistics good for? What is statistics good for? >> A Crash Course in Data Science TOTAL POINTS 5 1.We covered four example ... Read more...
- Week 1 Comprehensive Week 1 Comprehensive >> Introduction to Machine Learning TOTAL POINTS 10 1.Which of the following are necessary for ... Read more...
- *Weekly challenge 5* *Weekly challenge 5* >> Foundations: Data, Data, Everywhere TOTAL POINTS 8 1.A magazine wants to understand why its ... Read more...
- Graded Quiz 8 Graded Quiz 8 >> Introduction to Data Analytics TOTAL POINTS 5 1.”A presentation is not a data dump”. ... Read more...