Shi Gu

Although post-hoc and probably inaccurate, we can still have some kind of picture about the embedding and geometric evolution of the loss landscape. For the brain-inspired/neuromorphic learning, can we think similarly beyond "intuition"?

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? 😡

Attending #NeurIPS2024 today. Excited to see old and new friends. Our presentation on spiking neural networks (SNNs) will be on Wed 11 Dec 11 a.m. PST 2 p.m. PST at East Exhibit Hall A-C #2410. Happy to chat on NeuroAI both from neuroscience and AI views.

How will the multitask and incremental learning help shape the modularized structure of both ANNs and brain networks? Meet me at poster A24 on Tuesday at #CCN2024 @CogCompNeuro. Excited to meet old and new friends!!!

Heading to Boston today for #CCN2024 @CogCompNeuro. Happy to chat on neural network, neural computing, and AI behaviors during the stay.

I will be at @OHBM 2024 in Seoul from Jun 23 to June 27. Happy to meet old and new friends : )