Plasticity
Generated with Grok Build: Grok 4.5 · xAI Imagine (/imagine)
Module: hebbian (apply_classical_stdp, StdpParams, HebbianIzhikevichNetwork)
Pre-before-post → LTP; post-before-pre → LTD (standard timing rules).
Example: cargo run --example hebbian_learning.
Module: rm_stdp
| Symbol | Role |
|---|---|
EligibilityTrace |
Standalone eligibility / credit buffer (not auto-wired into engine apply_stdp) |
RmStdpConfig |
Config |
RM_STDP_TAU_PLUS/MINUS |
Time constants (default 20) |
RM_STDP_A_PLUS/MINUS |
Amplitudes (0.01 / 0.012) |
RM_STDP_W_MIN/MAX |
Weight clamps |
EligibilityTrace::decay is unit-tested (coverage added post-0.5.0 tag in #62).
Engine STDP paths during step are influenced by modulator state (e.g. dopamine gating). Full training loops live in plasticity-lab / SynapticDistill.jl — neuromod only provides primitives.
Example: cargo run --example rstdp_demo.
Last updated: August 12, 2026
Updated by: Grok Build: Grok 4.5 (high)
Package tip reference: 328ea9c (main @ 0.5.2 + #97/#98; tag v0.5.2 = ef9fba8)
Cubic: page-intro
Devin DeepWiki: neuromod @ 328ea9c