はてなブックマーク

Li Wan, Matthew Zeiler, Sixin Zhang, Yann LeCun, Rob Fergus Dept. of Computer Science, Courant Institute of Mathematical Science, New York University Introduction We introduce DropConnect, a generalization of Hinton's Dropout for regularizing large fully-connected layers within neural networks. When training with Dropout, a randomly selected subset of activations are set to zero within each layer.

If you use the dataset, please cite the following work: Indoor Segmentation and Support Inference from RGBD Images ECCV 2012 [PDF][Bib] Samples of the RGB image, the raw depth image, and the class labels from the dataset. Overview The NYU-Depth V2 data set is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras from the Microsoft Kinect. It fea

Deep Learning Methods for Vision CVPR 2012 Tutorial 9:00am-5:30pm, Sunday June 17th, Ballroom D (Full day) Rob Fergus (NYU), Honglak Lee (Michigan), Marc'Aurelio Ranzato (Google) Ruslan Salakhutdinov (Toronto), Graham Taylor (Guelph), Kai Yu (Baidu) Overview Hand-designed features such as SIFT and HOG underpin many successful object recognition approaches. However, these only capture low-level edg

Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models Gideon Mann Google gmann@google.com Ryan McDonald Google ryanmcd@google.com Mehryar Mohri Courant Institute and Google mohri@cims.nyu.edu Nathan Silberman Google nsilberman@google.com Daniel D. Walker∗ NLP Lab, Brigham Young University danl4@cs.byu.edu Abstract Training conditional maximum entropy models on massive da

CSCI-GA.3033-003 Scott Burton Financial Software Projects Graduate Division - Computer Science Tuesday 7:10-9:00  WWH Room WWH 3 This course will be taught by a veteran Wall St. technology manager currently employed at a top tier investment bank. The theme of this course will be “applied case study” and will focus on Fixed Income markets. The semester will begin with a big-picture view of the mark

OUT OF THEIR MINDS: The Lives and Discoveries of 15 Great Computer Scientists Computer science is one of the most important forces shaping today's society and the future, yet it is one of the least understood. Who made the key breakthroughs and how did they do it? This page has been translated to Russian by Decoded Butter. Into Ukrainian by Lesley Ryan of domyessay. Into Belarussian by Alex Navid

Jump to: A detailed tutorial description of the algorithm. References and links to LLE publications and (p)reprints. Gallery of example pictures and animations. LLE code page. Some notes and pointers to related work. Sam T. Roweis............ roweis at cs dot toronto dot edu ...... www.cs.toronto.edu/~roweis/ Lawrence K. Saul......... lsaul@research.att.com.......... www.research.att.com/~lsaul/

Multi-Touch Interaction Research © 2006, Jeff Han Bi-manual, multi-point, and multi-user interactions on a graphical display surface. Update Jan-2007: Yes, we saw the keynote too! We have some very, very exciting updates coming soon- stay tuned! Update: We've spun this off into a company, Perceptive Pixel While touch sensing is commonplace for single points of contact, multi-touch sensing enables

Jeff Han Consultant Department of Computer Science Courant Institute of Mathematical Sciences New York University email: jhan at cs.nyu.edu Note! This site is no longer being maintained! I have not been affiliated with NYU since 2006, when I founded Perceptive Pixel Research Interests: I am a consulting research scientist for NYU's Department of Computer Science, currently working with Yann Lecun

Multi-Touch Sensing through LED Matrix Displays Using an LED display bidirectionally to optically detect finger touches Two scalable techniques for enabling ordinary LED matrices to simultaneously act as multi-touch input devices. In 1977, Forrest M. Mims reminds us in one of his "Engineer's Notebooks" that LEDs can also be used as photodiodes... More info coming soon, I promise... Short video [12

Multi-Touch Interaction Research © 2006, Jeff Han Bi-manual, multi-point, and multi-user interactions on a graphical display surface. Update Jan-2007: Yes, we saw the keynote too! We have some very, very exciting updates coming soon- stay tuned! Update: We've spun this off into a company, Perceptive Pixel While touch sensing is commonplace for single points of contact, multi-touch sensing enables

Currently Core Library (from v1.4) uses GNU Multiple Precision Arithmetic Library (GMP) as its low level big number package. GMP is a free library for arbitrary precision arithmetic, operating on signed integers, rational numbers, and floating point numbers. As GMP was originally designed to work under Unix platform, there is few information about how to compile and install under Windows platform.

Courses and Tutorials [CSCI-GA.2566-001] Fall -- Foundations of Machine Learning. [CSCI-GA.3033-007] Spring - Advanced Machine Learning. [CSCI-GA.3850-006] Spring - Ph.D. Research Seminar - Machine Learning.

Table of Contents Entity/Relationship and Relational Models Purpose of the ER Model and Basic Concepts Entity Relationship Attribute Keys ER Diagrams Binary Relationships and Their Functionality Binary Relationships and ... (Cont.) Binary Relationships and ... (Cont.) Binary Relationships and ... (Cont.) Binary Relationships Involving One Entity Set Non-Binary Relationships Non-Binary Relationship