Skip to main content

AlwaysOnDetectorTargetsScenario

Data scenarios · Implementation: mlsysim/engine/scenario_definitions/data.py.

Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.

An always-on detector’s product contract: what it must catch, how rarely it may wake falsely, what it may occupy on the device, and the data budget and schedule that must deliver it.

Notes

Equation: this record declares detection, false-alarm, memory, time, and cost constraints without computing achieved performance.

Assumptions: Targets are supplied product requirements; memory and time budgets carry units.

Excludes: A solver proving these targets are jointly achievable or an empirical validation of detection quality.

References

Derivation: this record declares detection, false-alarm, memory, time, and cost constraints without computing achieved performance. The individual properties state units and intermediate accounting; this class introduces no fitted coefficient.

Examples

The named scenario supplies illustrative requirements; this reads its declared target.

>>> from mlsysim import Scenarios
>>> case = Scenarios.KeywordSpotterTargets
>>> round(float(case.detection_target), 3)
0.98

Attributes

Name Description
base_detection_rate
data_budget
detection_target
false_wake_budget
false_wake_horizon
model_memory
preprocessing_memory
response_limit
timeline

detection_target

Type: float.

Declared default: required.

false_wake_budget

Type: float.

Declared default: required.

false_wake_horizon

Type: Quantity.

Declared default: required.

response_limit

Type: Quantity.

Declared default: required.

model_memory

Type: Quantity.

Declared default: required.

preprocessing_memory

Type: Quantity.

Declared default: required.

data_budget

Type: Quantity.

Declared default: required.

timeline

Type: Quantity.

Declared default: required.

base_detection_rate

Type: float.

Declared default: required.

Back to top