Pengfei
@pengfei-sun.bsky.social
I’m a postdoc @Imperial, advised by @danakarca.bsky.social and @neural-reckoning.org.
I’m passionate about brain‑inspired neural networks, focusing on delay learning in RNNs (spiking/rate) and lightweight attention mechanisms.
I’m passionate about brain‑inspired neural networks, focusing on delay learning in RNNs (spiking/rate) and lightweight attention mechanisms.
thanks! will check and follow this.
November 14, 2025 at 12:58 PM
thanks! will check and follow this.
Thanks for this insightful comment. I expect that low-precision weights and Gaussian noise could play a similar role as sources of imprecision, and that delays (or other parameters) offer additional degrees of freedom that can compensate for it. Good way to further explore
November 14, 2025 at 12:20 PM
Thanks for this insightful comment. I expect that low-precision weights and Gaussian noise could play a similar role as sources of imprecision, and that delays (or other parameters) offer additional degrees of freedom that can compensate for it. Good way to further explore
This might suggest that a large fraction of computational power may actually live in the temporal parameters, not just in the weights.
November 13, 2025 at 8:52 PM
This might suggest that a large fraction of computational power may actually live in the temporal parameters, not just in the weights.
🔗 Try it now: github.com/neural-recko...
GitHub - neural-reckoning/temporal-shd: Variant of the SHD dataset with only timing information retained
Variant of the SHD dataset with only timing information retained - neural-reckoning/temporal-shd
github.com
July 24, 2025 at 5:48 PM
🔗 Try it now: github.com/neural-recko...