Underfitting
Topic of Networks in practice, part of Statistical learning
Underfitting
| Type | Topic |
| Taught in | Networks in practice |
| Part | Statistical learning |
A model too simple, trained too little, or given too little data to capture the structure, so that the error is high on the training data and on new data alike.
In Networks in practice
From Networks in practice
Underfitting. The model is not a good fit to the training data. The size of E is a good indication. The model may be too simple, there may not be enough data, or the data may be so noisy that the output can never be predicted very accurately.
Used in
- Taught in Networks in practice
- Also used in Backpropagation
- All 7 questions on Networks in practice
See also
Training set · 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 · Output coding, softmax, and cross-entropy