AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity

Joel Ye, Jennifer L Collinger, Leila Wehbe, Robert Gaunt

NeurIPS 2023 · Architectures and efficiency › Spiking networks · approach: Sparse efficient spiking sequence models · 24 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cross-subject human pretraining data (ablation)NDT2 · Human reach intent decoding P2velocity R2: 0.487 -> 0.503Improved
add cross-task (online control) pretraining data (ablation)NDT2 · Human reach intent decoding P2velocity R2: 0.444 -> 0.503Improved
add cross-task pretraining data (ablation)NDT2 · Human reach intent decoding P3velocity R2: 0.493 -> 0.515Improved
add monkey data to pretraining or decoder preparation (ablation)NDT2 · Human reach intent decodingvelocity R2: 0.503 -> 0.486 (P2), 0.515 -> 0.472 (P3)Hurt
pretrain on other sessions/subjects/tasks (multi-context) vs single-sessionNDT2 · RTT monkey Indy, 300 trialsvelocity R2 / NLLImproved
add stitching layers instead of context tokens for multi-context dataNDT1 · RTT sortedvelocity R2 / NLLHurt
use unsorted instead of sorted spikesNDT2 · RTTvelocity R2Improved
add session context tokens (1 vs none) (ablation)NDT2 · sorted multisession NLLNLLImproved
increase number of session/subject tokens beyond one (ablation)NDT2 · multi-session / subject transferNLLNo clear effect
use smaller patches (8 vs 32 neurons) (ablation)NDT2 · RTTNLL / decoding R2Mixed
vary mask ratio (ablation)NDT2 · 5 datasetsdecodingNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy