Evidence item

The AlexNet paper directly links GPU training to its ImageNet/ILSVRC breakthrough and reports leading results there. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10541

Source: ImageNet Classification with Deep Convolutional Neural Networks · locator {} · excerpt hash sha256:cc4722ddf36177371c7242aaa5c551a7b7344c44cb44f31df8444958a2b775b5

Exact excerpt

Current GPUs, paired with a highly-optimized implementation of 2D convolution, are powerful enough to facilitate the training of interestingly-large CNNs. The specific contributions of this paper are as follows: we trained one of the largest convolutional neural networks to date on the subsets of ImageNet used in the ILSVRC-2010 and ILSVRC-2012 competitions and achieved by far the best results ever reported on these datasets.

Linked claims

Claim	Direction	Relevance	Steps	Counted
f5b7e850	SUPPORT	STRONG	0	yes

Audits

None.