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 7016630125431198720

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)));

Inputs: [
[ [ 0.08 ], [ -0.128 ], [ -0.608 ] ],
[ [ 0.7 ], [ 0.496 ], [ 1.764 ] ]
]
Inputs Statistics: {meanExponent=-0.403119694464533, negative=2, min=-0.608, max=1.764, mean=0.38399999999999995, count=6, sum=2.304, positive=4, stdDev=0.747821725636086, zeros=0}
Output: [
[ [ 0.0799146939691727 ], [ -0.12765076088614874 ], [ -0.5712270194231158 ] ],
[ [ 0.644217687237691 ], [ 0.4759113823183197 ], [ 0.9813941545641375 ] ]
]
Outputs Statistics: {meanExponent=-0.4593565011103761, negative=2, min=-0.5712270194231158, max=0.9813941545641375, mean=0.24709335629667606, count=6, sum=1.4825601377800564, positive=4, stdDev=0.5143431379622218, 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()));

Feedback for input 0
Inputs Values: [
[ [ 0.08 ], [ -0.128 ], [ -0.608 ] ],
[ [ 0.7 ], [ 0.496 ], [ 1.764 ] ]
]
Value Statistics: {meanExponent=-0.403119694464533, negative=2, min=-0.608, max=1.764, mean=0.38399999999999995, count=6, sum=2.304, positive=4, stdDev=0.747821725636086, zeros=0}
Implemented Feedback: [ [ 0.9968017063026194, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.7648421872844885, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.9918191787040556, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.879493238279787, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.8207921127063681, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, -0.19200394107242127 ] ]
Implemented Statistics: {meanExponent=-0.1632685113393257, negative=1, min=-0.19200394107242127, max=0.9968017063026194, mean=0.11838179117235824, count=36, sum=4.261744482204897, positive=5, stdDev=0.3136639706273164, zeros=30}
Measured Feedback: [ [ 0.9967977089066216, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.7648099751256243, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.9918255595889325, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.8794694412450621, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.82082067268896, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, -0.19205301046043566 ] ]
Measured Statistics: {meanExponent=-0.16325232843231338, negative=1, min=-0.19205301046043566, max=0.9967977089066216, mean=0.11837973186374347, count=36, sum=4.261670347094765, positive=5, stdDev=0.31366383065626685, zeros=30}
Feedback Error: [ [ -3.997395997878961E-6, 0.0, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, -3.22121588641755E-5, 0.0, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 6.3808848769220106E-6, 0.0, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, -2.3797034724881705E-5, 0.0, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 2.8559982591880306E-5, 0.0 ], [ 0.0, 0.0, 0.0, 0.0, 0.0, -4.906938801438332E-5 ] ]
Error Statistics: {meanExponent=-4.7603717768168705, negative=4, min=-4.906938801438332E-5, max=2.8559982591880306E-5, mean=-2.0593086147921436E-6, count=36, sum=-7.413511013251717E-5, positive=2, stdDev=1.146422852199718E-5, zeros=30}

Returns

    {
      "absoluteTol" : {
        "count" : 36,
        "sum" : 1.440168450701218E-4,
        "min" : 0.0,
        "max" : 4.906938801438332E-5,
        "sumOfSquare" : 4.8840943527191085E-9,
        "standardDeviation" : 1.0939174740704484E-5,
        "average" : 4.000467918614494E-6
      },
      "relativeTol" : {
        "count" : 6,
        "sum" : 1.8497279539825392E-4,
        "min" : 2.00511495307567E-6,
        "max" : 1.2776591549387782E-4,
        "sumOfSquare" : 1.726766475282109E-8,
        "standardDeviation" : 4.3903636105896184E-5,
        "average" : 3.082879923304232E-5
      }
    }

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" : 36,
        "sum" : 1.440168450701218E-4,
        "min" : 0.0,
        "max" : 4.906938801438332E-5,
        "sumOfSquare" : 4.8840943527191085E-9,
        "standardDeviation" : 1.0939174740704484E-5,
        "average" : 4.000467918614494E-6
      },
      "relativeTol" : {
        "count" : 6,
        "sum" : 1.8497279539825392E-4,
        "min" : 2.00511495307567E-6,
        "max" : 1.2776591549387782E-4,
        "sumOfSquare" : 1.726766475282109E-8,
        "standardDeviation" : 4.3903636105896184E-5,
        "average" : 3.082879923304232E-5
      }
    }

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));

Finite-Difference Derivative Accuracy:
absoluteTol: 4.0005e-06 +- 1.0939e-05 [0.0000e+00 - 4.9069e-05] (36#)
relativeTol: 3.0829e-05 +- 4.3904e-05 [2.0051e-06 - 1.2777e-04] (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

  {
    "result": "OK",
    "performance": {
      "execution_time": "0.158",
      "gc_time": "0.106"
    },
    "created_on": 1586738139480,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.SinewaveActivationLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/SinewaveActivationLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/SinewaveActivationLayer/Basic/derivativeTest/202004133539",
    "id": "7acce509-bfd7-4d21-a49f-802c62e4cd4f",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "SinewaveActivationLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.SinewaveActivationLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/SinewaveActivationLayer.java",
      "javaDoc": ""
    }
  }