Search Results for author: Sebastian Thrun

Found 5 papers, 3 papers with code

BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits

1 code implementation NeurIPS 2020 Mo Tiwari, Martin J. Zhang, James Mayclin, Sebastian Thrun, Chris Piech, Ilan Shomorony

In these experiments, we observe that BanditPAM returns the same results as state-of-the-art PAM-like algorithms up to 4x faster while performing up to 200x fewer distance computations.

Multi-Armed Bandits

BanditPAM: Almost Linear Time $k$-Medoids Clustering via Multi-Armed Bandits

2 code implementations11 Jun 2020 Mo Tiwari, Martin Jinye Zhang, James Mayclin, Sebastian Thrun, Chris Piech, Ilan Shomorony

Current state-of-the-art $k$-medoids clustering algorithms, such as Partitioning Around Medoids (PAM), are iterative and are quadratic in the dataset size $n$ for each iteration, being prohibitively expensive for large datasets.

Multi-Armed Bandits

Skin Cancer Detection and Tracking using Data Synthesis and Deep Learning

no code implementations4 Dec 2016 Yunzhu Li, Andre Esteva, Brett Kuprel, Rob Novoa, Justin Ko, Sebastian Thrun

Dense object detection and temporal tracking are needed across applications domains ranging from people-tracking to analysis of satellite imagery over time.

Dense Object Detection

Learning to Track at 100 FPS with Deep Regression Networks

3 code implementations6 Apr 2016 David Held, Sebastian Thrun, Silvio Savarese

We propose a method for offline training of neural networks that can track novel objects at test-time at 100 fps.

Deep Learning for Single-View Instance Recognition

no code implementations29 Jul 2015 David Held, Sebastian Thrun, Silvio Savarese

We show that feedforward neural networks outperform state-of-the-art methods for recognizing objects from novel viewpoints even when trained from just a single image per object.

Cannot find the paper you are looking for? You can Submit a new open access paper.