Convolutional codes

Monday, October 5, 2009 - 2:00pm - 2:30pm
Yann LeCun (New York University)
Keywords: unsupervised learning, object recognition, sparse coding,
convolutional networks

Abstract:Image processing and recognition has traditionally relied on hard-wired
features and trainable classifiers. The next challenge of computer
vision, machine learning, and image processing, is to devise methods
that can automatically learn feature extractors and high-level image
representations from labeled and unlabeled data. The set of methods
collectively known as Deep Learning is an attempt to learn
Thursday, April 19, 2007 - 1:30pm - 2:20pm
Heide Gluesing-Luerssen (University of Kentucky)
Convolutional codes can be described by linear input-state-output systems. This gives rise to a state transition graph and an associated weight adjacency matrix. The latter counts in a detailed way the weights occurring in the code. After discussing some uniqueness issues we will present a MacWilliams identity theorem for convolutional codes and their duals in terms of the weight adjacency matrix. Furthermore, we will discuss isometries for convolutional codes and their effect on the weight adjacency matrix.
Subscribe to RSS - Convolutional codes