Recent searches

No recent searches

Search options

Only available when logged in.
med-mastodon.com is one of the many independent Mastodon servers you can use to participate in the fediverse.
Medical community on Mastodon

Administered by:

Server stats:

373
active users

med-mastodon.com: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

#richardsutton

0 posts0 participants0 posts today
Teixi<p><span class="h-card" translate="no"><a href="https://fediscience.org/@ekmiller" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>ekmiller</span></a></span> </p><p>» The point of the bitter lesson is that the right learning algorithms (those that scale efficiently with massive computation) are exactly what we need.<br>Massive computation does not alleviate the need for data efficiency «</p><p>24/11/2023 <a href="https://mastodon.social/tags/RichardSutton" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RichardSutton</span></a></p><p>Nowadays neuroscience forever expansing body of literature, spreading across different subfields, disperse schools, training practices, and multiple sets of technologies. Instead attempts for building a comprehensive knowledge consensus.</p>
Teixi<p><a href="https://mastodon.social/tags/ACMPrize" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACMPrize</span></a><br><a href="https://mastodon.social/tags/2024ACMPrize" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>2024ACMPrize</span></a><br><a href="https://mastodon.social/tags/ACMTuringAward" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACMTuringAward</span></a></p><p><a href="https://mastodon.social/tags/AndrewBarto" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AndrewBarto</span></a><br><a href="https://mastodon.social/tags/RichardSutton" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RichardSutton</span></a> </p><p>» <a href="https://mastodon.social/tags/ReinforcementLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ReinforcementLearning</span></a><br>An Introduction<br>1998<br>standard reference...cited over 75,000<br>...<br>prominent example of <a href="https://mastodon.social/tags/RL" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RL</span></a><br><a href="https://mastodon.social/tags/AlphaGo" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AlphaGo</span></a> victory<br>over best human <a href="https://mastodon.social/tags/Go" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Go</span></a> players<br>2016 2017<br>....<br>recently has been the development of the chatbot <a href="https://mastodon.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatGPT</span></a><br>...<br>large language model <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> trained in two phases ...employs a technique called<br>reinforcement learning from human feedback <a href="https://mastodon.social/tags/RLHF" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RLHF</span></a> «</p><p>aka cheap labor unnamed in papers</p><p><a href="https://awards.acm.org/about/2024-turing" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">awards.acm.org/about/2024-turi</span><span class="invisible">ng</span></a></p><p>2/2</p>
Teixi<p><span class="h-card" translate="no"><a href="https://indieweb.social/@emilygorcenski" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>emilygorcenski</span></a></span> <span class="h-card" translate="no"><a href="https://neuromatch.social/@kordinglab" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>kordinglab</span></a></span> </p><p>» Not at all.</p><p>The point of the bitter lesson is that the right learning algorithms </p><p>(those that scale efficiently with massive computation)</p><p>are exactly what we need.</p><p>Massive computation does not alleviate the need for data efficiency «</p><p><a href="https://mastodon.social/tags/RichardSutton" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RichardSutton</span></a> 24/11/2023</p><p><a href="https://nitter.cz/RichardSSutton/status/1728129341287198885#m" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">nitter.cz/RichardSSutton/statu</span><span class="invisible">s/1728129341287198885#m</span></a></p><p><a href="https://mastodon.social/tags/TheBitterLessonInML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TheBitterLessonInML</span></a></p><p><a href="http://www.incompleteideas.net/IncIdeas/BitterLesson.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">http://www.</span><span class="ellipsis">incompleteideas.net/IncIdeas/B</span><span class="invisible">itterLesson.html</span></a></p>
TrendingLive feeds
About