arXiv:1605.09081 [stat.ML]AbstractReferencesReviewsResources
Understanding Convolutional Neural Networks
Published 2016-05-30Version 1
Convoulutional Neural Networks (CNNs) exhibit extraordinary performance on a variety of machine learning tasks. However, their mathematical properties and behavior are quite poorly understood. There is some work, in the form of a framework, for analyzing the operations that they perform. The goal of this project is to present key results from this theory, and provide intuition for why CNNs work.
Comments: Statistical Machine Learning Course Project at Carnegie Mellon University
Related articles: Most relevant | Search more
arXiv:1506.01113 [stat.ML] (Published 2015-06-03)
Multi-Objective Optimization for Self-Adjusting Weighted Gradient in Machine Learning Tasks
arXiv:1701.01293 [stat.ML] (Published 2017-01-05)
OpenML: An R Package to Connect to the Networked Machine Learning Platform OpenML
Giuseppe Casalicchio et al.
arXiv:1904.04917 [stat.ML] (Published 2019-04-09)
Novel Uncertainty Framework for Deep Learning Ensembles