From nicolas.brodu at numerimoire.net Mon Mar 2 16:37:43 2009 From: nicolas.brodu at numerimoire.net (Nicolas Brodu) Date: Mon, 2 Mar 2009 17:37:43 +0100 Subject: [Causality-ML] Next talk announcement, video replay of last talk is available Message-ID: <200903021737.43261.nicolas.brodu@numerimoire.net> Dear Causality and Machine Learning group, The next presentation is by Jerry Jenkins. He will present the SIGNET dataset generated for the "Causality Challenge". When: Thursday 5 February 2009, Paris 17h, ET 11h, PT 8h, Tokyo 1h(Friday) URL: http://www.afia-france.org/tiki-index.php?page=GroupeDeLecture090305JJ This talk will be followed next week by a presentation by Mehreen Saeed who received the significant advance award on the SIGNET challenge. NEW FEATURE: You can listen to the audio from the Internet! Just open the presentation link at the indicated time and check the given audio link in the interface. You can also ask questions directly from your web browser. You may try the system in advance with the demo: http://www.encours.org/demo.html The video of the last talk by Nicolas Brodu is available online, despite some technical difficulties impairing the audio quality: http://www.encours.org/causality/decisionalStates/replay.html Abstract of this week's presentation: -------- The presentation will describe the SIGNET dataset generated for the "Causality Challenge". Briefly, cellular signaling pathways are most illusive types of networks to access experimentally due to the lack of methods for determining the state of a signaling network in an intact living cell. Boolean network models are currently being used for the modeling of signaling networks due to their compact formulation and ability to adequately represent network dynamics without the need for chemical kinetics. The problem posed in the SIGNET challenge is to determine the set of Boolean rules that describe the interactions of nodes within a plant signaling network, given a set of 300 Boolean pseudodynamic simulations of the true rules. Solutions to the SIGNET challenge were submitted by Mehreen Saeed of the Department of Computer Science at the National University of Computer and Emerging Sciences (Lahore Campus, Pakistan), and Cheng Zheng of the School of Mathematical Sciences at Peking University (Beijing, China). Prof. Saeed submitted a Bernoulli Mixture Model (BMM), and Prof. Zheng submitted a Minimum Explanatory Set and Maximum Likelihood (MESML). The presentation will discuss the results in light of the larget context of ab initio determination of signaling network topology and dynamics. -------- If you know of potentially interested speakers or if you wish to present a paper, please send us a message so we can add you in the planning. Best regards, Nicolas Brodu From nicolas.brodu at numerimoire.net Sat Mar 7 16:27:06 2009 From: nicolas.brodu at numerimoire.net (Nicolas Brodu) Date: Sat, 7 Mar 2009 17:27:06 +0100 Subject: [Causality-ML] Next talk announcement, video replay of last talk is available Message-ID: <200903071727.06621.nicolas.brodu@numerimoire.net> Dear Causality and Machine Learning group, The next presentation is by Mehreen Saeed. She will present Bernoulli mixture models for extracting Boolean rules from data. Mehreen won the significant advance award on the SIGNET dataset at the NIPS 2008 workshop. *** DATE ?and TIME *** Thursday 12 March Lahore 20h = Paris 16h = New York 11h = Los Angeles 8h = Tokyo 24h Please watch out for daylight savings changes Presentation link: http://www.afia-france.org/tiki-index.php?page=GroupeDeLecture090312MS This talk is the logical continuation of last week presentation by Jerry Jenkins on the SIGNET challenge. You can view the video here: http://www.encours.org/causality/SIGNET/replay.html You can listen to the next presentation on the Internet! Just open the presentation link at the indicated time and check the given audio link in the interface. You can also ask questions directly from your web browser. You may try the system in advance with the demo: http://www.encours.org/demo.html Abstract of this week's presentation: -------- This talk will focus on the method that was applied to solve the SIGNET task of the causality pot-luck challenge no. 2. The SIGNET challenge is to extract Boolean rules from a dataset that has been derived by simulating a biological signaling network with 21 time steps and 43 random Boolean variables. This presentation will illustrate a novel technique for converting a probabilistic model into a rule based system. The method is based on the use of Bernoulli mixture models for extracting Boolean rules from data. Bernoulli mixtures identify high data density areas on the corners of a hypercube. One corner represents a conjunction of literals in a Boolean clause and the set of all identified corners, of the hypercube, indicates disjuncts of clauses to form a rule. Further class labels can be used to select features or variables, in the individual conjuncts, that are relevant to the target variable. Results indicate that Bernoulli mixtures are quite effective at extracting Boolean rules and hence a Boolean network from raw data. -------- If you know of potentially interested speakers or if you wish to present a paper, please send us a message so we can add you in the planning. Best regards, Nicolas Brodu From isabelle at clopinet.com Wed Mar 11 17:34:27 2009 From: isabelle at clopinet.com (isabelle at clopinet.com) Date: Wed, 11 Mar 2009 17:34:27 +0000 Subject: [Causality-ML] KDD cup 2009 Message-ID: <20090311173428.943.qmail@clopinet.com> An HTML attachment was scrubbed... URL: From nicolas.brodu at numerimoire.net Thu Mar 12 00:23:36 2009 From: nicolas.brodu at numerimoire.net (Nicolas Brodu) Date: Thu, 12 Mar 2009 01:23:36 +0100 Subject: [Causality-ML] Reminder: Bernoulli mixture models for extracting Boolean rules from data Message-ID: <200903120123.36280.nicolas.brodu@numerimoire.net> Dear Causality and Machine Learning group, Today's presentation is by Mehreen Saeed. She will present Bernoulli mixture models for extracting Boolean rules from data. Mehreen won the significant advance award on the SIGNET dataset at the NIPS 2008 workshop. *** DATE ?and TIME *** Thursday 12 March (TODAY) Lahore 20h = Paris 16h = New York 11h = Los Angeles 8h = Tokyo 24h Please watch out for daylight savings changes Presentation link: http://www.afia-france.org/tiki-index.php?page=GroupeDeLecture090312MS This talk is the logical continuation of last week presentation by Jerry Jenkins on the SIGNET challenge. You can view the video here: http://www.encours.org/causality/SIGNET/replay.html Abstract of this week's presentation: -------- This talk will focus on the method that was applied to solve the SIGNET task of the causality pot-luck challenge no. 2. The SIGNET challenge is to extract Boolean rules from a dataset that has been derived by simulating a biological signaling network with 21 time steps and 43 random Boolean variables. This presentation will illustrate a novel technique for converting a probabilistic model into a rule based system. The method is based on the use of Bernoulli mixture models for extracting Boolean rules from data. Bernoulli mixtures identify high data density areas on the corners of a hypercube. One corner represents a conjunction of literals in a Boolean clause and the set of all identified corners, of the hypercube, indicates disjuncts of clauses to form a rule. Further class labels can be used to select features or variables, in the individual conjuncts, that are relevant to the target variable. Results indicate that Bernoulli mixtures are quite effective at extracting Boolean rules and hence a Boolean network from raw data. -------- If you know of potentially interested speakers or if you wish to present a paper, please send us a message so we can add you in the planning. Best regards, Nicolas Brodu From guyon at clopinet.com Wed Mar 18 09:10:47 2009 From: guyon at clopinet.com (Isabelle Guyon) Date: Wed, 18 Mar 2009 02:10:47 -0700 Subject: [Causality-ML] Presentation of the KDD cup Message-ID: <49C0BA97.5080306@clopinet.com> Subject: Mar 19 teleconference: Vincent Lemaire KDD cup 2009 Thursday March 19 Vincent Lemaire KDD cup 2009: Fast Scoring on a Large Database http://www.kddcup-orange.com/ Teleconference presentation Thursday 19 march, at 16h Paris time, ET 11h, PT 8h, Tokyo 0h (Friday) Slides: http://www.afia-france.org/tiki-index.php?page=GroupeDeLecture090313VL Phone number: +1 (218) 936-7999 Participant code: 665140# ------------------------------------------------------------------------ Abstract: Customer Relationship Management (CRM) is a key element of modern marketing strategies. The KDD Cup 2009 offers the opportunity to work on large marketing databases from the French Telecom company Orange to predict the propensity of customers to switch provider (churn), buy new products or services (appetency), or buy upgrades or add-ons proposed to them to make the sale more profitable (up-selling). The most practical way, in a CRM system, to build knowledge on customer is to produce scores. A score (the output of a model) is an evaluation for all instances of a target variable to explain (i.e. churn, appetency or up-selling). Tools which produce scores allow to project, on a given population, quantifiable information. The score is computed using input variables which describe instances. Scores are then used by the information system (IS), for example, to personalize the customer relationship. An industrial customer analysis platform able to build prediction models with a very large number of input variables has been developed by Orange Labs. This platform implements several processing methods for instances and variables selection, prediction and indexation based on an efficient model combined with variable selection regularization and model averaging method. The main characteristic of this platform is its ability to scale on very large datasets with hundreds of thousands of instances and thousands of variables. The rapid and robust detection of the variables that have most contributed to the output prediction can be a key factor in a marketing application. The challenge is to beat the in-house system developed by Orange Labs. It is an opportunity to prove that you can deal with a very large database, including heterogeneous noisy data (numerical and categorical variables), and unbalanced class distributions. Time efficiency is often a crucial point. Therefore part of the competition will be time-constrained to test the ability of the participants to deliver solutions quickly. Key dates: March 10, 2009 -- fast challenge opens April 10, 2009 -- deadline of the fast challenge May 11, 2009 -- challenge ends Schedule of further presentations: http://www.afia-france.org/tiki-index.php?page=Groupe+de+lecture -------------- next part -------------- An HTML attachment was scrubbed... URL: From haroon.lums at gmail.com Thu Mar 26 21:03:10 2009 From: haroon.lums at gmail.com (haroon javed) Date: Fri, 27 Mar 2009 02:03:10 +0500 Subject: [Causality-ML] Regarding lecture on BMM Message-ID: Hi, My name is haroon javed and i am working as a Research Assistant in Lahore University of Managment Sciences. We are using BMM technique in one of our modules of Research Project and i miss the talk on Bernoulli mixture models for extracting Boolean rules from data by Dr. Saeed. So kindly, will you please upload the video of the lecture, so that i can take benefit of it. Hoping a positive response Haroon Javed Research Assistant Lahore University of Managment Sciences, Lahore,Pakistan. -------------- next part -------------- An HTML attachment was scrubbed... URL: From guyon at clopinet.com Thu Mar 26 11:39:12 2009 From: guyon at clopinet.com (Isabelle Guyon) Date: Thu, 26 Mar 2009 04:39:12 -0700 Subject: [Causality-ML] Regarding lecture on BMM References: Message-ID: <49CB6960.6000704@clopinet.com> Dear Haroon, The video is available at: http://www.afia-france.org/tiki-index.php?page=GroupeDeLecture090305JJ Please let me know whether you have any problem. Thank you for your interest in these seminars. Best regards, Isabelle haroon javed wrote: > Hi, > My name is haroon javed and i am working as a Research Assistant in > Lahore University of Managment Sciences. We are using BMM technique in > one of our modules of Research Project and i miss the talk on > Bernoulli mixture models for extracting Boolean rules from data by Dr. > Saeed. > So kindly, will you please upload the video of the lecture, so that i > can take benefit of it. > > Hoping a positive response > > Haroon Javed > Research Assistant > Lahore University of Managment Sciences, > Lahore,Pakistan. > >------------------------------------------------------------------------ > >_______________________________________________ >Causality and Machine Learning >Mailing-list subscription: >http://mail.encours.org/listinfo/causality-ml >Material and presentation schedule: >http://www.afia-france.org/tiki-index.php?page=Groupe+de+lecture > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From nicolas.brodu at numerimoire.net Thu Mar 26 21:49:59 2009 From: nicolas.brodu at numerimoire.net (Nicolas Brodu) Date: Thu, 26 Mar 2009 22:49:59 +0100 Subject: [Causality-ML] Regarding lecture on BMM In-Reply-To: References: Message-ID: <200903262249.59202.nicolas.brodu@numerimoire.net> Dear Haroon Javed, Thanks for your interest in our working group. I indeed plan to upload a video of Dr. Saeed?s talk, but I have yet to create it from the sound and page action recordings of the conference. I will do this as soon as I can find the time, hopefully before the next session (on Thursday 2nd). Best regards, Nicolas Brodu haroon javed wrote: > Hi, > My name is haroon javed and i am working as a Research Assistant in Lahore > University of Managment Sciences. We are using BMM technique in one of our > modules of Research Project and i miss the talk on Bernoulli mixture models > for extracting Boolean rules from data by Dr. Saeed. > So kindly, will you please upload the video of the lecture, so that i can > take benefit of it. > > Hoping a positive response > > Haroon Javed > Research Assistant > Lahore University of Managment Sciences, > Lahore,Pakistan. From nicolas.brodu at numerimoire.net Tue Mar 31 19:39:44 2009 From: nicolas.brodu at numerimoire.net (Nicolas Brodu) Date: Tue, 31 Mar 2009 21:39:44 +0200 Subject: [Causality-ML] Next talk announcement: Detecting the arrow of time with independent noise models Message-ID: <200903312139.44771.nicolas.brodu@numerimoire.net> Dear Causality and Machine Learning group, The next presentation is THIS THURSDAY by Jonas Peters. He will present us how to detect the arrow of time with independent noise models When: Thursday 2nd April 2009, Paris 17h, ET 11h, PT 8h, Tokyo 0h(Friday) URL: http://www.afia-france.org/tiki-index.php?page=GroupeDeLecture090402JP Phone number: +1 (218) 936-7999 Participant code: 665140# See below for tips how to access the conference on the Internet using voice-over-IP. Abstract of this week's presentation: -------- We propose a method that detects the true direction of time series by fitting an autoregressive moving average model to the data. Whenever the noise is independent of the previous samples for one ordering of the observations, but dependent for the opposite ordering, we infer the former direction to be the true one. We prove that our method works in the population case as long as the noise of the process is not normally distributed (for the latter case, the direction is not identifiable). An implication of our result is that it confirms a fundamental causal reasoning - that noise is independent of signal when the true direction of the model is recovered - in the case of time series. We test our approach on two types of data: simulated data sets conforming to our modeling assumptions, and real world EEG time series. Our method makes a decision for a significant fraction of both data sets, and these decisions are mostly correct. -------- If you know of potentially interested speakers or if you wish to present a paper, please send us a message so we can add you in the planning. The planning for the next presentation is maintained at: http://www.afia-france.org/tiki-index.php?page=Groupe+de+lecture Tip for a cheap voice-over-IP connection to the conference: Open an account on nonoh.net (server in Germany) or voipcheap.com (server in US) or another SIP provider near your country. Pay 10 euros for 3 or 4 month unlimited access to nearly all land line phone numbers in the world, including the teleconference number. This means you will be able to spend as much time as you want for free on long-distance and international calls with the basic fee. Use a microphone + headset on your computer, and a program like Twinkle (Linux) or Ekiga (multi-OS) or X-Lite (windows). Set it up with your nonoh.net or voipcheap account (see the help page on these sites). Beware of filtering firewalls. Then call our teleconference number from your computer. Note: We are not affiliated to any of these groups. We provide this information in the hope it is useful. Best regards, Nicolas Brodu