Upgrade to remove ads
Only $35.99/year

Machine Learning

Terms in this set (47)

Which of the following does not belong to the automatic hyperparameter optimization algorithm?
Random gradient descent
What are the commonly used kernel functions in SVM?
All of the choices
Training error will reduce the accuracy of the model and produce underfitting. How to improve the model fit?
Feature, add, increase
Reducing the gap between the training error and the test error will result in overfitting. How to prevent overfitting?
Cross validation
Which of the following statements is wrong in comparing Gradient Boosting Decision Tree (GBDT) and Random Forest algorithms?
GBDT algorithm is easier to overfit than random forest.
What are the common types of dirty data?
all
Which of the following descriptions is wrong about the hyperparameter?
Hyperparameters cannot be modified
With a lot of sales data but no labels, a company wants to identify a VIP customer. Which of the following models is/are suitable?
Except SVM
After the data has completed the feature engineering operation, in the process of constructing the model, which of the following options is not a step in the decision tree construction process?
Data cleaning
As the number of training examples goes to infinity, your model trained on that data will have:
Same Bias
If the direction of the error is important, the best loss function is RMSE (Root mean Square Error)
False
Mean Squared Error is also called Cost Function.
True
Which of the following about the description of expectations and variances is incorrect?
The greater the expectation the smaller the variance
In Random Forest, what strategy is used to determine the outcome of the final ensemble model?
Voting System
Which of the following statements about K in the KNN algorithm is correct?
K is a hyperparameter
Training error causes underfitting by reducing model accuracy. How can the model be a better fit?
All of these mentioned
When dealing with actual problems, when should machine learning be used in the following situations?
The complexity & Task rules
Which of the following evaluation indicators belong to the regression algorithm?
Mean Square Error
Which of the following description of the validation set is wrong?
The validation set can coincide with the test set.
Grid search is a method of parameter adjustment.
False
In machine learning, what input the model needs to train itself and predict the unknown?
Historical data
Which of the following statements about supervised learning is correct?
Decision tree is a supervised learning
K folding cross-validation refers to dividing the test data set into K sub-data sets.
False
Which of the following is true about unsupervised learning?
Unsupervised algorithm only processes "features" and does not process tags
What does not belong to supervised learning?
Principal component analysis
Which of the following statements about gradient descent is not true?
The gradient descent algorithm is fast and reliable.
In order for a machine to be intelligent, it must be knowledgeable. There is a research field in artificial intelligence which mainly studies how computers automatically acquire knowledge and skills to achieve self-improvement. Which of the following is this research field?
Machine learning
If an L1 Regular term is added to the loss function of linear regression, the regression is called Lasso regression.
True
The following is the correct difference between machine learning algorithms and traditional rule-based methods?
All, except 'must be implicit'
A machine learning engineer is preparing a data frame for a supervised learning task. The ML engineer notices the target label classes are highly imbalanced and multiple feature columns contain missing values. The proportion of missing values across the entire data frame is less than 5%. What should the ML engineer do to minimize bias due to missing values?
For each feature, approximate the missing values using supervised learning based on other features.
What is the data type of the iris variable shown in the below code?

from sklearn import datasets
import numpy as np
import pandas as pd
iris = datasets.load_iris()
sklearn.utils.Bunch
What is the most important difference between batch gradient descent, mini-batch gradient descent, and stochastic gradient descent?
Number of samples used
Bagging in integrated learning, the relationship between each base learner is?
Relationship
The model composed of machine learning algorithms cannot represent the true data distribution function on a theoretical level. It will just approach it.
True
As the number of training examples goes to infinity, your model trained on that data will have:
Lower variance
When the feature space is larger, over fitting is more likely.
True
A regularization term can also be added to logistic regression to avoid overfitting.
True
L1 with L2 Regularization is a method commonly used in traditional machine learning to reduce generalization errors. Which of the following statements about L1 and L2 regularization is correct?
L1 Regularization can do feature selection
The loss function of logistic regression is the cross-entropy loss function.
True
The Naive Bayes algorithm does not require independent and identical distribution among sample features.
False
If a model has a large deviation on the test set and a small variance, it means that the model is __________.
Underfitting
The training error will continue to decrease as the model complexity increases.
True
In the Bayesian formula

P(W|X) = P(X|W) * P(W) / P(X)

Which of the following is the correct description?
P(X|W) is a conditional probability
It is a higher dimensional generalization of a line in 2D space or a plane in 3D space
hyperplane
Deep learning is a branch of machine learning
True
In polynomial regression, there is a square term in the formula of the model, so it is not linear.
False
The label predicted by the regression algorithm is?
...
Students also viewed