Zoom link: https://us02web.zoom.us/j/87537900653?pwd=RXcrb2N3MnMvek4vZ2VjRis4ei81dz09 

Meeting ID: 875 3790 0653
Passcode: TAUEESYS  

Speaker: Dr.  Ariel Jaffe

Applied Mathematics, Yale University

Monday, December 14^th, 2020, at 15:00

Recovering tree models via spectral graph theory

Abstract

Modeling high dimensional data by latent tree graphical models is a common approach in multiple machine learning applications. In these models, the key task is to infer the structure of the tree, given only observations on its leaves. A canonical example of this setting is the tree of life, where the evolutionary history of a set of organisms is inferred by their nucleotide or protein sequences.
In this talk, we will show that the tree structure is strongly related to the spectral properties of a fully connected graph, defined over the terminal nodes of the tree.  This relation forms the theoretical basis of two new methods to recover latent tree models: (i) spectral neighbor joining, where subsets of nodes are iteratively merged to form the full tree, and (ii) spectral top down recovery, where the terminal nodes are iteratively partitioned into smaller subsets. Comparing our approach to several competing methods, we show that in many settings, spectral methods have stronger theoretical guarantees and work better in practice.
Short Bio

Ariel Jaffe is a Gibbs assistant professor in the program of applied mathematics, Yale University.  
Previously, he completed his Ph.D. in the Weizmann Institute of Science under the guidance of Prof. Boaz Nadler. His research interests include statistical machine learning and high dimensional data analysis, with a focus on applications in the fields of computational biology and signal processing.‏

השתתפות בסמינר תיתן קרדיט שמיעה = עפ"י רישום שם מלא + מספר ת.ז.  בצ'אט

Zoom link: https://us02web.zoom.us/j/82241257771?pwd=R2paU3puSEljOTRXeFZyeFk1OTZ5dz09

Meeting ID: 822 4125 7771
Passcode: TAUEESYS  

Speaker: Dr.  Hadar Averbuch-Elor

Cornell-Tech

Monday, December 7^th, 2020, at 15:00

Deep into 3DV: Pushing the Boundaries of 3D Vision

Abstract

3D computer vision has significantly advanced over the past several decades, with modern algorithms successfully reconstructing entire urban cities. However, many questions remain unexplored, as geometric reasoning alone cannot fully infer the connections among images capturing different parts of the scene or semantic relationships between images captured at distant geographic locations.   

In this talk, I will present an ongoing line of research that leverages powerful deep networks to address new and exciting problems in 3D vision. Considering a single 3D scene, we ask: Can we estimate the relative camera rotation between a pair of images in an extreme setting, where the images have little to no overlap? We address this seemingly impossible task by designing a neural network that can implicitly reason about hidden cues, such as vanishing points and direction of shadows. Expanding beyond a single scene, we jointly analyze dozens of 3D-augmented collections and connect them to a new domain: language. We demonstrate how a joint learned model that considers language, images, and 3D geometry can reason about the rich semantics associated with complex architectural landmarks. Finally, I will discuss several future directions. 

Short Bio

Hadar Averbuch-Elor is a postdoctoral researcher at Cornell-Tech working with Prof. Noah Snavely. Her research interests lie in the intersection of computer graphics and computer vision. Currently, her research focuses on understanding and manipulating visual concepts by combining pixels with more structured modalities, including natural language and 3D geometry. She completed her PhD in Electrical Engineering at Tel-Aviv University in Israel where she was advised by Prof. Daniel Cohen-Or. She also held research positions at Facebook and Amazon AI. Hadar has received several awards including the Zuckerman Postdoctoral Scholar Fellowship and the Tel Aviv University President Award for Women.‏ 

השתתפות בסמינר תיתן קרדיט שמיעה = עפ"י רישום שם מלא + מספר ת.ז.  בצ'אט