サクサク読めて、アプリ限定の機能も多数！
トップへ戻る
ドラクエ3
www.cs.ubc.ca/~van
DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning Transactions on Graphics (Proc. ACM SIGGRAPH 2017) Xue Bin Peng (1) Glen Berseth (1) KangKang Yin (2) Michiel van de Panne (1) (1)University of British Columbia (2)National University of Singapore Learning physics-based locomotion skills is a difficult problem, leading to solutions that typically exploit prior knowl
www.cs.ubc.ca
Deep Learning Local Optima Alireza Shafaei - Dec. 2015 Saddle Points A critical point Saddle Points A critical point With Hessian Local minimum: Saddle Points A critical point With Hessian Local minimum: Local maximum: Saddle Points With Hessian ... Saddle point with min-max structure Saddle Points With Hessian ... Saddle point with min-max structure Saddle Points With Hessian ... Saddle point wit
Terrain-Adaptive Locomotion Skills Using Deep Reinforcement Learning Transactions on Graphics (Proc. ACM SIGGRAPH 2016) (to appear) Xue Bin Peng Glen Berseth Michiel van de Panne University of British Columbia Reinforcement learning offers a promising methodology for developing skills for simulated characters, but typically requires working with sparse hand-crafted features. Building on re
Abstract SMAC (sequential model-based algorithm configuration) is a versatile tool for optimizing algorithm parameters (or the parameters of some other process we can run automatically, or a function we can evaluate, such as a simulation). SMAC has helped us speed up both local search and tree search algorithms by orders of magnitude on certain instance distributions. Recently, we have also found
What is FLANN? FLANN is a library for performing fast approximate nearest neighbor searches in high dimensional spaces. It contains a collection of algorithms we found to work best for nearest neighbor search and a system for automatically choosing the best algorithm and optimum parameters depending on the dataset. FLANN is written in C++ and contains bindings for the following languages: C, MATLA
Home | Papers | Software | Licensing Many different machine learning algorithms exist that can easily be used off the shelf, many of these methods are implemented in the open source WEKA package. However, each of these algorithms have their own hyperparameters that can drastically change their performance, and there are a staggeringly large number of possible alternatives overall. Auto-WEKA co
www.cs.ubc.ca/~murphyk
Machine Learning: a Probabilistic Perspective by Kevin Patrick Murphy. MIT Press, 2012. See new web page.
Polynomial Optics: A Construction Kit for Efficient Ray-Tracing of Lens Systems Matthias B. Hullin, Johannes Hanika and Wolfgang Heidrich In: Computer Graphics Forum / Proceedings of EUROGRAPHICS Symposium on Rendering (EGSR) 2012 Caustic of light falling through a lens (Edmund Optics article #NT49-291) where image formation is dominated by ray optics. For each wavelength, we determine a polynomia
www.cs.ubc.ca/~lowe
Note to the reader: I started this web page in the 1990's when there were only a handful of companies with computer vision products. Since then, computer vision has had huge success in developing useful applications, and it is no longer feasible for my list to keep up with the constant growth in the number of companies working in the field. Most large tech companies also have computer vision group
Written by Kevin Murphy. Last updated 16 June 2014. (Thanks to Alex Gorban for helping me with the switch to Google Sheets.) Review articles List of GM code at MLOSS Click here for a short article I wrote for the ISBA (International Society for Bayesian Analysis) Newsletter, December 2007, sumarizing some of the packages below. Click here for a more detailed discussion of some of these packages wr
David Lowe is Professor Emeritus with the Computer Science Department of the University of British Columbia. From 2015-2018, David Lowe was a Senior Research Scientist with Google in the Machine Intelligence Group. From 2009-2015 he was co-founder and chairman of Cloudburst Research, a computer vision startup in Vancouver that was acquired by Google in May 2015. From 1987-2015, he was a professor
www.cs.ubc.ca/~mariusm
www.cs.ubc.ca/~nando
Written by Kevin Murphy, 1999 Last updated: 23 October, 2002. This toolbox supports value and policy iteration for discrete MDPs, and includes some grid-world examples from the textbooks by Sutton and Barto, and Russell and Norvig. It does not implement reinforcement learning or POMDPs. For a very similar package, see INRA's matlab MDP toolbox. Download toolbox A brief introduction to MDPs, POMDPs
www.cs.ubc.ca/~hoos
All instances provided here are cnf formulae encoded in DIMACS cnf format. This format is supported by most of the solvers provided in the SATLIB Solvers Collection. For a description of the DIMACS cnf format, see DIMACS Challenge - Satisfiability: Suggested Format (ps file, 108k) (taken from the DIMACS FTP site). Please help us to extend our benchmark set by submitting new benchmark instances or
See also kernel-machines.org. List originally created by Vlad Magdin (UBC), 25 April 2005. Updated by Kevin Murphy, 15 December 2005.
www.cs.ubc.ca/~harrison
We all know that Quicksort is one of the fastest algorithms for sorting. It's not often, however, that we get a chance to see exactly how fast Quicksort really is. The following applets chart the progress of several common sorting algorithms while sorting an array of data using in-place algorithms. This means that the algorithms do not allocate additional storage to hold temporary results: they so
Written by Kevin Murphy, 1998. Last updated: 8 June 2005. Distributed under the MIT License This toolbox supports inference and learning for HMMs with discrete outputs (dhmm's), Gaussian outputs (ghmm's), or mixtures of Gaussians output (mhmm's). The Gaussians can be full, diagonal, or spherical (isotropic). It also supports discrete inputs, as in a POMDP. The inference routines support filtering,
www.cs.ubc.ca/~rbridson
Dept. Computer Science, UBC 201-2366 Main Mall Vancouver, V6T 1Z4, Canada Current Position As of August 2013 I am no longer a full-time professor at UBC, but retain adjunct status. I am not taking on graduate students for supervision. I am now a Senior Principal Research Scientist for Visual Effects at Autodesk. Symposium on Computer Animation I helped organize SCA 2011, August 5-7 in Vancouver, j
A Brief Introduction to Graphical Models and Bayesian Networks By Kevin Murphy, 1998. "Graphical models are a marriage between probability theory and graph theory. They provide a natural tool for dealing with two problems that occur throughout applied mathematics and engineering -- uncertainty and complexity -- and in particular they are playing an increasingly important role in the design and ana
BNT has moved to https://github.com/bayesnet/bnt. It is not supported or maintained.
Moved to here.
Implementations of the SIFT Keypoint Detector There are many publicly available implementations of SIFT. A good one is VLFeat by Andrea Vedaldi. There are also versions in OpenCV and other sources. For historic purposes, this page provides access to an older 2005 demo version of David Lowe's SIFT keypoint detector in the form of compiled binaries that can run under Linux or Windows. The demo softw
Sorting Algorithms We all know that Quicksort is one of the fastest algorithms for sorting. It's not often, however, that we get a chance to see exactly how fast Quicksort really is. The following applets chart the progress of several common sorting algorithms while sorting an array of data using in-place algorithms. This means that the algorithms do not allocate additional storage to hold tempora
Robert Bridson Matthias Müller-Fischer Book A large part of this course was extended with a lot of new material into a book, Fluid Simulation for Computer Graphics, available from A K Peters. SIGGRAPH 2007 Course Notes You can download the current version of the course notes here: fluids_notes.pdf. SIGGRAPH 2007 Presentations The basics of fluids: BasicFluids.ppt. Real-time fluids: GameFluids2007.
Written by Kevin Murphy, 1998. Last updated: 7 June 2004. This toolbox supports filtering, smoothing and parameter estimation (using EM) for Linear Dynamical Systems. Download toolbox What is a Kalman filter? Example of Kalman filtering and smoothing for tracking What about non-linear and non-Gaussian systems? Other software for Kalman filtering, etc. Recommended reading Functions kalman_filter ka
次のページ
このページを最初にブックマークしてみませんか？
『www.cs.ubc.ca』の新着エントリーを見る
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
