One-hot encoding
Topic of Networks in practice, part of Statistical learning
One-hot encoding
| Type | Topic |
| Taught in | Networks in practice |
| Part | Statistical learning |
Coding a categorical variable with K levels as K indicator variables, exactly one of which is 1. A network with a softmax output is trained against this coding; for predictors in a linear model one level is usually dropped to avoid redundancy.
In Networks in practice
From Networks in practice
Let the target be a one-hot vector y, with y_k=1 for the true class c, and let the loss be
E=-\sum_{k=1}^{m} y_k\ln s_k=-\ln s_c.
Used in
See also
Output coding, softmax, and cross-entropy · Cross-entropy · Softmax is multinomial logistic regression · What has to be settled before a step · Weight initialisation · Variance argument for weight initialisation · Batch and online learning · Preparing data for a network