Week8测验：Anomaly Detection【Maching Learning】

1、

For which of the following problems would anomaly detection be a suitable algorithm?

A、Given an image of a face, determine whether or not it is the face of a particular famous individual.

B、Given a dataset of credit card transactions, identify unusual transactions to flag them as possibly fraudulent.

正确

By modeling "normal" credit card transactions, you can then use anomaly detection to flag the unusuals ones which might be fraudulent.

C、Given data from credit card transactions, classify each transaction according to type of purchase (for example: food, transportation, clothing).

D、From a large set of primary care patient records, identify individuals who might have unusual health conditions.

正确

Since you are just looking for unusual conditions instead of a particular disease, this is a good application of anomaly detection.

正确答案：BD

2、For which of the following problems would anomaly detection be a suitable algorithm?

A、Given data from credit card transactions, classify each transaction according to type of purchase (for example: food, transportation, clothing).

B、From a large set of primary care patient records, identify individuals who might have unusual health conditions.

正确

Since you are just looking for unusual conditions instead of a particular disease, this is a good application of anomaly detection.

C、Given an image of a face, determine whether or not it is the face of a particular famous individual.

这个选项的答案不正确

This problem is more suited to traditional supervised learning, as you want both famous and non-famous images in the training set.

D、Given a dataset of credit card transactions, identify unusual transactions to flag them as possibly fraudulent.

正确

By modeling "normal" credit card transactions, you can then use anomaly detection to flag the unusuals ones which might be fraudulent.

正确答案：BD

4.第 4 个问题

4、Which of the following are true? Check all that apply.

A、If you are developing an anomaly detection system, there is no way to make use of labeled data to improve your system.

B、If you do not have any labeled data (or if all your data has label y=0y=0y=0), then is is still possible to learn p(x)p(x)p(x), but it may be harder to evaluate the system or choose a good value of ϵ.

正确

Only negative examples are used in training, but it is good to have some labeled data of both types for cross-validation.

C、When choosing features for an anomaly detection system, it is a good idea to look for features that take on unusually large or small values for (mainly the) anomalous examples.

正确

These are good features, as they will lie outside the learned model, so you will have small values for p(x)p(x)p(x) with these examples.

D、If you have a large labeled training set with many positive examples and many negative examples, the anomaly detection algorithm will likely perform just as well as a supervised learning algorithm such as an SVM

正确答案：BC

4.第 4 个问题

Which of the following are true? Check all that apply.

A、When developing an anomaly detection system, it is often useful to select an appropriate numerical performance metric to evaluate the effectiveness of the learning algorithm.

B、In a typical anomaly detection setting, we have a large number of anomalous examples, and a relatively small number of normal/non-anomalous examples.

C、When evaluating an anomaly detection algorithm on the cross validation set (containing some positive and some negative examples), classification accuracy is usually a good evaluation metric to use.

D、In anomaly detection, we fit a model p(x)p(x)p(x) to a set of negative (y=0y=0y=0) examples, without using any positive examples we may have collected of previously observed anomalies.

正确

We want to model "normal" examples, so we only use negative examples in training.

正确答案：AD