[FRIAM] A pretty cellular automata video

[uǝlƃ ☤>$]

Maybe I'm just incompetent today. But what PCM devices did they use? Internal IBM research devices? Or did they only use the simulator (https://github.com/IBM/aihwkit)? Are there commercial PCM chips yet?

On 10/1/21 7:34 AM, Marcus Daniels wrote:
> Companies like Mythic and IBM have developed analog devices for energy- efficient deep learning.   Noise and low precision are often used as part of ML training protocols anyway.    Here they did careful side-by-side testing to quantify the impact of going analog.
> 
> https://www.frontiersin.org/articles/10.3389/fncom.2021.675741/full <https://www.frontiersin.org/articles/10.3389/fncom.2021.675741/full>
> 
> Or perhaps the proposition is that CS people (for example) can’t appreciate complexity that where the generative rules are unknown or obscure?   Sure that horse is fast, but how can I put a new engine in it?

-- 
"Better to be slapped with the truth than kissed with a lie."
☤>$ uǝlƃ