Learning Tab
Hebbian learning is a principle grounded in the functioning of biological neural networks
The Learning Tab focuses on the Hebbian learning principle: "neurons that fire together, wire together."
This tab visualizes neuron pairs that were selected for learning (happens every 30 seconds by default) The connection strength between them (weight) was either strengthened or weakened, meaning they became more or less associated with each other.
For example: if Hunger and Satisfaction both happened to be firing at the same time (perhaps the squid just had a positive eating experience) these two neurons would have their connection strengthened when the counter reaches zero
Over time the same useful connections will keep strengthening and strong pathways will develop. This is how the squid 'learns' favourable behaviours
External links
- 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