Linear Readout of Object Manifolds
This work addresses a foundational issue in neuroscience and machine learning for understanding sensory processing and invariant recognition, but it appears incremental as it builds on existing manifold theories.
The paper tackled the problem of how sensory representations enable invariant object decoding by analyzing the capacity of a linear perceptron to classify objects from variable neural responses, showing that this capacity depends on the dimensionality, size, and shape of object manifolds.
Objects are represented in sensory systems by continuous manifolds due to sensitivity of neuronal responses to changes in physical features such as location, orientation, and intensity. What makes certain sensory representations better suited for invariant decoding of objects by downstream networks? We present a theory that characterizes the ability of a linear readout network, the perceptron, to classify objects from variable neural responses. We show how the readout perceptron capacity depends on the dimensionality, size, and shape of the object manifolds in its input neural representation.