<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><description>I’m a postdoc @Imperial, working with @neural-reckoning.org.&#xA; I’m passionate about brain‑inspired neural networks, focusing on delay learning in RNNs (spiking/rate) and lightweight attention mechanisms.</description><link>https://bsky.app/profile/pengfei-sun.bsky.social</link><title>@pengfei-sun.bsky.social - Pengfei</title><item><link>https://bsky.app/profile/pengfei-sun.bsky.social/post/3m5k2aedqgc2r</link><description>With my great advisors and colleagues, @achterbrain.bsky.social @zhe @danakarca.bsky.social @neural-reckoning.org, we show that if heterogeneous axonal delays (imprecise) can capture the essential temporal structure of a task, spiking networks do not need precise synaptic weights to perform well.&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>13 Nov 2025 20:51 +0000</pubDate><guid isPermaLink="false">at://did:plc:7unlunktsvt2d3onsx2pqi6v/app.bsky.feed.post/3m5k2aedqgc2r</guid></item><item><link>https://bsky.app/profile/pengfei-sun.bsky.social/post/3luq3q4m7ks2x</link><description>Together with my supervisor and the Neural Reckoning team neuralreckoning.bsky.social, we’ve developed a new SHD/SSC variant that strips out rate information but spike‑timing information—designed to really challenge SNNs. Your feedback is welcome—let us know how it performs in your models!&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>24 Jul 2025 17:47 +0000</pubDate><guid isPermaLink="false">at://did:plc:7unlunktsvt2d3onsx2pqi6v/app.bsky.feed.post/3luq3q4m7ks2x</guid></item></channel></rss>