Reference library
Differentiable plasticity: training plastic neural networks with backpropagation
Paper summary
Makes Hebbian plasticity differentiable so gradient-based outer training can optimize plastic-network parameters. Recurrent networks then change connection state during new tasks, with memory, meta-learning, and reinforcement-learning demonstrations.
Relevance to the project
A baseline separating fixed control parameters from mutable lifetime state. Useful for comparison with an evolved shared updater of per-neuron F.
External backpropagation and benchmark objectives are not adopted.
Source record
- Reference ID
- pmlr-miconi18a
- Archived version
- Publisher/institution PDF advertised by article metadata
- Summary provenance
- reference-library/papers/pmlr-miconi18a/metadata.json · summary
- Review status
- initial orientation summary; not a critical full-paper review
- Reading scope
- Selected abstract/opening and available closing discussion/conclusion passages in the preserved text extract; broader project notes provide context. No reproduction of experiments, exhaustive methods review, or equation/figure audit.