Gabriel Barello

The paper develops a biophysical model of chromatophore arrays to generate dynamic skin patterns similar to those in cephalopods, showing that minimal central control can produce complex behaviors.

This paper introduces a sparse-coding variational auto-encoder (SVAE) that improves upon sparse coding by using a probabilistic model with a deep neural network, achieving better performance on natural image data.

This paper uses GANs to fit mechanistic neural network models to experimental tuning curves, capturing their diversity without requiring explicit likelihood computation.