Beyond the Patterns 32 - Raghavendra Selvan: Quantum Tensor Networks for Medical Image Analysis

0:04 Opening 1:59 Introduction by Raghav 5:19 Introduction to Quantum Tensor Networks 12:09 Penrose’s Tensor Notation 14:20 Linear Models in High-dimensional Spaces 22:26 Tensor dot product approximations 30:10 Tensor Networks for Medical Image Classification 35:01 Classification Evaluation 40:12 Tensor Networks for Image Segmentation 45:17 Segmentation Evaluation 49:22 Summary & Conclusion 55:38 Discussion 1:10:19 Concluding Remarks It’s a great pleasure to welcome Raghav Selvan from the University of Copenhagen at our lab! Abstract: Quantum Tensor Networks (QTNs) provide efficient approximations of operations involving high dimensional tensors and have been extensively used in modeling quantum many-body systems and also compressing large neural networks. More recently, supervised learning has been attempted with tensor networks, and has primarily focused on classification of 1D signals and small images. In this talk, we will look at two formulations of QTN-based models for 2D & 3D medical image classifica