API reference

Synaptic efficacy banks

Signatures, parameters, return contracts, and source for synaptic efficacy banks.

Overview

An efficacy bank contains one positive multiplier for each retained incoming E/I contact slot. The retained width is 2*ceil(channels_per_role/recurrent_stride). W8 storage quantizes deviation around a positive baseline with one shared scale; dequantization reconstructs floating-point multipliers.

Source revision: caef7be03abd. Public export index.

QuantizedSynapticEfficacyBank

axosim.synapse.QuantizedSynapticEfficacyBank(values: torch.Tensor, scale: torch.Tensor, channels_per_role: int, recurrent_stride: int, baseline: float = 1.0)

Source

One W8 multiplicative efficacy for every retained incoming contact.

Parameters

values torch.Tensor
required. Physical quantized values, interpreted using the bank's scale and layout metadata.
scale torch.Tensor
required. Multiplicative normalization or reconstruction scale.
channels_per_role int
required. Available contact-channel slots for each E/I role.
recurrent_stride int
required. Stride selecting retained contact slots.
baseline float
default=1.0. Positive shared reference efficacy for deviation quantization.

Attributes

Constructor fields are retained as read-only attributes.

Read-only attributes

QuantizedSynapticEfficacyBank.population_size: int
Number of persistent neurons. Source
QuantizedSynapticEfficacyBank.values_per_neuron: int
Logical retained-contact multiplier count per neuron. Source
QuantizedSynapticEfficacyBank.storage_bytes: int
Physical bank storage, including quantized values and reconstruction scales. Source

retained_synaptic_efficacies_per_neuron

axosim.synapse.retained_synaptic_efficacies_per_neuron(*, channels_per_role: int, recurrent_stride: int) -> int

Source

Return compact E/I contact slots for the declared routed topology.

Parameters

channels_per_role int
keyword-only, required. Available contact-channel slots for each E/I role.
recurrent_stride int
keyword-only, required. Stride selecting retained contact slots.

Returns

int

quantize_synaptic_efficacies

axosim.synapse.quantize_synaptic_efficacies(efficacies: torch.Tensor, *, channels_per_role: int, recurrent_stride: int, baseline: float=1.0) -> QuantizedSynapticEfficacyBank

Source

Quantize positive per-contact multipliers around a shared baseline.

efficacies is floating-point (N,2*ceil(channels_per_role/recurrent_stride)) with all values positive. Returns a W8 bank containing int8 values, one colocated floating scale, topology metadata, and positive baseline.

Parameters

efficacies torch.Tensor
required. Positive floating-point contact multipliers, shaped by the retained topology.
channels_per_role int
keyword-only, required. Available contact-channel slots for each E/I role.
recurrent_stride int
keyword-only, required. Stride selecting retained contact slots.
baseline float
keyword-only, default=1.0. Positive shared reference efficacy for deviation quantization.

Returns

bank QuantizedSynapticEfficacyBank
W8 values, one shared scale, positive baseline, and retained topology metadata.

Examples

Quantize a unit-efficacy bank with four retained slots per E/I role.

import torch
from axosim.synapse import quantize_synaptic_efficacies

bank = quantize_synaptic_efficacies(
    torch.ones(2, 8), channels_per_role=4, recurrent_stride=1
)
print(bank.values.shape, bank.values.dtype)
torch.Size([2, 8]) torch.int8

dequantize_synaptic_efficacies

axosim.synapse.dequantize_synaptic_efficacies(bank: QuantizedSynapticEfficacyBank) -> torch.Tensor

Source

Materialize a W8 efficacy bank for training checks or export.

Returns floating-point (N,K) values reconstructed as bank.values*bank.scale+bank.baseline. Validates the bank’s layout and scale device.

Parameters

bank QuantizedSynapticEfficacyBank
required. Quantized bank including its scale and layout metadata.

Returns

efficacies torch.Tensor
Reconstructed floating-point contact multipliers with shape (population, retained_contacts).

Search guides, examples, and API signatures.