Concept
Learning rules
How a system changes its own parameters from experience — the question neuroscience asks about synapses and control engineering asks about adaptive controllers.
From the EE side
From the neuro side
Hebb’s rule, spike-timing-dependent plasticity, and error-driven parameter updates are all answers to one question: given an outcome, which parameters should move, and by how much? A controller that retunes itself and a synapse that strengthens are solving the same problem under different names.
Nearby concepts
All topics under Learning rules
- Reward prediction error 1997 Dopamine neurons signal not reward but the difference between reward received and reward expected — an error signal, of exactly the kind a feedback controller runs on.
- The artificial neuron 1943 Stripping the neuron to a weighted sum and a threshold, which gave engineering a computing element built from biology and is still the unit inside every network built since.