Crowdly
Add to Chrome
Data Analytics (Eng) / Data Analitika (Ing) - 344
Looking for Data Analytics (Eng) / Data Analitika (Ing) - 344 test answers and solutions? Browse our comprehensive collection of verified answers for Data Analytics (Eng) / Data Analitika (Ing) - 344 at stemlearn.sun.ac.za.
Get instant access to accurate answers and detailed explanations for your course questions. Our community-driven platform helps students succeed!
A multinomial logistic regression model comprises of 3 one-versus-all models. Two of the one-versus-all models (A and B) have logistic outputs of 0.2 and 0.4, respectively, and the third one-versus-all model (C) has a higher logistic output than models A and B. If the normalized output of the multinomial logistic regression model is 0.5, what is the output of model C?
View this question
True or false? A linear regression model with an L1 error of 0 implies that all predicted values are equivalent to the ground truth values.
100%
0%
View this question
At the end of an epoch of the gradient descent algorithm, a weight w0 is updated to a new value of 1.75. The errorDelta value at the end of the epoch was 2.5 and a learning rate of 0.1 was used. What was the previous value of w0 before the update?
View this question
Given a training set of 1000 instances and a batch size of 200, how many epochs will it take to present each of the 1000 instances in the training set once to a model using batch gradient descent? Write your answer as an integer, not a word.
View this question
True or false? In the context of classifying emails as either spam or not, the bag of words approach can be used to represent emails numerically. In this context using L2 to sum the squared errors rather than just using the sum of the errors, is of no benefit since word counts are always 0 or positive and never negative, hence the risk of negative and positive errors cancelling out does not arise.
0%
100%
View this question
During the pre-processing of a training set for input into linear regression model, the training set is transformed from having 4 continuous and 1 categorical descriptive features, respectively to having 8 descriptive features. How many levels did the categorical descriptive feature have before the transformation?
View this question
In multivariable linear regression, the weight vector w has at least elements.
View this question
True or false? The intercept setting in a linear regression model is a hyper-parameter.
0%
100%
View this question
True or false? f(x) = |x| is not differentiable.
0%
0%
View this question
True or false? A linear regression model with one descriptive feature has a one to one mapping between the descriptive feature value and the target feature value i.e. each descriptive feature value can only lead to one target feature value, and vice versa.
0%
100%
View this question