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 6193450290329099264

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 ] ],
[ [ 0.7 ], [ 0.496 ] ]
]
Inputs Statistics: {meanExponent=-0.6122800817139336, negative=1, min=-0.128, max=0.7, mean=0.287, count=4, sum=1.148, positive=3, stdDev=0.3276141022605712, zeros=0}
Output: [
[ [ 0.5199893712997437 ], [ 0.46804359555244446 ] ],
[ [ 0.6681877970695496 ], [ 0.6215188503265381 ] ]
]
Outputs Statistics: {meanExponent=-0.24884159532774097, negative=0, min=0.46804359555244446, max=0.6681877970695496, mean=0.5694349035620689, count=4, sum=2.2777396142482758, positive=4, stdDev=0.07935667818033819, zeros=0}

Feedback Validation

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

SingleDerivativeTester.java:117 executed in 0.06 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 ] ],
[ [ 0.7 ], [ 0.496 ] ]
]
Value Statistics: {meanExponent=-0.6122800817139336, negative=1, min=-0.128, max=0.7, mean=0.287, count=4, sum=1.148, positive=3, stdDev=0.3276141022605712, zeros=0}
Implemented Feedback: [ [ 0.24960042536258698, 0.0, 0.0, 0.0 ], [ 0.0, 0.2217128574848175, 0.0, 0.0 ], [ 0.0, 0.0, 0.24897880852222443, 0.0 ], [ 0.0, 0.0, 0.0, 0.23523317277431488 ] ]
Implemented Statistics: {meanExponent=-0.622325712249936, negative=0, min=0.0, max=0.24960042536258698, mean=0.05972032900899649, count=16, sum=0.9555252641439438, positive=4, stdDev=0.10359710813736547, zeros=12}
Measured Feedback: [ [ 0.24974346160888672, 0.0, 0.0, 0.0 ], [ 0.0, 0.22113323211669922, 0.0, 0.0 ], [ 0.0, 0.0, 0.2491474151611328, 0.0 ], [ 0.0, 0.0, 0.0, 0.23543834686279297 ] ]
Measured Statistics: {meanExponent=-0.6223795684398395, negative=0, min=0.0, max=0.24974346160888672, mean=0.05971640348434448, count=16, sum=0.9554624557495117, positive=4, stdDev=0.10359795216848089, zeros=12}
Feedback Error: [ [ 1.4303624629974365E-4, 0.0, 0.0, 0.0 ], [ 0.0, -5.796253681182861E-4, 0.0, 0.0 ], [ 0.0, 0.0, 1.6860663890838623E-4, 0.0 ], [ 0.0, 0.0, 0.0, 2.0517408847808838E-4 ] ]
Error Statistics: {meanExponent=-3.6356023317921204, negative=1, min=-5.796253681182861E-4, max=2.0517408847808838E-4, mean=-3.925524652004242E-6, count=16, sum=-6.280839443206787E-5, positive=3, stdDev=1.633062660478543E-4, zeros=12}

Returns

    {
      "absoluteTol" : {
        "count" : 16,
        "sum" : 0.0010964423418045044,
        "min" : 0.0,
        "max" : 5.796253681182861E-4,
        "sumOfSquare" : 4.26949540388577E-7,
        "standardDeviation" : 1.4828455063918027E-4,
        "average" : 6.852764636278152E-5
      },
      "relativeTol" : {
        "count" : 4,
        "sum" : 0.0023697120675487343,
        "min" : 2.8644837762460673E-4,
        "max" : 0.0013088641442896031,
        "sumOfSquare" : 2.099772239712916E-6,
        "standardDeviation" : 4.170996340628314E-4,
        "average" : 5.924280168871836E-4
      }
    }

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" : 16,
        "sum" : 0.0010964423418045044,
        "min" : 0.0,
        "max" : 5.796253681182861E-4,
        "sumOfSquare" : 4.26949540388577E-7,
        "standardDeviation" : 1.4828455063918027E-4,
        "average" : 6.852764636278152E-5
      },
      "relativeTol" : {
        "count" : 4,
        "sum" : 0.0023697120675487343,
        "min" : 2.8644837762460673E-4,
        "max" : 0.0013088641442896031,
        "sumOfSquare" : 2.099772239712916E-6,
        "standardDeviation" : 4.170996340628314E-4,
        "average" : 5.924280168871836E-4
      }
    }

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: 6.8528e-05 +- 1.4828e-04 [0.0000e+00 - 5.7963e-04] (16#)
relativeTol: 5.9243e-04 +- 4.1710e-04 [2.8645e-04 - 1.3089e-03] (4#)

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": "0.233",
      "gc_time": "0.119"
    },
    "created_on": 1586740757678,
    "file_name": "derivativeTest",
    "report": {
      "simpleName": "Sigmoid_Float",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ActivationLayerTest.Sigmoid_Float",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/test/java/com/simiacryptus/mindseye/layers/cudnn/ActivationLayerTest.java",
      "javaDoc": ""
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/cudnn/ActivationLayer/Sigmoid_Float/derivativeTest/202004131917",
    "id": "f03ed8fb-16bc-4f24-9787-bdd2af6ebe32",
    "report_type": "Components",
    "display_name": "Derivative Validation",
    "target": {
      "simpleName": "ActivationLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.cudnn.ActivationLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-cudnn/tree/59d5b3318556370acb2d83ee6ec123ce0fc6974f/src/main/java/com/simiacryptus/mindseye/layers/cudnn/ActivationLayer.java",
      "javaDoc": ""
    }
  }