< Back to Article

Learning brain dynamics for decoding and predicting individual differences

Fig 1

Model architectures based on neural networks with gated recurrent units (GRUs).

(A) Classifier. At each time step, time series data,x_t, provided inputs. The recurrent neural network transformed the inputs into a latent representation, h_t, which then determined the output class scores, . The unit with highest activation determined the model’s prediction of the input stimulus at each time. (B) Dimensionality reduction. The encoder shares the GRU component shown in A. GRU outputs, h_t, were first linearly projected to a lower-dimensional space using a fully-connected layer (DR-FC). Classification was then performed based on the low-dimensional representation, . (C) Input signal reconstruction. A separate GRU was trained independently to reconstruct the original brain signals based on the low-dimensional signals, .

doi: https://doi.org/10.1371/journal.pcbi.1008943.g001