UPDATE RULE PLUGINS

permutation

Update rule plugin, replacing the state with its permutation, augmented by the current signal.

Details

Plugin for delay and temporal components.
Not applicable with auto-associative memory (auto).
Transparently handles multiset and inhibitory signals.
Repeated permutation of the temporal state encodes temporal sequences.

Delay component with temporal sequence permutation

The delay component applying the permutation update rule:

{ "hyperparameters": {"default": [1000, 10]},
  "dataflow": [
    {"component": "input", "send": [1]},
    {"component": "delay", "plugin": "permutation", 
        "send": [11], "receive": [1], "capacity": 2, "decay": 0.15},
    {"component": "output", "receive": [11]}
  ]}

Temporal associative memory with state permutation

Used as a plugin for the temporal component, permutation aggregates a state that preserves the order of prior inputs.

{ "hyperparameters": {"default": [1000, 10]},
  "dataflow": [
    {"component": "input", "send": [1]},
    {"component": "temporal", "plugin": "permutation", 
        "send": [11], "receive": [1], "capacity": 2},
    {"component": "output", "receive": [11]}
  ]}

Source code

def permutation(config):
    dims = sum(b[0] for b in config.get("receive_blocks", []))
    dim = dims if dims else 0
    perm = rng.choice(
        range(1, dim + 1),
        size = dim,
        replace=False).tolist() if dim > 0 else []

    def updaterule(y, x):
        mapped_x = sorted([(1 if i > 0 else -1 if i < 0 else 0)
                          * perm[abs(i) - 1] for i in x if i != 0])
        return multiset([y, mapped_x])

    return {"updaterule": updaterule, "label": "π", "size": 16}