Understanding Gaussian noise injections in neural networks

Thesis

Deep Learning (read neural networks) has emerged as one of the most exciting and powerful tools in the statistical machine learning toolbox. Neural networks over the past decade have defeated incumbent state of the art models in computer vision, natural language processing, and reinforcement learning; amongst a myriad of other fields. Though these achievements are impressive, neural networks remain surprisingly brittle, especially in the case of smaller network architectures. They can easi...

Expand abstract

Authors: Camuto, A

• DOI: 10.5287/ora-zbodknqoq
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: Statistics; Deep Learning; Probabilistic Models; Deep Generative Models; Variational Autoencoders; Harmonic Analysis; Neural Networks; Noise; Deep Learning
• Subjects: Deep learning (Machine learning)