1. Test Modules
  2. Differential Validation
    1. Feedback Validation
    2. Learning Validation
    3. Total Accuracy
    4. Frozen and Alive Status
  3. Results

Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase

Test Modules

Using Seed 6620053956704227328

Differential Validation

SingleDerivativeTester.java:101 executed in 0.00 seconds (0.000 gc):

        log.info(RefString.format("Inputs: %s", prettyPrint(inputPrototype)));
        log.info(RefString.format("Inputs Statistics: %s", printStats(inputPrototype)));
        log.info(RefString.format("Output: %s", outputPrototype.prettyPrint()));
        assert outputPrototype != null;
        log.info(RefString.format("Outputs Statistics: %s", outputPrototype.getScalarStatistics()));
      },
      outputPrototype.addRef(),
      RefUtil.addRef(inputPrototype)));
Logging
Inputs: [ 0.08 ]
Inputs Statistics: {meanExponent=-1.0969100130080565, negative=0, min=0.08, max=0.08, mean=0.08, count=1, sum=0.08, positive=1, stdDev=0.0, zeros=0}
Output: [ 0.08 ]
Outputs Statistics: {meanExponent=-1.0969100130080565, negative=0, min=0.08, max=0.08, mean=0.08, count=1, sum=0.08, positive=1, stdDev=0.0, zeros=0}

Feedback Validation

We validate the agreement between the implemented derivative of the inputs apply finite difference estimations:

SingleDerivativeTester.java:117 executed in 0.02 seconds (0.000 gc):

        return testFeedback(
            statistics,
            component.addRef(),
            RefUtil.addRef(inputPrototype),
            outputPrototype.addRef());
      },
      outputPrototype.addRef(),
      RefUtil.addRef(inputPrototype),
      component.addRef()));
Logging
Feedback for input 0
Inputs Values: [ 0.08 ]
Value Statistics: {meanExponent=-1.0969100130080565, negative=0, min=0.08, max=0.08, mean=0.08, count=1, sum=0.08, positive=1, stdDev=0.0, zeros=0}
Implemented Feedback: [ [ 1.0 ] ]
Implemented Statistics: {meanExponent=0.0, negative=0, min=1.0, max=1.0, mean=1.0, count=1, sum=1.0, positive=1, stdDev=0.0, zeros=0}
Measured Feedback: [ [ 1.0000000000000286 ] ]
Measured Statistics: {meanExponent=1.2439824318537225E-14, negative=0, min=1.0000000000000286, max=1.0000000000000286, mean=1.0000000000000286, count=1, sum=1.0000000000000286, positive=1, stdDev=0.0, zeros=0}
Feedback Error: [ [ 2.864375403532904E-14 ] ]
Error Statistics: {meanExponent=-13.542970064227774, negative=0, min=2.864375403532904E-14, max=2.864375403532904E-14, mean=2.864375403532904E-14, count=1, sum=2.864375403532904E-14, positive=1, stdDev=0.0, zeros=0}

Returns

    {
      "absoluteTol" : {
        "count" : 1,
        "sum" : 2.864375403532904E-14,
        "min" : 2.864375403532904E-14,
        "max" : 2.864375403532904E-14,
        "sumOfSquare" : 8.204646452364286E-28,
        "standardDeviation" : 0.0,
        "average" : 2.864375403532904E-14
      },
      "relativeTol" : {
        "count" : 1,
        "sum" : 1.4321877017664317E-14,
        "min" : 1.4321877017664317E-14,
        "max" : 1.4321877017664317E-14,
        "sumOfSquare" : 2.0511616130910136E-28,
        "standardDeviation" : 0.0,
        "average" : 1.4321877017664317E-14
      }
    }

Learning Validation

We validate the agreement between the implemented derivative of the internal weights apply finite difference estimations:

SingleDerivativeTester.java:133 executed in 0.00 seconds (0.000 gc):

        return testLearning(
            statistics,
            component.addRef(),
            RefUtil.addRef(inputPrototype),
            outputPrototype.addRef());
      },
      outputPrototype.addRef(),
      RefUtil.addRef(inputPrototype),
      component.addRef()));

Returns

    {
      "absoluteTol" : {
        "count" : 1,
        "sum" : 2.864375403532904E-14,
        "min" : 2.864375403532904E-14,
        "max" : 2.864375403532904E-14,
        "sumOfSquare" : 8.204646452364286E-28,
        "standardDeviation" : 0.0,
        "average" : 2.864375403532904E-14
      },
      "relativeTol" : {
        "count" : 1,
        "sum" : 1.4321877017664317E-14,
        "min" : 1.4321877017664317E-14,
        "max" : 1.4321877017664317E-14,
        "sumOfSquare" : 2.0511616130910136E-28,
        "standardDeviation" : 0.0,
        "average" : 1.4321877017664317E-14
      }
    }

Total Accuracy

The overall agreement accuracy between the implemented derivative and the finite difference estimations:

SingleDerivativeTester.java:148 executed in 0.00 seconds (0.000 gc):

    //log.info(String.format("Component: %s\nInputs: %s\noutput=%s", component, Arrays.toStream(inputPrototype), outputPrototype));
    log.info(RefString.format("Finite-Difference Derivative Accuracy:"));
    log.info(RefString.format("absoluteTol: %s", statistics.absoluteTol));
    log.info(RefString.format("relativeTol: %s", statistics.relativeTol));
Logging
Finite-Difference Derivative Accuracy:
absoluteTol: 2.8644e-14 +- 0.0000e+00 [2.8644e-14 - 2.8644e-14] (1#)
relativeTol: 1.4322e-14 +- 0.0000e+00 [1.4322e-14 - 1.4322e-14] (1#)

Frozen and Alive Status

SingleDerivativeTester.java:156 executed in 0.01 seconds (0.000 gc):

    testFrozen(component.addRef(), RefUtil.addRef(inputPrototype));
    testUnFrozen(component.addRef(), RefUtil.addRef(inputPrototype));

LayerTests.java:425 executed in 0.00 seconds (0.000 gc):

    throwException(exceptions.addRef());

Results

classdetailsresult
com.simiacryptus.mindseye.test.unit.SingleDerivativeTesterToleranceStatistics{absoluteTol=2.8644e-14 +- 0.0000e+00 [2.8644e-14 - 2.8644e-14] (1#), relativeTol=1.4322e-14 +- 0.0000e+00 [1.4322e-14 - 1.4322e-14] (1#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.159",
      "gc_time": "0.100"
    },
    "created_on": 1586734840052,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.StaticScalarLossLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/StaticScalarLossLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/StaticScalarLossLayer/Basic/derivativeTest/202004124040",
    "id": "3cbeecfa-be59-4a1e-ac41-75e8f6d23b39",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "StaticScalarLossLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.StaticScalarLossLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/StaticScalarLossLayer.java",
      "javaDoc": ""
    }
  }