heukarya alternatives and similar packages
Based on the "AI" category.
Alternatively, view heukarya alternatives based on common mentions on social networks and blogs.
-
-
-
tensor-safe
A Haskell framework to define valid deep learning models and export them to other frameworks like TensorFlow JS or Keras. -
moo
Genetic algorithm library for Haskell. Binary and continuous (real-coded) GAs. Binary GAs: binary and Gray encoding; point mutation; one-point, two-point, and uniform crossover. Continuous GAs: Gaussian mutation; BLX-α, UNDX, and SBX crossover. Selection operators: roulette, tournament, and stochastic universal sampling (SUS); with optional niching, ranking, and scaling. Replacement strategies: generational with elitism and steady state. Constrained optimization: random constrained initialization, death penalty, constrained selection without a penalty function. Multi-objective optimization: NSGA-II and constrained NSGA-II. -
-
-
HaVSA
HaVSA (Have-Saa) is a Haskell implementation of the Version Space Algebra Machine Learning technique described by Tessa Lau. -
Etage
A general data-flow framework featuring nondeterminism, laziness and neurological pseudo-terminology.
CodeRabbit: AI Code Reviews for Developers
* Code Quality Rankings and insights are calculated and provided by Lumnify.
They vary from L1 to L5 with "L5" being the highest.
Do you think we are missing an alternative of heukarya or a related project?
README
HEuyarka
A Strong Typed Genetic Programming Library It based on Data.Dynamic and tree container, so that Gene can represent both haskell functions and syntax trees by type connstructors. since it also supports higher order functions by multiple way type parsing, there's no need to have any variable in Gene's Tree structure.
take a look at module AI.Heukarya.Center first
AI.Heukarya.Gene : Abstract Gene manipulation and Typeclass for implementing data types under tree structure
AI.Heukarya.Jungle : Operating Collections of Gene
AI.Heukarya.Center : Module which wraps main functionality for library using
AI.Heukarya.Gene.Dynamic : one of Gene's implementation. since it's impossible to save checkpoints if using Data.Dynamic directly, a symbolic wrapper around dynamic is provied inside
AI.Heukarya.Gene.Dynamic.Double : a sample geneList of operators of Double precision numbers
TODO :
- AI.Heukarya.Island : let creatures can across the sea between islands. flood fill points' ip address through points, distributed computing.
- maybe use 'plugins' and 'haskell-src' to evolve haskell codes