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 6471305680182189056

Differential Validation

SingleDerivativeTester.java:101 executed in 0.01 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, 1.108 ], [ -0.608, -1.616 ], [ 1.208, 1.032 ], [ -0.852, 1.556 ] ],
[ [ 0.7, 0.028 ], [ 1.764, 1.356 ], [ -1.72, 0.3 ], [ 1.912, 0.788 ] ],
[ [ -0.128, -0.712 ], [ 0.048, 1.512 ], [ -1.028, 0.636 ], [ -1.688, -0.768 ] ],
[ [ 0.496, 1.048 ], [ 1.524, 1.556 ], [ -0.384, -0.176 ], [ -0.804, -0.068 ] ]
]
Inputs Statistics: {meanExponent=-0.21478244038380173, negative=13, min=-1.72, max=1.912, mean=0.253125, count=32, sum=8.1, positive=19, stdDev=1.0492889184466785, zeros=0}
Output: [
[ [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ] ],
[ [ 0.0, 0.0 ], [ 0.08, 1.108 ], [ 0.0, 0.0 ], [ -0.608, -1.616 ], [ 0.0, 0.0 ], [ 1.208, 1.032 ], [ 0.0, 0.0 ], [ -0.852, 1.556 ] ],
[ [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ] ],
[ [ 0.0, 0.0 ], [ 0.7, 0.028 ], [ 0.0, 0.0 ], [ 1.764, 1.356 ], [ 0.0, 0.0 ], [ -1.72, 0.3 ], [ 0.0, 0.0 ], [ 1.912, 0.788 ] ],
[ [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ] ],
[ [ 0.0, 0.0 ], [ -0.128, -0.712 ], [ 0.0, 0.0 ], [ 0.048, 1.512 ], [ 0.0, 0.0 ], [ -1.028, 0.636 ], [ 0.0, 0.0 ], [ -1.688, -0.768 ] ],
[ [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ], [ 0.0, 0.0 ] ],
[ [ 0.0, 0.0 ], [ 0.496, 1.048 ], [ 0.0, 0.0 ], [ 1.524, 1.556 ], [ 0.0, 0.0 ], [ -0.384, -0.176 ], [ 0.0, 0.0 ], [ -0.804, -0.068 ] ]
]
Outputs Statistics: {meanExponent=-0.21478244038380173, negative=13, min=-1.72, max=1.912, mean=0.06328125, count=128, sum=8.1, positive=19, stdDev=0.5359714156542655, zeros=96}

Feedback Validation

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

SingleDerivativeTester.java:117 executed in 0.15 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, 1.108 ], [ -0.608, -1.616 ], [ 1.208, 1.032 ], [ -0.852, 1.556 ] ],
[ [ 0.7, 0.028 ], [ 1.764, 1.356 ], [ -1.72, 0.3 ], [ 1.912, 0.788 ] ],
[ [ -0.128, -0.712 ], [ 0.048, 1.512 ], [ -1.028, 0.636 ], [ -1.688, -0.768 ] ],
[ [ 0.496, 1.048 ], [ 1.524, 1.556 ], [ -0.384, -0.176 ], [ -0.804, -0.068 ] ]
]
Value Statistics: {meanExponent=-0.21478244038380173, negative=13, min=-1.72, max=1.912, mean=0.253125, count=32, sum=8.1, positive=19, stdDev=1.0492889184466785, zeros=0}
Implemented Feedback: [ [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], ... ]
Implemented Statistics: {meanExponent=0.0, negative=0, min=0.0, max=1.0, mean=0.0078125, count=4096, sum=32.0, positive=32, stdDev=0.08804240366863003, zeros=4064}
Measured Feedback: [ [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], ... ]
Measured Statistics: {meanExponent=-4.076694364854251E-14, negative=0, min=0.0, max=1.0000000000000286, mean=0.007812499999999266, count=4096, sum=31.999999999996994, positive=32, stdDev=0.08804240366862177, zeros=4064}
Feedback Error: [ [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], [ 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ... ], ... ]
Error Statistics: {meanExponent=-13.052415404627574, negative=29, min=-1.1013412404281553E-13, max=2.864375403532904E-14, mean=-7.333543494691952E-16, count=4096, sum=-3.0038194154258235E-12, positive=3, stdDev=9.109806220769671E-15, zeros=4064}

Returns

    {
      "absoluteTol" : {
        "count" : 4096,
        "sum" : 3.1756819396377978E-12,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 3.421240442136952E-25,
        "standardDeviation" : 9.106331191808968E-15,
        "average" : 7.753129735443842E-16
      },
      "relativeTol" : {
        "count" : 32,
        "sum" : 1.5878409698189833E-12,
        "min" : 2.9976021664879317E-15,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 8.553101105343314E-26,
        "standardDeviation" : 1.451539485400742E-14,
        "average" : 4.962003030684323E-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" : 4096,
        "sum" : 3.1756819396377978E-12,
        "min" : 0.0,
        "max" : 1.1013412404281553E-13,
        "sumOfSquare" : 3.421240442136952E-25,
        "standardDeviation" : 9.106331191808968E-15,
        "average" : 7.753129735443842E-16
      },
      "relativeTol" : {
        "count" : 32,
        "sum" : 1.5878409698189833E-12,
        "min" : 2.9976021664879317E-15,
        "max" : 5.50670620214108E-14,
        "sumOfSquare" : 8.553101105343314E-26,
        "standardDeviation" : 1.451539485400742E-14,
        "average" : 4.962003030684323E-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: 7.7531e-16 +- 9.1063e-15 [0.0000e+00 - 1.1013e-13] (4096#)
relativeTol: 4.9620e-14 +- 1.4515e-14 [2.9976e-15 - 5.5067e-14] (32#)

Frozen and Alive Status

SingleDerivativeTester.java:156 executed in 0.00 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=7.7531e-16 +- 9.1063e-15 [0.0000e+00 - 1.1013e-13] (4096#), relativeTol=4.9620e-14 +- 1.4515e-14 [2.9976e-15 - 5.5067e-14] (32#)}OK
 
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.302",
      "gc_time": "0.110"
    },
    "created_on": 1586735795846,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.UnpoolingLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/test/java/com/simiacryptus/mindseye/layers/java/UnpoolingLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/UnpoolingLayer/Basic/derivativeTest/202004125635",
    "id": "d5d4ecf1-0d83-493b-a452-8d358a5df53e",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "UnpoolingLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.UnpoolingLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/93db34cedee48c0202777a2b25deddf1dfaf5731/src/main/java/com/simiacryptus/mindseye/layers/java/UnpoolingLayer.java",
      "javaDoc": ""
    }
  }