Peter Bloem<p>Solving ARC (well... up to 20%) with inference-time compression. Another indication that <a href="https://sigmoid.social/tags/MDL" class="mention hashtag" rel="tag">#<span>MDL</span></a> and <a href="https://sigmoid.social/tags/AlgorithmicComplexity" class="mention hashtag" rel="tag">#<span>AlgorithmicComplexity</span></a> are becoming relevant in the age of Deep Learning. </p><p><a href="https://iliao2345.github.io/blog_posts/arc_agi_without_pretraining/arc_agi_without_pretraining.html" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">iliao2345.github.io/blog_posts</span><span class="invisible">/arc_agi_without_pretraining/arc_agi_without_pretraining.html</span></a></p>
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!
Administered by:
Server stats:
575active users
sigmoid.social: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.3
#AlgorithmicComplexity
0 posts · 0 participants · 0 posts today
Marcel Fröhlich<p>Zenil et al describe an algorithmic causal deconvolution method that disentangles the dimensions which originally provided meaning to the sequence solely by analysing the sequence based on algorithmic information dynamics.</p><p><a href="https://arxiv.org/pdf/2303.16045" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/pdf/2303.16045</span><span class="invisible"></span></a></p><p>But how does that relate to transformers?</p><p><a href="https://mathstodon.xyz/tags/AlgorithmicInformationTheory" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AlgorithmicInformationTheory</span></a> <a href="https://mathstodon.xyz/tags/AlgorithmicComplexity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AlgorithmicComplexity</span></a> <a href="https://mathstodon.xyz/tags/CausalDeconvolution" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CausalDeconvolution</span></a></p>
TrendingLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload