Evidence item

The primary papers directly document GPU-enabled ImageNet CNN training and DeepMind’s 2015 deep-Q learning results on Atari, supporting their landmark status; they do not establish that GPU use or reinforcement learning as fields began with those works. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 12518

Source: ImageNet Classification with Deep Convolutional Neural Networks; Human-level control through deep reinforcement learning · locator {} · excerpt hash sha256:1b4ad7254b561ba8c4412eff895f7f62035f07cca80cd0000ee43216226db420

Current GPUs, paired with a highly-optimized implementation of 2D convolution, are powerful enough to facilitate the training of interestingly-large CNNs ... Our network takes between five and six days to train on two GTX 580 3GB GPUs. ... The deep Q-network ... can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning ... across a set of 49 games.