v2.4.1e

Patches

• isEs6 missing cases of non-minified es6 methods.
• Removed deprecated & commented out Dann.prototype.save & Dann.prototype.load methods in unminified build.

v2.4.1c

Fixes

• Dann.prototype.toFunction es6 activation functions fixes for browser & node, pointed out by #48.

• Activation functions names are now all lowercase, and activation names specified by the user are passed through name.toLocaleLowerCase which allows for mixed cases and backwards compatibility. Feature implemented by @and1can through issue #44

• Removed Dann.prototype.losses since it was used to store loss values if the saveLoss option was set to true when calling Dann.prototype.backpropagate. This feature did not need to be built in the library, the prefered way to achieve something like this would be:

let savedLosses = [];
for (...) {
  nn.backpropagate(input, output);
  savedLosses.push(nn.loss);
}

This allows more control on when to save a loss, as opposed to always have to save a loss value when Dann.prototype.backpropagate is called with saveLoss ticked to true.

v2.4.0

Changes

• Added asLabel option for feedForward and feed.

nn.feed([1, 1]) // Outputs an array
nn.feed([1, 1], { asLabel: true }) // Outputs the index of the largest output value

• Changed exports, Classes are now capitalized, old uncapitalized names are still available for old code support.

v2.3.14

Changes

• Cleaner Dann.prototype.log, Dann.prototype.feedForward, Dann.prototype.backpropagate methods.
• Added a validity check system to work with the error handling.
• Restored logo in manual browser tests
• Added a static Dann.print method to print either as a log or table. Instead of using console.log & console.table in if statements.

v2.3.13

Changes

• Removed duplicate function fromJSON
• Added social icons in readme

v2.3.12

Bug fix

• Fixed Dann.prototype.log null values

Dropout Update

Changes

• Options now use less conditionals
• Added a new dropout option, which allows you to set a value in between 0 and 1 to determine the chance of a neuron being idle during a backward pass.

Here is an example with 10% chance a neuron becomes inactive

nn.backpropagate([your_inputs],[your_outputs],{ dropout : 0.1 });

Dropout

v2.2.11

Changes

• Added quantile loss function & support for a percentile value.
  Here is documentation about loss functions, including quantile loss

Dev changes

• Fixed missing sig task
• Added unit tests for quantile loss & percentile value.

v2.2.10

Changes

• Added makeXOR method which allows for the creation of X inputs XOR datasets
• Added Dann.prototype.feed alias for Dann.prototype.feedForward
• Added Dann.prototype.train alias for Dann.prototype.backpropagate

Dev changes

• Fixed dev dependencies

v2.2.9

v2.2.9

Changes

• Added Add class
  • Add.activation allows the user to add custom activation functions
  • Add.loss allows the user to add custom loss functions

Add documentation can be found here

Dev changes

• Added grunt tasks for documentation build
• Added unit tests for Add and its methods