Feng Zhu

PhD student in Neuroscience at Emory University. Research: Computational Neuroscience and Machine Learning.

[Takaki Komiyama @takaki_komiyama]

663 days since the senseless tragedy that took An, we present a manuscript that reports some of the discoveries that she left us.

https://t.co/hEbu4OfH1E

[Jonathan McCart @JonathanDMcCart]

Modern neuroscientists routinely record the complex, goal-oriented, and time-varying activity of thousands of neurons. Can we find representations of neural activity that 1) are human-interpretable and 2) enable the generation of neural activity for unrecorded behavioral conditions? We present our recent work on Generating Neural Observations Conditioned on Codes with High Information (GNOCCHI) 🥔🍝 !!

By leveraging unsupervised, information-based diffusion models, GNOCCHI can discover interpretable latent spaces from neural data and generate high-quality neural activity for specific conditions outside of the set of available neural recordings!

[Feng Zhu @fzhu23]

To take it for a spin, check out our demo using SBTT with a sequential autoencoder and Lorenz dataset (https://t.co/b8EPE0V27y).

To appear as a poster at #NeurIPS2021!
https://t.co/Qkt8TklXcW
/end

[Feng Zhu @fzhu23]

Want more neurons & higher frequencies, but don’t have the bandwidth?😢

Check out SBTT💪, a new way to infer neural dynamics with spatio-temporal superresolution! 🧠📈

At #NeurIPS2021
w/ co-first @arsedle, Grier, @nauman_ahad, Davenport, @MattAntimatt, @agiovann76, @chethan
🧵

[Feng Zhu @fzhu23]

Finally, performance on sparse data is boosted by pretraining on fully observed data to learn dynamics. This points towards a new paradigm for power savings in BMIs - initial high-bandwidth modes for pretraining and subsequent low-bandwidth (low-power) modes for long-term use.
9/

[Chethan Pandarinath @chethan]

Do you like

✅Neural population dynamics🧠?
✅2P Calcium imaging🔬?

Come see @fzhu23 at 3-043!

RADICaL: a new DL method to extract network dynamics

Achieves sub-frame temporal resolution 👉 Substantially improved accuracy! 📈

Exciting collab with @agiovann76 @MattAntimatt!