Have an account?
Traditional machine learning and deep learning are the core technologies of artificial
intelligence. There is a slight difference in the engineering process. The following steps. What
you don't need to do in deep learning is:
Which of the following description of the validation set is wrong?
The verification set can coincide with the test set.
The test set can coincide with the training set
The subset used to pick hyperparameters is called a validation set.
Typically 80% of the training data 1s used for training and 20% 1s used for verification.
What are the common clustering algorithms?
All the above
The model composed of machine learning algorithms cannot represent the true data
distribution function on a theoretical level. Just approach it.
What is the performance of artificial intelligence in the stage of perceptual intelligence?
Machines begin to understand, think and make decisions like humans.
Machines begin to calculate and transmit information just like humans.
The machine starts to understand and understand, make judgments, and take some simple actions
Which of the following is true about unsupervised learning?
Unsupervised algorithm only processes "features" and does tags.
Dimensionality reduction algorithm is not unsupervised learning
K-means algorithm and SVM algorithm belong lo unsupervised learning.
none of the above.
The training error will continue to decrease as the model complexity increases.
Which of the following statements about supervised learning is correct?
Decision tree is a supervised learning
Supervised learning cannot use cross-validation for training.
Supervised learning is a rule-based algorithm
Supervised learning can be trained without labels
Jobs that are repetitive and require weak social skills are the easiest to be AI Replaced work.
Reducing the gap between the training error and the test error will result in over-fitting How to
All the above.
The test error will keep getting smaller as the complexity of the model increases.
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?
Decision tree generation
What does factors that promote the development of artificial intelligence not include?
In machine learning, what input the model needs to train itself and predict the unknown?
What does not belong to supervised learning?
Support vector machine
Princi1pal component analysis
Training error will reduce the accuracy of the model and produce under-fitting. How to improve the model fit?
a. Increase the amount of data
c.Reduce regularization parameters
.Among machine learning algorithms, which of the following is not unsupervised
Which description is wrong about the hyperparameter?
hyperparameters are parameters that set values before the algorithm begins learning.
Most machine learning algorithms have hyperparameters.
Hyperparameters cannot be modified
The value of the hyperparameter is not learned by the algorithm itself.