Skip to content

Accuracy and Error Rate

Jump to bottom Edit New page
Oscar Serra edited this page Feb 21, 2015 · 1 revision

Accuracy and Error Rate

When looking at a binary classifier, the most intuitive measure is accuracy. It tells us the general probability of our classifier to get it right, regardless of whether we are talking about P or N examples. The complementary way to look at it is the error rate, which we want as small as possible.

<math> \textrm{accuracy} = \frac{TP+TN}{TP+TN+FP+FN} = \frac{T}{all} </math>

<math> \textrm{error rate} = \frac{FP+FN}{TP+TN+FP+FN} = \frac{F}{all} </math>

Accuracy and Precision - Wikipedia

Add a custom footer
  1. Machine Learning
    1. Regression
    2. Classification
    3. Ensembling
    4. Evaluation Metrics
    5. Dimensionality Reduction
    6. Neural Networks
    7. Convex Solvers
    8. Unsupervised Learning
  2. Deep Learning
    1. Basic Neural Networks
    2. Multilayer Neural Networks
Clone this wiki locally