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 1810818724508116992

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, 0.496 ]
Inputs Statistics: {meanExponent=-0.6122800817139336, negative=1, min=-0.128, max=0.7, mean=0.287, count=4, sum=1.148, positive=3, stdDev=0.3276141022605712, zeros=0}
Output: [ 0.055999999999999994, -0.01024, 0.03968, -0.0896, 0.34719999999999995, -0.063488 ]
Outputs Statistics: {meanExponent=-1.2245601634278669, negative=3, min=-0.0896, max=0.34719999999999995, mean=0.046591999999999995, count=6, sum=0.27955199999999997, positive=3, stdDev=0.1439891195889467, 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, 0.7, -0.128, 0.496 ]
Value Statistics: {meanExponent=-0.6122800817139336, negative=1, min=-0.128, max=0.7, mean=0.287, count=4, sum=1.148, positive=3, stdDev=0.3276141022605712, zeros=0}
Implemented Feedback: [ [ 0.7, -0.128, 0.496, 0.0, 0.0, 0.0 ], [ 0.08, 0.0, 0.0, -0.128, 0.496, 0.0 ], [ 0.0, 0.08, 0.0, 0.7, 0.0, 0.496 ], [ 0.0, 0.0, 0.08, 0.0, 0.7, -0.128 ] ]
Implemented Statistics: {meanExponent=-0.6122800817139334, negative=3, min=-0.128, max=0.7, mean=0.1435, count=24, sum=3.4439999999999995, positive=9, stdDev=0.2725027522796788, zeros=12}
Measured Feedback: [ [ 0.7000000000000756, -0.1280000000000031, 0.4960000000000381, 0.0, 0.0, 0.0 ], [ 0.08000000000001062, 0.0, 0.0, -0.12799999999993372, 0.496000000000385, 0.0 ], [ 0.0, 0.07999999999999327, 0.0, 0.7000000000000062, 0.0, 0.4959999999999687 ], [ 0.0, 0.0, 0.08000000000001062, 0.0, 0.700000000000145, -0.12799999999993372 ] ]
Measured Statistics: {meanExponent=-0.6122800817139232, negative=3, min=-0.1280000000000031, max=0.700000000000145, mean=0.1435000000000318, count=24, sum=3.444000000000763, positive=9, stdDev=0.2725027522797137, zeros=12}
Feedback Error: [ [ 7.560618797697316E-14, -3.1086244689504383E-15, 3.808064974464287E-14, 0.0, 0.0, 0.0 ], [ 1.061650767297806E-14, 0.0, 0.0, 6.628031457012185E-14, 3.850253449400043E-13, 0.0 ], [ 0.0, -6.7307270867900115E-15, 0.0, 6.217248937900877E-15, 0.0, -3.1308289294429414E-14 ], [ 0.0, 0.0, 1.061650767297806E-14, 0.0, 1.4499512701604544E-13, 6.628031457012185E-14 ] ]
Error Statistics: {meanExponent=-13.540772938977755, negative=3, min=-3.1308289294429414E-14, max=3.850253449400043E-13, mean=3.1773773427149856E-14, count=24, sum=7.625705622515966E-13, positive=9, stdDev=8.223193835331213E-14, zeros=12}

Returns

    {
      "absoluteTol" : {
        "count" : 24,
        "sum" : 8.448658439519363E-13,
        "min" : 0.0,
        "max" : 3.850253449400043E-13,
        "sumOfSquare" : 1.8651994471542674E-25,
        "standardDeviation" : 8.082345707377893E-14,
        "average" : 3.5202743497997346E-14
      },
      "relativeTol" : {
        "count" : 12,
        "sum" : 1.3248235873676853E-12,
        "min" : 4.4408920985006064E-15,
        "max" : 3.881303880442085E-13,
        "sumOfSquare" : 3.115661613805353E-25,
        "standardDeviation" : 1.1736802277572126E-13,
        "average" : 1.1040196561397377E-13
      }
    }

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" : 24,
        "sum" : 8.448658439519363E-13,
        "min" : 0.0,
        "max" : 3.850253449400043E-13,
        "sumOfSquare" : 1.8651994471542674E-25,
        "standardDeviation" : 8.082345707377893E-14,
        "average" : 3.5202743497997346E-14
      },
      "relativeTol" : {
        "count" : 12,
        "sum" : 1.3248235873676853E-12,
        "min" : 4.4408920985006064E-15,
        "max" : 3.881303880442085E-13,
        "sumOfSquare" : 3.115661613805353E-25,
        "standardDeviation" : 1.1736802277572126E-13,
        "average" : 1.1040196561397377E-13
      }
    }

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: 3.5203e-14 +- 8.0823e-14 [0.0000e+00 - 3.8503e-13] (24#)
relativeTol: 1.1040e-13 +- 1.1737e-13 [4.4409e-15 - 3.8813e-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=3.5203e-14 +- 8.0823e-14 [0.0000e+00 - 3.8503e-13] (24#), relativeTol=1.1040e-13 +- 1.1737e-13 [4.4409e-15 - 3.8813e-13] (12#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.152",
      "gc_time": "0.095"
    },
    "created_on": 1586737771872,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.CrossProductLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/CrossProductLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/CrossProductLayer/Basic/derivativeTest/202004132931",
    "id": "04902573-fdeb-4793-80c5-4bcec7c80a7d",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "CrossProductLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.CrossProductLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/CrossProductLayer.java",
      "javaDoc": ""
    }
  }