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 7689124154073123840

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, 0.7, -0.128 ]
Inputs Statistics: {meanExponent=-0.7148673344486438, negative=1, min=-0.128, max=0.7, mean=0.2173333333333333, count=3, sum=0.6519999999999999, positive=2, stdDev=0.3517018939701949, zeros=0}
Output: [ [ 0.0, 0.055999999999999994, -0.01024 ], [ 0.055999999999999994, 0.0, -0.0896 ], [ -0.01024, -0.0896, 0.0 ] ]
Outputs Statistics: {meanExponent=-1.4297346688972874, negative=4, min=-0.0896, max=0.055999999999999994, mean=-0.009742222222222223, count=9, sum=-0.08768000000000001, positive=2, stdDev=0.04908477604620574, zeros=3}

Feedback Validation

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

SingleDerivativeTester.java:117 executed in 0.03 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, 0.7, -0.128 ]
Value Statistics: {meanExponent=-0.7148673344486438, negative=1, min=-0.128, max=0.7, mean=0.2173333333333333, count=3, sum=0.6519999999999999, positive=2, stdDev=0.3517018939701949, zeros=0}
Implemented Feedback: [ [ 0.0, 0.7, -0.128, 0.7, 0.0, 0.0, -0.128, 0.0, 0.0 ], [ 0.0, 0.08, 0.0, 0.08, 0.0, -0.128, 0.0, -0.128, 0.0 ], [ 0.0, 0.0, 0.08, 0.0, 0.0, 0.7, 0.08, 0.7, 0.0 ] ]
Implemented Statistics: {meanExponent=-0.7148673344486437, negative=4, min=-0.128, max=0.7, mean=0.09659259259259258, count=27, sum=2.6079999999999997, positive=8, stdDev=0.25814312126462213, zeros=15}
Measured Feedback: [ [ 0.0, 0.7000000000000756, -0.1280000000000031, 0.7000000000000756, 0.0, 0.0, -0.1280000000000031, 0.0, 0.0 ], [ 0.0, 0.08000000000001062, 0.0, 0.08000000000001062, 0.0, -0.12799999999993372, 0.0, -0.12799999999993372, 0.0 ], [ 0.0, 0.0, 0.07999999999999327, 0.0, 0.0, 0.7000000000000062, 0.07999999999999327, 0.7000000000000062, 0.0 ] ]
Measured Statistics: {meanExponent=-0.7148673344486675, negative=4, min=-0.1280000000000031, max=0.7000000000000756, mean=0.09659259259260361, count=27, sum=2.6080000000002976, positive=8, stdDev=0.25814312126463224, zeros=15}
Feedback Error: [ [ 0.0, 7.560618797697316E-14, -3.1086244689504383E-15, 7.560618797697316E-14, 0.0, 0.0, -3.1086244689504383E-15, 0.0, 0.0 ], [ 0.0, 1.061650767297806E-14, 0.0, 1.061650767297806E-14, 0.0, 6.628031457012185E-14, 0.0, 6.628031457012185E-14, 0.0 ], [ 0.0, 0.0, -6.7307270867900115E-15, 0.0, 0.0, 6.217248937900877E-15, -6.7307270867900115E-15, 6.217248937900877E-15, 0.0 ] ]
Error Statistics: {meanExponent=-13.859974653330575, negative=4, min=-6.7307270867900115E-15, max=7.560618797697316E-14, mean=1.1028215377943221E-14, count=27, sum=2.97761815204467E-13, positive=8, stdDev=2.5347679706733696E-14, zeros=15}

Returns

    {
      "absoluteTol" : {
        "count" : 27,
        "sum" : 3.371192214274288E-13,
        "min" : 0.0,
        "max" : 7.560618797697316E-14,
        "sumOfSquare" : 2.063141282531149E-26,
        "standardDeviation" : 2.4662294597173438E-14,
        "average" : 1.248589708990477E-14
      },
      "relativeTol" : {
        "count" : 12,
        "sum" : 8.758321449040816E-13,
        "min" : 4.4408920985006064E-15,
        "max" : 2.589074787896055E-13,
        "sumOfSquare" : 1.5257823052358514E-25,
        "standardDeviation" : 8.595286257577697E-14,
        "average" : 7.298601207534013E-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" : 27,
        "sum" : 3.371192214274288E-13,
        "min" : 0.0,
        "max" : 7.560618797697316E-14,
        "sumOfSquare" : 2.063141282531149E-26,
        "standardDeviation" : 2.4662294597173438E-14,
        "average" : 1.248589708990477E-14
      },
      "relativeTol" : {
        "count" : 12,
        "sum" : 8.758321449040816E-13,
        "min" : 4.4408920985006064E-15,
        "max" : 2.589074787896055E-13,
        "sumOfSquare" : 1.5257823052358514E-25,
        "standardDeviation" : 8.595286257577697E-14,
        "average" : 7.298601207534013E-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: 1.2486e-14 +- 2.4662e-14 [0.0000e+00 - 7.5606e-14] (27#)
relativeTol: 7.2986e-14 +- 8.5953e-14 [4.4409e-15 - 2.5891e-13] (12#)

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=1.2486e-14 +- 2.4662e-14 [0.0000e+00 - 7.5606e-14] (27#), relativeTol=7.2986e-14 +- 8.5953e-14 [4.4409e-15 - 2.5891e-13] (12#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.180",
      "gc_time": "0.107"
    },
    "created_on": 1586737072376,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.CrossDotMetaLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/CrossDotMetaLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/CrossDotMetaLayer/Basic/derivativeTest/202004131752",
    "id": "2d3685f8-3857-4f61-818d-53114a227a8a",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "CrossDotMetaLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.CrossDotMetaLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/CrossDotMetaLayer.java",
      "javaDoc": ""
    }
  }