Now showing items 1-5 of 5
The Role of Early Recurrence in Improving Visual Representations
This dissertation proposes a computational model of early vision with recurrence, termed as early recurrence. The idea is motivated from the research of the primate vision. Specifically, the proposed model relies on the ...
Merging the Natural with the Artificial: The Nature of a Machine and the Collapse of Cybernetics
This thesis is concerned with the rise and fall of cybernetics, understood as an inquiry regarding the nature of a machine. The collapse of this scientific movement, usually explained by external factors such as lack of ...
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 ...
Efficient Calculation of Optimal Configuration Processes
Customers are getting increasingly involved in the design of the products and services they choose by specifying their desired characteristics. As a result, configuration systems have become essential technologies to support ...
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), ...