Now showing items 1-2 of 2
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), ...
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 ...