<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><description>Research scientist in neural networks @ IBM Research | 📍NYC | https://ito-takuya.github.io</description><link>https://bsky.app/profile/takuito.bsky.social</link><title>@takuito.bsky.social - Taku Ito</title><item><link>https://bsky.app/profile/takuito.bsky.social/post/3lwry3fy7gc2c</link><description>What complexity of algorithms can AI compute? In a new paper with colleagues at IBM Research, we explore how circuit complexity theory can help quantify the degree of algorithmic generalization in AI systems. https://www.nature.com/articles/s42256-025-01092-w&#xA;@natmachintell.nature.com &#xA;#ML #AI #MLSky&#xA;1/n</description><pubDate>19 Aug 2025 22:38 +0000</pubDate><guid isPermaLink="false">at://did:plc:2xwpdpt6btxlglcu4ph2jlqd/app.bsky.feed.post/3lwry3fy7gc2c</guid></item></channel></rss>