About
The ever increasing size of available data to be processed by machine learning algorithms has yielded several approaches, from online algorithms to parallel and distributed computing on multi-node clusters. Nevertheless, it is not clear how modern machine learning approaches can either cope with such parallel machineries or take into account strong constraints regarding the available time to handle training and/or test examples.
This workshop explores two alternatives:
- modern machine learning approaches that can handle real time processing at train and/or at test time, under strict computational constraints (when the flow of incoming data is continuous and needs to be handled), and\
- modern machine learning approaches that can take advantage of new commodity hardware such as multicore, GPUs, and fast networks.
This two-day workshop aims to set the agenda for future advancements by fostering a discussion of new ideas and methods and by demonstrating the potential uses of readily-available solutions. It brings together both researchers and practitioners to offer their views and experience in applying machine learning to large scale learning.
Find out more at the Workshop website.
Videos
Overcoming Computational Bottlenecks in Machine Learning

New Quasi-Newton Methods for Efficient Large-Scale Machine Learning
Dec 29, 2007
·
6978 views

Who is Afraid of Non-Convex Loss Functions?
Dec 29, 2007
·
46903 views

Architecture Conscious Data Analysis: Progress and Future Outlook
Dec 29, 2007
·
3670 views

Efficient Machine Learning using Random Projections
Dec 29, 2007
·
5981 views

Learning with Millions of Examples and Dimensions - Competition proposal
Feb 1, 2008
·
3711 views

Stationary Features and Folded Hierarchies for Efficient Object Detection
Dec 29, 2007
·
4566 views

Large Scale Learning with String Kernels
Dec 29, 2007
·
8961 views

Model Compression: Bagging your Cake and Eating it too (part 1)
Dec 29, 2007
·
4083 views

Large Scale Sequence Labelling
Dec 29, 2007
·
3509 views

Speeding Up Stochastic Gradient Descent
Dec 29, 2007
·
12977 views

Large-Scale Euclidean MST and Hierarchical Clustering
Dec 29, 2007
·
4579 views

Model Compression: Bagging your Cake and Eating it too (part 2)
Dec 29, 2007
·
3380 views
Interview

Interview with Yann LeCun
Feb 1, 2008
·
9580 views