Keeping ISIL Quiet
Jobs and Jihad
Obama’s Biggest Fear
Oil Via Rail
Creepy Joe Biden
Meme: Snow Days
Dodd Frank Financial Reform
Quote: Conan O’Brien on Jeb Bush
Read more excellent articles at The Patriot Post
I recall a February of rain. On the first of the month, the first drops fell. It didn’t let up until March. I idled the whole time warmed by electric heat, entertained by flickering images cast on phosphorous and glass. A full month of rain, and I spent it dry and warm. I used to be annoyed at February. Now it terrifies me.
After the Collapse, after the missiles flew, after the countless billions of lives gently winked out in a brief atomic holler, after the miserable few left over finished their terminal crawl though the radioactive wreckage, it was the ancient tooth and fang of the wild—the gnashing of winter—that hewed to the merciless cull. I’ve been lucky enough to count myself among the fortunate few to escape an icy death at the side of the overgrown highways of this once-mighty nation.
Anyone likely to read this will already know…
Ver la entrada original 953 palabras más
Microsoft on Monday released a white paper explaining a current effort to run convolutional neural networks — the deep learning technique responsible for record-setting computer vision algorithms — on FPGAs rather than GPUs.
Microsoft claims that new FPGA designs provide greatly improved processing speed over earlier versions while consuming a fraction of the power of GPUs. This type of work could represent a big shift in deep learning if it catches on, because for the past few years the field has been largely centered around GPUs as the computing architecture of choice.
If there’s a major caveat to Microsoft’s efforts, it might have to do with performance. While Microsoft’s research shows FPGAs consuming about one-tenth the power of high-end GPUs (25W compared with 235W), GPUs still process images at a much higher rate. Nvidia’s Tesla K40 GPU can do between 500 and 824 images per second on one popular benchmark dataset, the white…
Ver la entrada original 358 palabras más