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 1863228913735813120

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, -0.608, 1.764 ]
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},
{meanExponent=-0.09137205448042225, negative=1, min=-0.608, max=1.764, mean=0.5506666666666667, count=3, sum=1.6520000000000001, positive=2, stdDev=0.9691361560115735, zeros=0}
Output: [ 0.03968, -0.4256, -0.225792 ]
Outputs Statistics: {meanExponent=-0.806239388929066, negative=2, min=-0.4256, max=0.03968, mean=-0.203904, count=3, sum=-0.611712, positive=1, stdDev=0.19057926261444783, 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 ]
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: [ [ 0.496, 0.0, 0.0 ], [ 0.0, -0.608, 0.0 ], [ 0.0, 0.0, 1.764 ] ]
Implemented Statistics: {meanExponent=-0.09137205448042225, negative=1, min=-0.608, max=1.764, mean=0.18355555555555558, count=9, sum=1.6520000000000001, positive=2, stdDev=0.6168145968713616, zeros=6}
Measured Feedback: [ [ 0.4960000000000381, 0.0, 0.0 ], [ 0.0, -0.6079999999997199, 0.0 ], [ 0.0, 0.0, 1.7639999999996547 ] ]
Measured Statistics: {meanExponent=-0.09137205448050616, negative=1, min=-0.6079999999997199, max=1.7639999999996547, mean=0.18355555555555256, count=9, sum=1.651999999999973, positive=2, stdDev=0.6168145968712254, zeros=6}
Feedback Error: [ [ 3.808064974464287E-14, 0.0, 0.0 ], [ 0.0, 2.80109269112927E-13, 0.0 ], [ 0.0, 0.0, -3.452793606584237E-13 ] ]
Error Statistics: {meanExponent=-12.81126585032861, negative=1, min=-3.452793606584237E-13, max=2.80109269112927E-13, mean=-3.0099379778726466E-15, count=9, sum=-2.708944180085382E-14, positive=2, stdDev=1.487158505655692E-13, zeros=6}
Feedback for input 1
Inputs Values: [ 0.496, -0.608, 1.764 ]
Value Statistics: {meanExponent=-0.09137205448042225, negative=1, min=-0.608, max=1.764, mean=0.5506666666666667, count=3, sum=1.6520000000000001, positive=2, stdDev=0.9691361560115735, zeros=0}
Implemented Feedback: [ [ 0.08, 0.0, 0.0 ], [ 0.0, 0.7, 0.0 ], [ 0.0, 0.0, -0.128 ] ]
Implemented Statistics: {meanExponent=-0.7148673344486438, negative=1, min=-0.128, max=0.7, mean=0.07244444444444444, count=9, sum=0.6519999999999999, positive=2, stdDev=0.22743746936056028, zeros=6}
Measured Feedback: [ [ 0.08000000000001062, 0.0, 0.0 ], [ 0.0, 0.700000000000145, 0.0 ], [ 0.0, 0.0, -0.1280000000000725 ] ]
Measured Statistics: {meanExponent=-0.7148673344485125, negative=1, min=-0.1280000000000725, max=0.700000000000145, mean=0.07244444444445368, count=9, sum=0.6520000000000831, positive=2, stdDev=0.22743746936061188, zeros=6}
Feedback Error: [ [ 1.061650767297806E-14, 0.0, 0.0 ], [ 0.0, 1.4499512701604544E-13, 0.0 ], [ 0.0, 0.0, -7.249756350802272E-14 ] ]
Error Statistics: {meanExponent=-13.317447168065735, negative=1, min=-7.249756350802272E-14, max=1.4499512701604544E-13, mean=9.234896797888976E-15, count=9, sum=8.311407118100078E-14, positive=2, stdDev=5.3358997927414475E-14, zeros=6}

Returns

    {
      "absoluteTol" : {
        "count" : 18,
        "sum" : 8.915784777130398E-13,
        "min" : 0.0,
        "max" : 3.452793606584237E-13,
        "sumOfSquare" : 2.255213692328115E-25,
        "standardDeviation" : 1.0037695102526329E-13,
        "average" : 4.953213765072443E-14
      },
      "relativeTol" : {
        "count" : 6,
        "sum" : 8.197237969055693E-13,
        "min" : 3.83877517587111E-14,
        "max" : 2.8319360745313353E-13,
        "sumOfSquare" : 1.5944201883081121E-25,
        "standardDeviation" : 8.892959290166084E-14,
        "average" : 1.3662063281759487E-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" : 18,
        "sum" : 8.915784777130398E-13,
        "min" : 0.0,
        "max" : 3.452793606584237E-13,
        "sumOfSquare" : 2.255213692328115E-25,
        "standardDeviation" : 1.0037695102526329E-13,
        "average" : 4.953213765072443E-14
      },
      "relativeTol" : {
        "count" : 6,
        "sum" : 8.197237969055693E-13,
        "min" : 3.83877517587111E-14,
        "max" : 2.8319360745313353E-13,
        "sumOfSquare" : 1.5944201883081121E-25,
        "standardDeviation" : 8.892959290166084E-14,
        "average" : 1.3662063281759487E-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: 4.9532e-14 +- 1.0038e-13 [0.0000e+00 - 3.4528e-13] (18#)
relativeTol: 1.3662e-13 +- 8.8930e-14 [3.8388e-14 - 2.8319e-13] (6#)

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=4.9532e-14 +- 1.0038e-13 [0.0000e+00 - 3.4528e-13] (18#), relativeTol=1.3662e-13 +- 8.8930e-14 [3.8388e-14 - 2.8319e-13] (6#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.154",
      "gc_time": "0.095"
    },
    "created_on": 1586738682141,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "NNTest",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.ProductInputsLayerTest.NNTest",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/ProductInputsLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/ProductInputsLayer/NNTest/derivativeTest/202004134442",
    "id": "96ebf5ce-46c2-4922-a816-5af8ba0e6c64",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "ProductInputsLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.ProductInputsLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/ProductInputsLayer.java",
      "javaDoc": ""
    }
  }