Alex Immer
@aleximmer.bsky.social
Research Scientist @Bioptimus. Previously at ETH Zürich, Max Planck Institute for Intelligent Systems, Google Research, EPFL, and RIKEN AIP.
aleximmer.github.io
aleximmer.github.io
Reposted by Alex Immer
⚡️ Excited to introduce ZAPBench, our #ICLR2025 spotlight: The Zebrafish Activity Prediction Benchmark measures progress in predicting neural activity within an entire vertebrate brain (70k+ neurons!)
Explore interactive visualizations, datasets, code + paper: google-research.github.io/zapbench
🧠🧪
Explore interactive visualizations, datasets, code + paper: google-research.github.io/zapbench
🧠🧪
ZAPBench
ZAPBench evaluates how well different models can predict the activity of over 70,000 neurons in a novel larval zebrafish dataset.
google-research.github.io
March 4, 2025 at 3:22 PM
⚡️ Excited to introduce ZAPBench, our #ICLR2025 spotlight: The Zebrafish Activity Prediction Benchmark measures progress in predicting neural activity within an entire vertebrate brain (70k+ neurons!)
Explore interactive visualizations, datasets, code + paper: google-research.github.io/zapbench
🧠🧪
Explore interactive visualizations, datasets, code + paper: google-research.github.io/zapbench
🧠🧪
Optimizing the marginal likelihood encoding the idea of Occam's razor leads to more sparsifiable neural networks. The title is 🔥
📢 Excited to present our work at #NeurIPS2024!
📄 "Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood"
Read it here: arxiv.org/abs/2402.15978
Details in 🧵
📄 "Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood"
Read it here: arxiv.org/abs/2402.15978
Details in 🧵
December 10, 2024 at 10:32 AM
Optimizing the marginal likelihood encoding the idea of Occam's razor leads to more sparsifiable neural networks. The title is 🔥