Differences

This shows you the differences between two versions of the page.

--- talks [2007/04/02 11:21]
leonb
+++ talks [2022/04/19 11:00] (current)
leonb
@@ Line 1: / Line 1: @@
 ====== Talks ======
-This page links the slides of my most significant lectures.
+This page contains pointers to my most significant lectures.
-All the slides are encoded in [[:research:djvu|DjVu]] format.
-You might have to install the [[http://www.djvuzone.org/download|DjVu browser plugin]]
-to see them.
-===== The BackPropagation CookBook =====
+All the slides are available under both the PDF and DjVu formats.
-{{talk-tricks.png?130 }}
+  * [[talks/cookbook|The BackPropagation CookBook (NIPS Workshop 1996)]]
-This lecture is co-authored with [[http://yann.lecun.com|Yann Le Cun]].
+  * [[talks/gtn|Graph Transformer Networks (ICML Workshop 2001)]]
-It took place at the 1996 NIPS Workshop
+  * [[talks/djvu|DjVu: Scanned Documents on the Web (2000)]]
-[[http://www.willamette.edu/~gorr/nipsws.htm|Tricks of the Trade]]
+  * [[talks/mlss|Online Learning and Stochastic Approximations (MLSS Tuebingen 2003)]]
-organized by [[http://ida.first.fraunhofer.de/~klaus|Klaus-Robert Müller]] and [[http://www.willamette.edu/~gorr|Genevieve Orr]].
+  * [[talks/largescale|The Tradeoffs of Large Scale Learning (NIPS Tutorial 2007)]]
+  * [[talks/onepass|Stochastic Algorithms for One Pass Learning (NIPS Workshop 2011)]]
+  * [[talks/counterfactuals|Counterfactual Reasoning and Learning Systems (2012)]]
+  * [[talks/mlss13|Multilayer Networks [no longer old fashioned!] (2013)]]
+  * [[talks/perceptrons|Perceptrons Revisited (AAAI Spring Symposium 2015)]]
+  * [[talks/2challenges|Two big Challenges in Machine Learning (ICML 2015)]]
+  * [[talks/invariances|Learning Representation with Causal Invariance (ICLR 2019)]]
-  * See [[http://leon.bottou.org/slides/tricks/index.djvu|the slides]].
-  * See the corresponding [[:papers:lecun-98x|book chapter]].
-===== Graph Transformer Networks =====
-{{talk-gtn.png?110 }}
-This lecture describe Graph Transformer Networks
-It took place at the 2001 ICML workshop [[http://web.engr.oregonstate.edu/~tgd/ml2001-workshop|Machine Learning for Spatial and Temporal Data]] organized by [[http://web.engr.oregonstate.edu/~tgd|Tom Dietterich]].
-[[:papers:bottou-97|Graph Transformer Networks]] are one of the most powerful and successful method for learning sequential data. About 10% to 20% of the checks written in the U.S. since 1996 have been processed by a Graph Transformer Network. Graph Transformer Networks are related to [[http://www.inference.phy.cam.ac.uk/hmw26/crf|Conditional Random Fields]] but have variable geometry and non-linear energies.
-   * See [[http://leon.bottou.org/slides/gtn/index.djvu|the slides (djvu 234KB)]] [[http://leon.bottou.org/slides/gtn/gtn.pdf|(pdf 2.4MB)]].
-   * See [[:papers:bottou-97|a short paper]] or [[:papers:lecun-98h|a long paper]].
-===== DjVu: Scanned Documents on the Web =====
-{{talk-djvu.png?100 }}
-[[http://www.djvuzone.org|DjVu]] is a document compression system that allows the distribution of scanned documents on the web.  DjVu files are //very compact//. A typical 300dpi bitonal page takes 10-15KB. A typical 300dpi color page takes 40-60KB.  The presentation discusses the main technical innovations that made DjVu possible.
-  * See [[http://leon.bottou.org/slides/djvu/index.djvu|the slides]].
-  * See the [[:research:djvu|DjVu research page]].
-  * See the [[:projects:djvulibre|DjVu software page]].
-===== Online Learning and Stochastic Approximations =====
-{{talk-mlss.png?200 }}
-This four part lecture was given at the
-[[http://www.mlss.cc|Machine Learning Summer School]]
-held in [[http://www.kyb.tuebingen.mpg.de/mlss04/mlss03|Tübingen in 2003]]
-organized by [[http://ml.typepad.com/about.html|Olivier Bousquet]],
-[[http://www.kyb.mpg.de/~bs|Bernhard Schölkopf]] and
-[[http://www.ipsi.fraunhofer.de/mine/en/people/luxburg|Ulrike von Luxburg]].
-The lecture discusses Stochastic Approximations and in particular [[wp>Stochastic_gradient_descent|Stochastic Gradient Descent]] applied to online learning algorithms.
-  * See [[http://leon.bottou.org/slides/mlss/part1.djvu|part 1]]: Framework.
-  * See [[http://leon.bottou.org/slides/mlss/part2.djvu|part 2]]: Cookbook.
-  * See [[http://leon.bottou.org/slides/mlss/part3.djvu|part 3]]: Convergence and Martingales.
-  * See [[http://leon.bottou.org/slides/mlss/part4.djvu|part 4]]: Optimal online algorithms.
-  * See the corresponding [[:papers:bottou-mlss-2004|book chapter]].

User Tools

Site Tools

Differences

Page Tools