Zenke Lab to present spiking network and surrogate gradient work at Bernstein Conference
hisspikeness · x · 2026-09-26
Zenke Lab (FMI) shared its Bernstein Conference schedule: three workshop talks plus posters. Highlights include connectome-constrained spiking models of a zebrafish place-cell circuit (robust to partial calcium data, fragile to incomplete connectomes), theory behind surrogate gradients for training SNNs, and a talk linking representation learning to local plasticity.
More from Research
- Synaptic pruning and infantile amnesia as biology's version of pre/post-training — sytelus · 2026-09-26
- The Pre-Training / Post-Training Divide Doesn't Exist in Biology — JosephJacks_ · 2026-09-26
- Peking University finds models "know" answers but can't say them: the Readout Bottleneck — jiqizhixin · 2026-09-26
- Silent mistakes that can hurt your Numerai models, per new community writeup — matlabulous · 2026-09-26
- Michael Levin: intelligence doesn't require genes, cognition is widespread in life — drmichaellevin · 2026-09-26
- Position paper argues grounded abduction is the missing reasoning leap for LLMs — bibryam · 2026-09-26