A large-scale neural network training framework for generalized estimation of single-trial population dynamics.

A large-scale neural network training framework for generalized estimation of single-trial population dynamics.
复制标题

DOI:
10.1038/s41592-022-01675-0
复制
发表时间:
2022-12
期刊:
影响因子:
48
通讯作者:
Pandarinath, Chethan
Pandarinath, Chethan
中科院分区:
生物学1区
文献类型:
--
作者:
Keshtkaran, Mohammad Reza;Sedler, Andrew R.;Chowdhury, Raeed H.;Tandon, Raghav;Basrai, Diya;Nguyen, Sarah L.;Sohn, Hansem;Jazayeri, Mehrdad;Miller, Lee E.;Pandarinath, Chethan

文献摘要

参考文献

被引文献

相似文献

使用深度神经种群动力学模型实现最先进的性能需要为每个新数据集进行广泛的超参数调整。AutoLFADS是一个模型调优框架,它可以在没有行为或任务信息的情况下,自动对来自各种大脑区域和任务的数据生成高性能的自动编码模型。我们通过一系列恒河猴数据集证明了其广泛的适用性:运动皮层在自由节奏达到,躯体感觉皮层在达到扰动,背内侧额叶皮层在认知计时任务。
Achieving state-of-the-art performance with deep neural population dynamics models requires extensive hyperparameter tuning for each new dataset. AutoLFADS is a model-tuning framework that produces high-performing autoencoding models on data from a variety of brain areas and tasks, automatically, without behavioral or task information. We demonstrate its broad applicability via an array of rhesus macaque datasets: motor cortex during free-paced reaching, somatosensory cortex during reaching with perturbations, and dorsomedial frontal cortex during a cognitive timing task.
DOI: 10.1038/nn.2731
发表时间: 2011-02
影响因子: 25
作者:
Stevenson, Ian H.;Kording, Konrad P.
通讯作者: Kording, Konrad P.
DOI: 10.7554/elife.51322
发表时间: 2020-05-04
期刊: ELIFE
影响因子: 7.7
作者:
Berger, Michael;Agha, Naubahar Shahryar;Gail, Alexander
通讯作者: Gail, Alexander
DOI: 10.1126/science.aau6249
发表时间: 2019-05-31
期刊: SCIENCE
影响因子: 56.9
作者:
Jaderberg, Max;Czarnecki, Wojciech M.;Graepel, Thore
通讯作者: Graepel, Thore
DOI: 10.1038/s41592-018-0109-9
发表时间: 2018-10
期刊: Nature methods
影响因子: 48
作者:
Pandarinath C;O'Shea DJ;Collins J;Jozefowicz R;Stavisky SD;Kao JC;Trautmann EM;Kaufman MT;Ryu SI;Hochberg LR;Henderson JM;Shenoy KV;Abbott LF;Sussillo D
通讯作者: Sussillo D
DOI: 10.1523/eneuro.0085-16.2016
发表时间: 2016-07
期刊: eNeuro
影响因子: 3.4
作者:
Kaufman MT;Seely JS;Sussillo D;Ryu SI;Shenoy KV;Churchland MM
通讯作者: Churchland MM