Verification of classification decisions in convolutional neural networks
AssigneeSiemens Aktiengesellschaft
InventorJindong Gu
Life of this patent
Estimating the term…
Loading patent…
AssigneeSiemens Aktiengesellschaft
InventorJindong Gu
Estimating the term…
In one aspect the invention relates to a computer-implemented method for providing a computer-implemented method for verifying a visual classification architecture of a convolutional neural network (CNN) and its decisions The method comprises to access (S1) a memory (MEM) with a convolutional neural network (CNN), being trained for a visual classification task into a set of target classes (tc); to use (S2) the convolutional neural network (CNN) for an input image (12) and after a forward pass of the convolutional neural network (CNN), in a backward pass: to apply (S3) a contrastive layer-wise relevance propagation algorithm (CLRP) or to apply (S4) a Bottom Up Attention pattern (BUAP), which is implicitly learned by the convolutional neural network (CNN) for providing (S5) a verification signal (vs).
A computer-implemented method for verifying a visual classification architecture of a convolutional neural network, the method comprising:
A verification unit which is configured for verifying a visual classification architecture of a convolutional neural network, comprising:
Dependencies are inferred from the claim text.