AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Deep Multi-State Dynamic Recurrent Neural Networks Operating on Wavelet Based Neural Features for Robust Brain Machine Interfaces

Benyamin Allahgholizadeh Haghi, Spencer Kellis, Sahil Shah, Maitreyi Ashok, Luke Bashford, Daniel Kramer, Brian Lee, Charles Liu, Richard Andersen, Azita Emami

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 14 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 prediction feedback and scheduled sampling to the recurrent decoder (DRNN vs standard recurrent nets)DRNN · single-day PPC center-out, MWT featuresaverage R2 (Y position)Improved
use mid-frequency wavelet features (MWT) instead of other 11 neural featuresDRNN · multi-day, trained on first 20 days of 2015R2Improved
use MWT instead of other features in cross-day analysis (train on one day, test on all others)DRNN · cross-day, 43 daysaverage R2Improved
train on only 10% of single-day dataDRNN · single-day, 2018-04-23regression quality (qualitative)No clear effect
use DRNN instead of other linear and nonlinear decoders over many daysDRNN · multi-day, days 21-43average R2Improved
increase number of training days from 1 to 20Deep-DRNN and DRNN · multi-dayR2Improved
use small DRNN (1 layer, 10 nodes, history 10) instead of Deep-DRNN (2 layers, 50 and 25 nodes, history 20)DRNN · multi-day, varying training daysR2No clear effect
re-train DRNN with 5-90% of subsequent test daysDRNN · multi-dayR2Improved
re-train annually versus only once on the first 20 daysDRNN · multi-dayR2No clear effect
train on first 90% of the same test day versus 20 prior daysDRNN · multi-dayaverage R2Improved
use feedback only, feedback with noise instead of neural data, or neural data only at trial start (ablation)DRNN · center-out predictionsprediction quality (qualitative)Hurt

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