Fig. 1: Changes in the geometry of object manifolds as they are transformed in a deep neural network.
From: Separability and geometry of object manifolds in deep neural networks
Illustration of three layers in a visual hierarchy where the population response of the first layer is mapped into intermediate layer by F1 and into the last layer by F2 (top). The transformation of per-stimuli responses is associated with changes in the geometry of the object manifold, the collection of responses to stimuli of the same object (colored blue for a ‘dog’ manifold and pink for a ‘cat’ manifold). Changes in geometry may result in transforming object manifolds which are not linearly separable (in the first and intermediate layers) into separable ones in the last layer (separating hyperplane, colored orange).
