Now showing items 1-6 of 6
Top-Down Selection in Convolutional Neural Networks
Feedforward information processing fills the role of hierarchical feature encoding, transformation, reduction, and abstraction in a bottom-up manner. This paradigm of information processing is sufficient for task requirements ...
Sweep-Line Extensions to the Multiple Object Intersection Problem: Methods and Applications in Graph Mining
Identifying and quantifying the size of multiple overlapping axis-aligned geometric objects is an essential computational geometry problem. The ability to solve this problem can effectively inform a number of spatial data ...
Comparing Representations of Contribution Labels in Goal Models
Goal models have been proposed to be an effective method to support decision making in early requirements engineering. Key to using them is the concept of contribution links that represent how the satisfaction of one goal ...
Biolocomotion Detection in Videos
Animals locomote for various reasons: to search for food, to find suitable habitat, to pursue prey, to escape from predators, or to seek a mate. The grand scale of biodiversity contributes to the great locomotory design ...
Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) For Natural Language Processing
In this thesis, we propose a new approach to employ fixed-size ordinally-forgetting encoding (FOFE) on Natural Language Processing (NLP) tasks, called dual-FOFE. The main idea behind dual-FOFE is that it allows the encoding ...
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), ...