v0.1.15

• Added a simple RNN (i.e.: Ai4cr::NeuralNetwork::Cmn::RnnSimple)
• Misc fixes, refactoring, and cleanup
• TODO: Add code to collect and train (i.e.: loop thru) a sequence of data ... probably next PR

0.1.13 prep for Crystal 1.0.0

• update dependencies that are Crystal 1.0 compatible (ascii_bar_charter)
• disable dependencies that are Crystal 1.0 compatible (ameba)
• Change required Crystal version to 1.0 (shard.yml, .crystal-version)
• version bump this repo from 0.1.12 to 0.1.13

Version 0.1.11

• More MiniNet tests and benchmarks
• Remove deprecated Backpropagation#marshal_dump and Backpropagation#marshal_load

Version 0.1.10

• update README based on 0.1.9 mods
• formatting

Version 0.1.9

• Roadmap added (as of v 0.1.8)
• Initial classes for Cmn ("Connectable Mini Networks")
• Generate an error history plot using AsciiBarCharter and error_distance_history , e.g.:

plot: '▇▊▂_▅▅▅_▅_▅▅▅▅_▅▅__▅_▅____▅___'

(Run crystal spec spec_examples to see more error history plot examples. NOTE: These run short training sessions, so some tests are likely to fail some of the time.)

Version 0.1.7

Drhuffman12/upgrade to crystal 0 32 1 (#32)

* bump Crystal version to 0.32.1

* add cleaner build notes

* crystal tool format

* doc re reformat

* misc scripts

0.1.3

• Fix CircleCI config
• Dockerize

Initial release

Ai4cr::NeuralNetwork::Backpropagation and related tests have been ported