This release is 229 versions behind 0.166.0 — the latest version of @stsoftware/neat-ai. Jump to latest
@stsoftware/neat-ai@0.76.2Built and signed on GitHub ActionsBuilt and signed on GitHub Actions
Built and signed on GitHub Actions
NEAT Neural Network. This project is a unique implementation of a neural network based on the NEAT (NeuroEvolution of Augmenting Topologies) algorithm, written in DenoJS using TypeScript.
c
Creature
Creature Class
- DEBUG
- activate
- activateAndTrace
- addBackConn
- addConnection
- addNeuron
- addSelfCon
- applyLearnings
- binarySearchForStartIndex
- cacheFrom
- cacheSelf
- cacheTo
- clearCache
- clearState
- compact
- connect
- disconnect
- dispose
- evaluateData
- evaluateDir
- evolveDataSet
- evolveDir
- exportJSON
- fix
- fromJSON
- getSynapse
- inFocus
- initialize
- input
- insertNeuron
- internalJSON
- inwardConnections
- loadFrom
- makeRandomConnection
- modActivation
- modBias
- modWeight
- mutate
- neurons
- nodeCount
- output
- outputCount
- outwardConnections
- propagate
- propagateUpdate
- score
- selfConnection
- state
- subBackConn
- subConnection
- subNeuron
- subSelfCon
- swapNodes
- synapses
- tags
- traceJSON
- uuid
- validate
- writeCreatures
I
CreatureExport
Export representation of a creature, including its synapses and neurons.
I
CreatureTrace
Trace representation of a creature, including detailed trace information for synapses and neurons.
c
I
CrisprInterface
Interface representing the structure of the CRISPR modification data.
v
Mutation
Mutation strategies used in genetic algorithms.
I
NeatOptions
Interface for NEAT (NeuroEvolution of Augmenting Topologies) training options.
v