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 5378351951133551616

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 ],
[ 0.048, 1.524, 1.208 ]
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},
{meanExponent=-0.35123562044523937, negative=0, min=0.048, max=1.524, mean=0.9266666666666667, count=3, sum=2.7800000000000002, positive=3, stdDev=0.6345630167463451, zeros=0}
Output: [ 0.00190464, -0.6486143999999999, -0.272756736 ]
Outputs Statistics: {meanExponent=-1.1574750093743054, negative=2, min=-0.6486143999999999, max=0.00190464, mean=-0.30648883199999993, count=3, sum=-0.9194664959999999, positive=1, stdDev=0.26664226481192027, zeros=0}

Feedback Validation

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

SingleDerivativeTester.java:117 executed in 0.04 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: [ [ 0.023808, 0.0, 0.0 ], [ 0.0, -0.926592, 0.0 ], [ 0.0, 0.0, 2.130912 ] ]
Implemented Statistics: {meanExponent=-0.4426076749256616, negative=1, min=-0.926592, max=2.130912, mean=0.13645866666666664, count=9, sum=1.2281279999999999, positive=2, stdDev=0.7624767244313465, zeros=6}
Measured Feedback: [ [ 0.023808000000000162, 0.0, 0.0 ], [ 0.0, -0.9265920000001149, 0.0 ], [ 0.0, 0.0, 2.1309119999995962 ] ]
Measured Statistics: {meanExponent=-0.44260767492567005, negative=1, min=-0.9265920000001149, max=2.1309119999995962, mean=0.13645866666660908, count=9, sum=1.2281279999994816, positive=2, stdDev=0.7624767244312469, zeros=6}
Feedback Error: [ [ 1.6306400674181987E-16, 0.0, 0.0 ], [ 0.0, -1.149080830487037E-13, 0.0 ], [ 0.0, 0.0, -4.036770917537069E-13 ] ]
Error Statistics: {meanExponent=-13.70708573553811, negative=2, min=-4.036770917537069E-13, max=1.6306400674181987E-16, mean=-5.760245675507431E-14, count=9, sum=-5.184221107956688E-13, positive=1, stdDev=1.2749583929095574E-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: [ [ 0.00384, 0.0, 0.0 ], [ 0.0, 1.0668, 0.0 ], [ 0.0, 0.0, -0.154624 ] ]
Implemented Statistics: {meanExponent=-1.0661029548938832, negative=1, min=-0.154624, max=1.0668, mean=0.10177955555555557, count=9, sum=0.916016, positive=2, stdDev=0.3446018420042054, zeros=6}
Measured Feedback: [ [ 0.0038399999999997464, 0.0, 0.0 ], [ 0.0, 1.0667999999991462, 0.0 ], [ 0.0, 0.0, -0.1546239999999921 ] ]
Measured Statistics: {meanExponent=-1.066102954894016, negative=1, min=-0.1546239999999921, max=1.0667999999991462, mean=0.10177955555546155, count=9, sum=0.916015999999154, positive=2, stdDev=0.3446018420039391, zeros=6}
Feedback Error: [ [ -2.5370330836160804E-16, 0.0, 0.0 ], [ 0.0, -8.537615059367454E-13, 0.0 ], [ 0.0, 0.0, 7.91033905045424E-15 ] ]
Error Statistics: {meanExponent=-13.922047400440233, negative=2, min=-8.537615059367454E-13, max=7.91033905045424E-15, mean=-9.401165224385031E-14, count=9, sum=-8.461048701946527E-13, positive=1, stdDev=2.686235759550845E-13, zeros=6}
Feedback for input 2
Inputs Values: [ 0.048, 1.524, 1.208 ]
Value Statistics: {meanExponent=-0.35123562044523937, negative=0, min=0.048, max=1.524, mean=0.9266666666666667, count=3, sum=2.7800000000000002, positive=3, stdDev=0.6345630167463451, zeros=0}
Implemented Feedback: [ [ 0.03968, 0.0, 0.0 ], [ 0.0, -0.4256, 0.0 ], [ 0.0, 0.0, -0.225792 ] ]
Implemented Statistics: {meanExponent=-0.806239388929066, negative=2, min=-0.4256, max=0.03968, mean=-0.067968, count=9, sum=-0.611712, positive=1, stdDev=0.1461031022744631, zeros=6}
Measured Feedback: [ [ 0.039680000000002436, 0.0, 0.0 ], [ 0.0, -0.425600000000248, 0.0 ], [ 0.0, 0.0, -0.2257919999998359 ] ]
Measured Statistics: {meanExponent=-0.806239388929078, negative=2, min=-0.425600000000248, max=0.039680000000002436, mean=-0.06796800000000906, count=9, sum=-0.6117120000000815, positive=1, stdDev=0.14610310227451107, zeros=6}
Feedback Error: [ [ 2.435551760271437E-15, 0.0, 0.0 ], [ 0.0, -2.4802382370125997E-13, 0.0 ], [ 0.0, 0.0, 1.6409096303959814E-13 ] ]
Error Statistics: {meanExponent=-13.334608191308236, negative=1, min=-2.4802382370125997E-13, max=1.6409096303959814E-13, mean=-9.055256544598933E-15, count=9, sum=-8.14973089013904E-14, positive=2, stdDev=9.871936326286916E-14, zeros=6}

Returns

    {
      "absoluteTol" : {
        "count" : 27,
        "sum" : 1.7952241256058432E-12,
        "min" : 0.0,
        "max" : 8.537615059367454E-13,
        "sumOfSquare" : 9.935780285822033E-25,
        "standardDeviation" : 1.7993969844427617E-13,
        "average" : 6.648978242984604E-14
      },
      "relativeTol" : {
        "count" : 9,
        "sum" : 1.3043527126213059E-12,
        "min" : 3.4245633136302783E-15,
        "max" : 4.001506870721256E-13,
        "sumOfSquare" : 3.925752652773529E-25,
        "standardDeviation" : 1.503839279473025E-13,
        "average" : 1.449280791801451E-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" : 27,
        "sum" : 1.7952241256058432E-12,
        "min" : 0.0,
        "max" : 8.537615059367454E-13,
        "sumOfSquare" : 9.935780285822033E-25,
        "standardDeviation" : 1.7993969844427617E-13,
        "average" : 6.648978242984604E-14
      },
      "relativeTol" : {
        "count" : 9,
        "sum" : 1.3043527126213059E-12,
        "min" : 3.4245633136302783E-15,
        "max" : 4.001506870721256E-13,
        "sumOfSquare" : 3.925752652773529E-25,
        "standardDeviation" : 1.503839279473025E-13,
        "average" : 1.449280791801451E-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: 6.6490e-14 +- 1.7994e-13 [0.0000e+00 - 8.5376e-13] (27#)
relativeTol: 1.4493e-13 +- 1.5038e-13 [3.4246e-15 - 4.0015e-13] (9#)

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=6.6490e-14 +- 1.7994e-13 [0.0000e+00 - 8.5376e-13] (27#), relativeTol=1.4493e-13 +- 1.5038e-13 [3.4246e-15 - 4.0015e-13] (9#)}OK
 
  {
    "result": "OK",
    "performance": {
      "execution_time": "0.174",
      "gc_time": "0.103"
    },
    "created_on": 1586738628997,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "NNNTest",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.ProductInputsLayerTest.NNNTest",
      "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/NNNTest/derivativeTest/202004134348",
    "id": "bcd98acf-06ac-4753-bc5f-fafba104c74c",
    "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": ""
    }
  }