--- !ruby/object:Gem::Specification
name: associative_memory
version: !ruby/object:Gem::Version
  version: 0.2.0
  prerelease: 
platform: ruby
authors:
- Dann Stayskal
autorequire: 
bindir: bin
cert_chain: []
date: 2012-04-25 00:00:00.000000000Z
dependencies:
- !ruby/object:Gem::Dependency
  name: rdoc
  requirement: &16462500 !ruby/object:Gem::Requirement
    none: false
    requirements:
    - - ~>
      - !ruby/object:Gem::Version
        version: '3.10'
  type: :development
  prerelease: false
  version_requirements: *16462500
- !ruby/object:Gem::Dependency
  name: newgem
  requirement: &16462040 !ruby/object:Gem::Requirement
    none: false
    requirements:
    - - ! '>='
      - !ruby/object:Gem::Version
        version: 1.5.3
  type: :development
  prerelease: false
  version_requirements: *16462040
- !ruby/object:Gem::Dependency
  name: hoe
  requirement: &16461600 !ruby/object:Gem::Requirement
    none: false
    requirements:
    - - ~>
      - !ruby/object:Gem::Version
        version: '3.0'
  type: :development
  prerelease: false
  version_requirements: *16461600
description: ! 'This is a ruby gem that lets you implement categorization systems
  with ease.


  **Associative memory neural networks** make it easy to identify probable patterns
  between sets of named data points.  It can be cumbersome to interface with the neural
  network directly, however, as a typical convergence matrix has a fixed size and
  training period, which limits how useful they can be to an integrated system.


  associative_memory simplifies these kind of machine learning models by offering
  dynamically configurable input and output sets, and a convergence model that adapts
  to the inputs you give it each time.  This allows your code to concentrate on extrapolating
  meaningful patterns rather than juggling bitmasks and transposition matrices.


  Under the hood, associative_memory implements a hetero-associative recurrent neural
  network designed according to Kosko''s landmark paper (http://sipi.usc.edu/~kosko/BAM.pdf)
  establishing the model.  The model then dynamically rebuilds and adapts this network
  to accomodate new inputs as necessary.'
email:
- dann@stayskal.com
executables: []
extensions: []
extra_rdoc_files:
- History.txt
- Manifest.txt
- README.rdoc
files:
- .rspec
- .rvmrc
- Gemfile
- Gemfile.lock
- Guardfile
- History.txt
- Manifest.txt
- README.rdoc
- Rakefile
- lib/associative_memory.rb
- lib/associative_memory/network.rb
- spec/associative_memory/network_spec.rb
- spec/associative_memory_spec.rb
- spec/spec_helper.rb
- .gemtest
homepage: http://dann.stayskal.com/software/associative_memory
licenses: []
post_install_message: 
rdoc_options:
- --main
- README.rdoc
require_paths:
- lib
required_ruby_version: !ruby/object:Gem::Requirement
  none: false
  requirements:
  - - ! '>='
    - !ruby/object:Gem::Version
      version: '0'
required_rubygems_version: !ruby/object:Gem::Requirement
  none: false
  requirements:
  - - ! '>='
    - !ruby/object:Gem::Version
      version: '0'
requirements: []
rubyforge_project: associative_memory
rubygems_version: 1.8.15
signing_key: 
specification_version: 3
summary: This is a ruby gem that lets you implement categorization systems with ease
test_files: []