Home
"What if a Tamagotchi had a neural network and could learn stuff?" — Gigazine
🦑 A transparent cognitive sandbox disguised as a digital pet squid with a neural network you can see thinking
Micro neural engine for small autonomous agents that learn via Hebbian dynamics and grow new structure
A digital cephalopod exhibiting emergent behaviour through artificial neural plasticity.
New to Dosidicus? Start here to understand how to interact with your squid.
- Raising a Neural Network as a Pet
- Care Guide / Getting Started
- Personalities — How different squid types behave.
- Decoration Window — Managing the squid's environment.
- Vision System — Realistic foraging and food detection.
- Hebbian Learning — 30-second learning cycles.
- Spike‐Timing‐Dependent Plasticity (STDP)
- Neurogenesis — How the squid creates new neurons based on environment.
- Decision Engine — Making choices based on hunger, sleep, and memory.
- Engine Overview — High-level system architecture.
- Neural Network: Technical Overview
- Data Flow Summary
- How Dosidicus differs from other systems - a unique form of artificial neurogenesis
- main.py — The main simulation loop.
- tamagotchi_logic.py — Core needs and health management.
- squid.py — The physical squid class.
- Memory System & memory_manager.py — Managing experiences.
Fine-tune the simulation and monitor the squid's neural activity.
- config.ini — Adjusting simulation parameters.
- Save File Format — Structure of persisted data.
- Plugin System — Extending the engine's capabilities.
- https://medium.com/@reutdayan1/hebbian-learning-biologically-plausible-alternative-to-backpropagation-6ee0a24deb00
- https://informatics.ed.ac.uk/sites/default/files/2024-03/Qiuye%20Zhang%20Lovelace%20Colloquium%20Poster.pdf
- https://en.wikipedia.org/wiki/Hebbian_theory
- https://www.youtube.com/watch?v=TvTQQO5yTa4
- https://pmc.ncbi.nlm.nih.gov/articles/PMC7781593/