1. Test Modules
  2. Differential Validation
    1. Feedback Validation
    2. Learning Validation
    3. Total Accuracy
    4. Frozen and Alive Status
  3. Results

Target Description: The type Sum reducer layer.

Report Description: The type Basic.

Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase

Test Modules

Using Seed 656818316946451456

Differential Validation

SingleDerivativeTester.java:153 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: [ 0.6519999999999999 ]
Outputs Statistics: {meanExponent=-0.18575240426807987, negative=0, min=0.6519999999999999, max=0.6519999999999999, mean=0.6519999999999999, count=1, sum=0.6519999999999999, positive=1, stdDev=0.0, zeros=0}

Feedback Validation

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

SingleDerivativeTester.java:169 executed in 0.01 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: [ [ 1.0 ], [ 1.0 ], [ 1.0 ] ]
Implemented Statistics: {meanExponent=0.0, negative=0, min=1.0, max=1.0, mean=1.0, count=3, sum=3.0, positive=3, stdDev=0.0, zeros=0}
Measured Feedback: [ [ 1.000000000001 ], [ 0.9999999999998899 ], [ 0.9999999999998899 ] ]
Measured Statistics: {meanExponent=1.1289060208443065E-13, negative=0, min=0.9999999999998899, max=1.000000000001, mean=1.00000000000026, count=3, sum=3.00000000000078, positive=3, stdDev=1.4901161193847656E-8, zeros=0}
Feedback Error: [ [ 1.000088900582341E-12 ], [ -1.1013412404281553E-13 ], [ -1.1013412404281553E-13 ] ]
Error Statistics: {meanExponent=-12.63870586291913, negative=2, min=-1.1013412404281553E-13, max=1.000088900582341E-12, mean=2.5994021749890333E-13, count=3, sum=7.7982065249671E-13, positive=1, stdDev=5.233641528945917E-13, zeros=0}

Returns

    {
      "absoluteTol" : {
        "count" : 3,
        "sum" : 1.220357148667972E-12,
        "min" : 1.1013412404281553E-13,
        "max" : 1.000088900582341E-12,
        "sumOfSquare" : 1.0244368596253521E-24,
        "standardDeviation" : 4.195287049603047E-13,
        "average" : 4.0678571622265736E-13
      },
      "relativeTol" : {
        "count" : 3,
        "sum" : 6.101785743337421E-13,
        "min" : 5.50670620214108E-14,
        "max" : 5.000444502909205E-13,
        "sumOfSquare" : 2.561092149060887E-25,
        "standardDeviation" : 2.097643524800331E-13,
        "average" : 2.0339285811124737E-13
      }
    }

Learning Validation

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

SingleDerivativeTester.java:185 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" : 3,
        "sum" : 1.220357148667972E-12,
        "min" : 1.1013412404281553E-13,
        "max" : 1.000088900582341E-12,
        "sumOfSquare" : 1.0244368596253521E-24,
        "standardDeviation" : 4.195287049603047E-13,
        "average" : 4.0678571622265736E-13
      },
      "relativeTol" : {
        "count" : 3,
        "sum" : 6.101785743337421E-13,
        "min" : 5.50670620214108E-14,
        "max" : 5.000444502909205E-13,
        "sumOfSquare" : 2.561092149060887E-25,
        "standardDeviation" : 2.097643524800331E-13,
        "average" : 2.0339285811124737E-13
      }
    }

Total Accuracy

The overall agreement accuracy between the implemented derivative and the finite difference estimations:

SingleDerivativeTester.java:200 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: 4.0679e-13 +- 4.1953e-13 [1.1013e-13 - 1.0001e-12] (3#)
relativeTol: 2.0339e-13 +- 2.0976e-13 [5.5067e-14 - 5.0004e-13] (3#)

Frozen and Alive Status

SingleDerivativeTester.java:208 executed in 0.00 seconds (0.000 gc):

    testFrozen(component.addRef(), RefUtil.addRef(inputPrototype));
    testUnFrozen(component.addRef(), RefUtil.addRef(inputPrototype));

LayerTests.java:605 executed in 0.00 seconds (0.000 gc):

    throwException(exceptions.addRef());

Results

classdetailsresult
com.simiacryptus.mindseye.test.unit.SingleDerivativeTesterToleranceStatistics{absoluteTol=4.0679e-13 +- 4.1953e-13 [1.1013e-13 - 1.0001e-12] (3#), relativeTol=2.0339e-13 +- 2.0976e-13 [5.5067e-14 - 5.0004e-13] (3#)}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.151",
      "gc_time": "0.102"
    },
    "created_on": 1587005972366,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.SumReducerLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/c9a1867488dc7e77a975f095285b5882c0486db6/src/test/java/com/simiacryptus/mindseye/layers/java/SumReducerLayerTest.java",
      "javaDoc": "The type Basic."
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/SumReducerLayer/Basic/derivativeTest/202004165932",
    "id": "ca0960a1-b976-428d-91f2-1ccccdf5fecd",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "SumReducerLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.SumReducerLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/c9a1867488dc7e77a975f095285b5882c0486db6/src/main/java/com/simiacryptus/mindseye/layers/java/SumReducerLayer.java",
      "javaDoc": "The type Sum reducer layer."
    }
  }