by Martina Megaro | Feb 12, 2016 | Machine Learning
Assumed Density Filtering Methods for Scalable Learning of Bayesian Neural Networks In this paper, we first rigorously compare the two algorithms and in the process develop several extensions, including a version of EBP for continuous regression problems and a PBP...
by Martina Megaro | Nov 4, 2015 | Digital Fabrication, Visual Computing
AutoConnect: Computational Design of 3D-Printable Connectors We present AutoConnect, an automatic method that creates customized, 3D-printable connectors attaching two physical objects together. November 4, 2015ACM SIGGRAPH Asia 2015 Authors Yuki Koyama (Disney...
by Martina Megaro | Jan 25, 2015 | Machine Learning
The Boundary Forest algorithm for online supervised and unsupervised learning We describe a new instance-based learning algorithm called the Boundary Forest (BF) algorithm, that can be used for supervised and unsupervised learning. The algorithm builds a forest of...
by Martina Megaro | Jan 25, 2015 | Machine Learning
Proximal operators for multi-agent path planning We address the problem of planning collision-free paths for multiple agents using optimization methods known as proximal algorithms. January 25, 2015Association for the Advancement of Artificial Intelligence (AAAI)...
by Martina Megaro | Jul 27, 2014 | Digital Fabrication, Robotics, Visual Computing
Boxelization: Folding 3D Objects Into Boxes We present a method for transforming a 3D object into a cube or a box using a continuous folding sequence. July 27, 2014ACM SIGGRAPH 2014 Authors Yahan Zhou (Disney Research) Shinjiro Sueda (Disney Research)...
