NETtalk
Section of Networks in practice, part of Statistical learning
NETtalk
| Type | Section |
| Taught in | Networks in practice |
| Part | Statistical learning |
| Questions using it | 1 |
NETtalk is an early example of learning a mapping from written context to a pronunciation code (Sejnowski and Rosenberg, 1986). A window of letters supplies the input and the central letter supplies the prediction target. The architecture with 203 inputs, 80 hidden units and 26 outputs has
(203+1)\,80+(80+1)\,26=18426
weights including biases. This count illustrates how quickly connections accumulate. Weight-decay experiments such as Krogh and Hertz (1992) motivate regularisation. A successful setting in one experiment is not a transferable value of \lambda.
Used in
- Taught in Networks in practice
- Also used in Backpropagation
- Questions that use it (1) — Counting for NETtalk
- All 7 questions on Networks in practice
See also
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 · Constructing and training a network