Barely Significant
← all excerpts

Guiding the retraining of convolutional neural networks against adversarial inputs.

PeerJ Comput Sci · 2023 · PMC10495969 · PMID 37705636

1
hedged sentence
closest p
boldest claim

The sentences

may not be significantno p-value reported
On the other hand, for NC metric it may be more difficult to identify good inputs for retraining because this metric identifies inputs that cover more neurons according to certain thresholds, which in retraining may not be significant.

also in 1,117 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.