Tensor Methods for Efficient, Robust, and Continual Machine Learning

Dr. Panagiotis (Panos P.) Markopoulos

UTSA

Friday, September 23, 2022

11am – 12pm CST

Abstract: Tensors are data structures that generalize vectors and matrices to arrays of higher order. Similar to matrices, tensors capture and preserve inherent correlations between measurements. For example, an RGB video can be naturally structured as a 4-way tensor such that entries (50,112,3,10) and (50,112,3,11) correspond to the value of the same pixel (50, 112), at the same frequency (B), and successive time frames (10 and 11). Accordingly, over the past decades, tensors have found numerous applications in fields such as signal processing, data mining, machine learning, and computer vision. More recently, the use of tensors has extended to modeling, training, and processing neural network parameters, such as in convolutional filters and fully connected layers. Similar to matrices, tensors are amenable to latent-factor analysis, that can serve multiple purposes, including compression, feature extraction, visualization, and denoising. In this talk, we will focus on deep learning and show how tensor factorization methods have been used for delivering effective solutions for efficient, robust, and continual machine learning.

Join from the webinar link

https://utsa.webex.com/utsa/j.php?MTID=m6b944381e9981692a5f461d1f8d69d39