diff --git a/Source/ComputationNetworkLib/ConvolutionalNodes.h b/Source/ComputationNetworkLib/ConvolutionalNodes.h
index 1fbc15c12faa..6fd69e06f953 100644
--- a/Source/ComputationNetworkLib/ConvolutionalNodes.h
+++ b/Source/ComputationNetworkLib/ConvolutionalNodes.h
@@ -286,6 +286,7 @@ protected:                                  \
     using Base::m_tempMatrixForward;        \
     using Base::m_tempMatrixBackward;       \
     using Base::m_convEng;                  \
+    using Base::InferConvolution2DReductionDims; \
     using Base::InferReductionDims;         \
 public:
 
diff --git a/Source/Math/CuDnnConvolutionEngine.cu b/Source/Math/CuDnnConvolutionEngine.cu
index 20d5e7c521a2..c2cc3f3a0ea5 100644
--- a/Source/Math/CuDnnConvolutionEngine.cu
+++ b/Source/Math/CuDnnConvolutionEngine.cu
@@ -664,7 +664,7 @@ bool CuDnnConvolutionEngineFactory<ElemType>::IsSupported(DEVICEID_TYPE deviceId
                    (poolKind == PoolKind::None ||
                    inputRank <= 3 && (kernelRank < 3 || kernel[2] == 1)));
 
-    // cuDNN as of version 6.0 does not handle asymmetric padding for convolution correctly. We need to detect asymmetric
+    // cuDNN as of version 6.0 does not handle asymmetric padding for even size kernel convolution correctly. We need to detect asymmetric
     // padding due to auto-padding and choose the reference convolution implementation instead
     if (poolKind == PoolKind::None)     // only for convolution, pooling seems fine
     {