Module ai_optimized 

Compatibility facade for bounded AI-optimised neuron modules.

Modules

adaptive_threshold_moe_neuron 🔒

arcane_neuron 🔒

attention_gated_neuron 🔒

compositional_binding_neuron 🔒

continuous_attractor_neuron 🔒

differentiable_surrogate_neuron 🔒

hybrid_linear_attention_neuron 🔒

meta_plastic_neuron 🔒

multi_timescale_neuron 🔒

predictive_coding_neuron 🔒

quantum_inspired_lif_neuron 🔒

self_referential_neuron 🔒

Structs

AdaptiveThresholdMoENeuron

Adaptive threshold spiking neuron matching the SpikingBrain architecture.

ArcaneNeuron

ArcaneNeuron — unified self-referential cognition model.

AttentionGatedNeuron

Spiking neuron with learned sigmoid attention gate. gate = sigmoid(w_key * I + w_query * v), modulates input before integration.

CompositionalBindingNeuron

Phase-coding neuron for compositional variable binding. Spike when amplitude * cos(phase) > threshold.

ContinuousAttractorNeuron

Ring attractor for continuous working memory. Mexican hat connectivity; holds a continuous value in persistent activity.

DifferentiableSurrogateNeuron

Spiking neuron with learnable surrogate gradient parameters. alpha (decay), beta (steepness), theta (threshold) all trainable.

HybridLinearAttentionNeuron

Hybrid linear attention neuron for spiking environments.

MetaPlasticNeuron

Neuron with self-regulating meta-learning rate. error_trace adapts learning speed: high error → learn faster, low error → stabilize.

MultiTimescaleNeuron

Three-compartment memory neuron (fast/medium/slow timescales). Slow compartment accumulates context, modulating excitability.

PredictiveCodingNeuron

Fires only on prediction errors. Silent when input matches prediction.

QuantumInspiredLIFNeuron

Quantum-inspired LIF neuron with non-classical probability logic.

SelfReferentialNeuron

Introspects on its own spike history; adjusts tau based on firing rate.