Léon Bottou
http://leon.bottou.org/
2010-02-23T10:37:16-05:00Léon Bottou
http://leon.bottou.org/
http://leon.bottou.org/lib/images/favicon.icotext/html2010-02-22T10:31:37-05:00Léon Bottouprojects:sgd
http://leon.bottou.org/projects/sgd?rev=1266852697&do=diff
Stochastic Gradient Descent (SGD) has been historically associated
with back-propagation algorithms in multilayer neural networks.
These nonlinear nonconvex problems can be very difficult.
Therefore it is useful to see how Stochastic Gradient Descent
performs on simple linear and convex problems such
as linear Support Vector Machines (SVMs)
or Conditional Random Fields (CRFs).text/html2010-02-16T10:26:26-05:00Léon Bottounews:senna_v2
http://leon.bottou.org/news/senna_v2?rev=1266333986&do=diff
Use BLAS, not PERL!
It is the nineties again.
Ronan Collobert from NEC Labs
just released a noncommercial version of his neural network system for semantic extraction.
Given an input sentence in plain english,
Senna outputs a host
of Natural Language Processing (NLP) tags:
part-of-speech (POS) tags, chunking (CHK),
name entity recognition (NER),
and semantic role labeling (SRL).
Senna does this with state-of-the-art accuracies,
roughly two hundred times faster than competing approaches.text/html2010-01-26T10:51:13-05:00Léon Bottoupapers:bordes-bottou-gallinari-2009
http://leon.bottou.org/papers/bordes-bottou-gallinari-2009?rev=1264521073&do=diff
SGD-QN: Careful Quasi-Newton Stochastic Gradient Descent
Abstract:
The SGDQN algorithm is a stochastic gradient descent
algorithm that makes careful use of second-order information
and splits the parameter update into independently scheduled
components. Thanks to this design, SGDQN iterates nearly as
fast as a first-order stochastic gradient
descent but requires less iterations
to achieve the same accuracy.
This algorithm won the “Wild Track” of the first
PASCAL Large Scale Learning Cha…text/html2010-01-26T10:49:11-05:00Léon Bottoupapers
http://leon.bottou.org/papers?rev=1264520951&do=diff
Follow each publication link to access papers and supplemental data.
Most papers are available in DjVu, PDF, and PS.GZ.
Download a DjVu viewer.
2009
Advances in Neural Information Processing Systems 21<http://books.nips.cc>
more...
Proceedings of the 26th International Conference on Machine Learning (ICML 2009)text/html2010-01-25T15:51:21-05:00Léon Bottoucos424
http://leon.bottou.org/cos424?rev=1264452681&do=diff
Are you looking for the cos424 pages ?text/html2010-01-14T10:20:49-05:00Léon Bottouwiki:playground
http://leon.bottou.org/wiki/playground?rev=1263482449&do=diff
section t
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
section one
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a
a