v2.0.4

Added dynamic member lookup to MetricsReporter

v2.0.3

Remove dataset protocol and moved to NeuronDatasets

v2.0.2

Drastically reduce size of the Neuron package by moving out unused datasets to a new repo NeuronDatasets.

v2.0.1

Updated NumSwift dependency to tag 2.0.0

v2.0

This is the big one! This is a complete re-write of Neuron! Changed effectively everything.

Please take a look at the README before updating to this version.

It is INCOMPATIBLE with the older versions of Neuron

v1.6.1

Added activation to addDenseNormal

v1.6.0

What's Changed

• Conv by @wvabrinskas in #17

• Added prototype Convolution support. Use with caution as this can potentially use 600+% of the CPU. GPU support coming...
• Refactored a bunch of functions to run concurrently. You might see an increase in CPU usage depending on your training size.
• Added a more robust metrics calculator and system.
• Added the MNIST dataset so the binary size of Neuron has increased due to this.
• Refactored the way Brain is constructed. This will make it a lot easier to create.

Full Changelog: 1.5.1...1.6.0

v1.5.1

• Refactored the way a GAN and WGAN are created
• Fixed Batch Normalizer and Adam optimizer logic
• Cleaned up some unneeded code

v1.5.0

• Drastically increased performance by utilizes Apple's Accelerate framework for matrix multiplication
• Refactored the way back propagation and forward propagation work
• Drastically improved runtime speed by removing overhead when it comes to mapping arrays
• Fixed a bug where optimizers weren't being applied.
• Fixed a bug where mini-batch gradient descent wasn't applied properly

v1.4.5

Migrated out array arithmetic to NumSwift package
Updated tests
Updated BatchNormalizer