機械学習
Sparse Neural Connectivity Recovery from Partial Measurements
Recover sparse neural connectivity from partial measurements using a covariance-based approach with Granger-causality refinement.
Infer the weight matrix of recurrent neural networks from sparse, partial observations of neural activity.
基于协方差和格兰杰因果的稀疏神经连接恢复方法,从部分观测中推断循环神经网络的连接权重矩阵。
触发词:sparse neural connectivity, partial measurements, covariance-based estimation, Granger causality,
neural connectivity recovery, recurrent neural network, RNN weight estimation, sparse recovery, 稀疏神经连接, 部分观测, 协方差估计