initlay

(To be removed) Layer-by-layer network initialization function

initlay will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

net = initlay(net)
info = initlay('code')


Description

initlay is a network initialization function that initializes each layer i according to its own initialization function net.layers{i}.initFcn.

net = initlay(net) takes

net	Neural network

and returns the network with each layer updated.

info = initlay('code') returns useful information for each supported code character vector:

'pnames'	Names of initialization parameters
'pdefaults'	Default initialization parameters

initlay does not have any initialization parameters.

Network Use

You can create a standard network that uses initlay by calling feedforwardnet, cascadeforwardnet, and many other network functions.

To prepare a custom network to be initialized with initlay,

1. Set net.initFcn to 'initlay'. This sets net.initParam to the empty matrix [], because initlay has no initialization parameters.

2. Set each net.layers{i}.initFcn to a layer initialization function. (Examples of such functions are initwb and initnw.)

To initialize the network, call init.

Algorithms

The weights and biases of each layer i are initialized according to net.layers{i}.initFcn.

Version History

Introduced before R2006a

R2026a: initlay will be removed

initlay will be removed in a future release.

To learn more about initializing and customizing neural network learnable parameters, see these examples and topics:

• Compare Layer Weight Initializers

• Specify Custom Weight Initialization Function

• Neural Network Weight Tying

• Initialize Learnable Parameters for Model Function

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.