Fig. 2: The BNN model architecture.
From: The origin and evolution of open habitats in North America inferred by Bayesian deep learning models
a The spatial and temporal distances extracted separately for 100 mammal and plant taxa (Fig. 1), are the input of the first two hidden layers in the BNN model. During training, the BNN optimizes weights (represented by lines labeled with \({w}_{{X}}\)) to reduce the multitude of spatial and temporal distance measurements into one single “proximity” value for each taxon (taxon nodes) relative to the given point in space and time. This process of feature generation is equivalent to the convolutional layers in an image classifier, reducing higher-dimensionality data into lower-dimensionality features for input into the subsequent neural network layers. In some of our tested models the resulting taxon features are pooled before being passed on to the next layer. b The taxon node values (“Biotic features”) are then used in combination with the abiotic features as input into the fully connected BNN classifier layers. Jointly with the weights of the feature generation layers, the weights of the BNN classifier are estimated during training through MCMC sampling, to optimally map the input data to the correct output vegetation label (“open” or “closed”). Once trained, a posterior sample of the weights is stored for each model and is used to make vegetation predictions for points with unknown vegetation interpretation.
