# ArztSamuel/Applying_EANNs

A 2D Unity simulation in which cars learn to navigate themselves through different courses. The cars are steered by a feedforward neural network. The weights of the network are trained using a modified genetic algorithm.

Repository: https://github.com/ArztSamuel/Applying_EANNs
Canonical: https://ross.abutalabs.com/products/applying_eanns
Language: ASP
License: MIT
License Family: permissive
Topics: artificial-neural-networks, neural-networks, evolutionary-algorithms, genetic-algorithm, deep-learning, machine-learning, self-driving-cars
Last push: 2025-05-23T18:52:00+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 23, release rhythm 35, longevity 100
- inputs: {"age_days": 3433, "days_push": 467, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1571, forks 367 (observed 2026-08-28T04:05:05.422741+00:00)

## What it is
A 2D Unity simulation where cars learn to navigate courses using a feedforward neural network trained by a modified genetic algorithm. It serves as a hands-on educational demo of evolutionary artificial neural networks with tunable parameters in the Unity Editor.

## Use cases
- simulate cars learning to drive through courses with neural networks
- learn how genetic algorithms train neural network weights
- demonstrate evolutionary algorithms in a visual simulation
- experiment with neural network and genetic algorithm parameters in Unity
- teach deep learning and neuroevolution concepts
- extend a genetic algorithm with custom selection and mutation operators

## When to choose
- you want a visual, interactive demo of neuroevolution
- you are learning how genetic algorithms can optimize neural networks
- you want a Unity project to tinker with and extend
- you need an educational example of self-driving car simulation

## When to avoid
- you need production-grade autonomous driving software
- you require gradient-based training like backpropagation
- you need a headless or high-performance training pipeline
- you want a framework or library rather than a self-contained Unity application

## Facets
- artifact type: application
- maturity: stable
- function: machine-learning, simulation, game-engine
- domain: artificial-intelligence, machine-learning, simulation
- platform: windows, cross-platform
- tags: genetic-algorithm, neural-networks, unity, self-driving-cars, evolutionary-algorithms, educational-demo, game-development

## Member repositories
- ArztSamuel/Applying_EANNs (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.422741+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:58:25.018549+00:00, confidence not recorded.
  - readme: https://github.com/ArztSamuel/Applying_EANNs (fetched 2026-08-28T04:05:05.422741+00:00, sha 63d239078ccd)
- Data as of 2026-08-30T08:39:29.467469+00:00.