Now showing items 1-3 of 3
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
This thesis introduces a two-stream model for dynamic texture synthesis. The model is based on pre-trained convolutional networks (ConvNets) that target two independent tasks: (i) object recognition, and (ii) optical flow ...
SuperLattice documents the creation of a hybrid structure that combines human perception with computational methods of processing information. Through SuperLattice I showcase the malleability of data and highlight the ...
Adaptive Momentum for Neural Network Optimization
In this thesis, we develop a novel and efficient algorithm for optimizing neural networks inspired by a recently proposed geodesic optimization algorithm. Our algorithm, which we call Stochastic Geodesic Optimization (SGeO), ...