|
|
| (38 intermediate revisions by the same user not shown) |
| Line 1: |
Line 1: |
| − | ==Introduction== | + | <gallery mode="packed"> |
| − | A false negative (FN), in machine learning, is a type error that occurs when a model incorrectly classes a sample as negative even though it is actually positive. A false negative (FN) is when a model fails identify a positive sample.
| + | File:ZYBER_Charging_Dock_for_Meta_Quest_2_image1.jpg |
| − | | + | File:ZYBER_Charging_Dock_for_Meta_Quest_2_image2.jpg |
| − | FNs are especially important in certain applications, such as medical diagnosis or fraud detection, where it is costly to fail to identify positive samples.
| + | File:ZYBER_Charging_Dock_for_Meta_Quest_2_image3.jpg |
| − | | + | File:ZYBER_Charging_Dock_for_Meta_Quest_2_image4.jpg |
| − | ==Examples==
| + | File:ZYBER_Charging_Dock_for_Meta_Quest_2_image5.jpg |
| − | In a medical diagnosis scenario, a FN could occur when a model that is supposed to identify patients with a specific disease incorrectly classifies a patient's health as healthy, when in fact they have the disease. This could result in the patient not receiving the treatment they need, which could have severe consequences.
| + | File:ZYBER_Charging_Dock_for_Meta_Quest_2_image6.jpg |
| − | | + | </gallery> |
| − | A fraud detection scenario would see a FN if a model that is designed to detect fraudulent transactions incorrectly classifies a fraudulent deal as legitimate. This could result in financial loss as the fraudulent transaction is approved.
| |
| − | | |
| − | ==Measures==
| |
| − | There are many measures that can be used to assess the performance of a model, including the false positive rate (FNR), and the false discovery (FDR).
| |
| − | | |
| − | FNR is the sum of the total number positive samples and the number of FNs. It is the percentage of positive samples incorrectly classified as being negative.
| |
| − | | |
| − | The FDR is the sum of the number of FNs and the total number that were predicted to be positive. It is the percentage of negative samples that are incorrectly classified to be positive.
| |
| − | | |
| − | ==Explain Like I'm 5 (ELI5)==
| |
| − | False negatives are when a computer claims something is false when it is actually true. A false negative is when a computer claims that a person isn't sick, but in fact they are. This can lead to the person not receiving the medication they need.
| |
