From awm at cs.cmu.edu Thu Mar 2 18:22:37 2006 From: awm at cs.cmu.edu (awm at cs.cmu.edu) Date: Thu, 2 Mar 2006 18:22:37 -0500 (EST) Subject: [Research] [Fwd: Machine Learning positions and internships available at Siemens] Message-ID: <2580.216.73.130.85.1141341757.squirrel@webmail.cs.cmu.edu> FYI. NB Medical informatics + Machine Learning is a sharply growing industry. ---------------------------- Original Message ---------------------------- Subject: Machine Learning positions and internships available at Siemens From: "Niculescu, Stefan (MED US)" Date: Thu, March 2, 2006 5:37 pm To: awm at cs.cmu.edu -------------------------------------------------------------------------- Hi Andrew! I believe I mentioned that after I finished my PhD, I joined the Computer Aided Diagnosis Group at Siemens Medical, near Philadelphia. We currently have several machine learning internship positions available and I was wondering if you know of any students who might be interested. I am attaching the internship ad to this message. We are also looking to hire PhDs with expertise in Machine Learning or Statistics. If you happen to know of anyone interested, we would appreciate if you can put us in contact. Thank you in advance! --Stefan Internships in Machine Learning/Data Mining 2006 Emphasis in Text Processing CAD: Computer-Aided Diagnosis & Therapy Solutions Group Siemens Medical Solutions, Malvern, PA Internship positions available for motivated Ph.D. students in machine learning and data mining, with emphasis in text processing and information retrieval, in particular information extraction from unstructured text. As an intern, you will join CAD's team of scientists in solving exciting and challenging research problems in the medical and biomedical fields. Our research is motivated by decision-support and data processing problems arising in the medical domain and related health areas; experience or interest in these areas is a plus. Our team currently conducts research in Bayesian methods, probabilistic inference, statistical learning theory, optimization, statistics, natural language processing, data mining and works closely with a team of image processing scientists. You will be expected to spend at least 10-12 weeks; however there is much flexibility in the starting and finishing dates (non-summer and longer internships are also considered). In order to apply, please follow these steps: * Email your CV to the address below * Request one letter of recommendation (preferably from your advisor) to be emailed to us * Briefly (e.g., in half a page) tell us about what research and application areas you would prefer to work on and during what dates you wish to join Email the above to romer.rosales[AT]siemens.com, with the subject "CAD ML Internships". Siemens Medical Solutions is one of the largest global suppliers of healthcare equipment, renowned for innovative products, services and solutions including diagnostic imaging systems, therapy equipment, electromedicine, and IT solutions to optimize workflow and increase efficiency in the healthcare industry. The CAD group is committed to building a world-class R&D team in machine learning and data mining. We are located in Malvern, PA, less than 30 miles from Center City Philadelphia on the suburban Main Line area. ------------------------------------------------------------------------------- This message and any included attachments are from Siemens Medical Solutions USA, Inc. and are intended only for the addressee(s). The information contained herein may include trade secrets or privileged or otherwise confidential information. Unauthorized review, forwarding, printing, copying, distributing, or using such information is strictly prohibited and may be unlawful. If you received this message in error, or have reason to believe you are not authorized to receive it, please promptly delete this message and notify the sender by e-mail with a copy to Central.SecurityOffice at shs.siemens.com Thank you -------------- next part -------------- An HTML attachment was scrubbed... URL: From smsiddiq at andrew.cmu.edu Mon Mar 6 11:43:29 2006 From: smsiddiq at andrew.cmu.edu (Sajid Siddiqi) Date: Mon, 6 Mar 2006 11:43:29 -0500 Subject: [Research] Borrowed AI book? Message-ID: <00de01c6413d$18e52a00$6ac70280@sp.cs.cmu.edu> Hi all, I've misplaced my green Russell & Norvig AI book and I might have lent it to someone ... if you happen to have it please let me know. Thanks, Sajid From awd at cs.cmu.edu Tue Mar 7 09:07:51 2006 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Tue, 07 Mar 2006 09:07:51 -0500 Subject: [Research] No Lab meetings this week Message-ID: <1141740471.32734.2.camel@logo.auton.cs.cmu.edu> From awd at cs.cmu.edu Tue Mar 7 12:11:48 2006 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Tue, 07 Mar 2006 12:11:48 -0500 Subject: [Research] [Fwd: Prof. Galit Shuemli, Mar 10: Seminar at noon Room 2503 HBH] Message-ID: <1141751508.32734.37.camel@logo.auton.cs.cmu.edu> -------------- next part -------------- An embedded message was scrubbed... From: Ramayya Krishnan Subject: Prof. Galit Shuemli, Mar 10: Seminar at noon Room 2503 HBH Date: Fri, 03 Mar 2006 23:11:24 -0500 Size: 7659 URL: From awd at cs.cmu.edu Tue Mar 7 15:08:48 2006 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Tue, 07 Mar 2006 15:08:48 -0500 Subject: [Research] [Fwd: intern and full-time positions at Motorola Labs] Message-ID: <1141762127.32734.43.camel@logo.auton.cs.cmu.edu> -------------- next part -------------- An embedded message was scrubbed... From: "Taskiran Cuneyt-ACT052" Subject: intern and full-time positions at Motorola Labs Date: Tue, 7 Mar 2006 15:01:15 -0500 Size: 66529 URL: From awm at cs.cmu.edu Tue Mar 7 17:49:58 2006 From: awm at cs.cmu.edu (awm at cs.cmu.edu) Date: Tue, 7 Mar 2006 17:49:58 -0500 (EST) Subject: [Research] [Fwd: intern and full-time positions at Motorola Labs] Message-ID: <1568.216.73.130.85.1141771798.squirrel@webmail.cs.cmu.edu> ---------------------------- Original Message ---------------------------- Subject: intern and full-time positions at Motorola Labs From: "Taskiran Cuneyt-ACT052" Date: Tue, March 7, 2006 3:03 pm To: awm at cs.cmu.edu -------------------------------------------------------------------------- Dear Prof. Moore: We have intern positions open at the Motorola Multimedia Research Lab, located at Schaumburg, IL. I am especially interested in students who desire an internship working on media association, media mining, and pattern recognition. I would much appreciate if you pass this information to students who you think have the qualifications. I have attached a flyer giving more information. Thanks, ========================================================Cuneyt Taskiran, Ph.D. Motorola Inc., Applications Research Center 1295 E. Algonquin Road, 2nd Floor Schaumburg, IL 60196 Phone: 847-576-9412 Fax: 847-576-6030 E-mail: cuneyt.taskiran at motorola.com ======================================================= -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Motorola_Labs_Multimedia_Research_Positions_2006.doc Type: application/msword Size: 43520 bytes Desc: not available URL: From awd at cs.cmu.edu Mon Mar 13 11:28:03 2006 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Mon, 13 Mar 2006 11:28:03 -0500 Subject: [Research] no lab mtg during regular hours, but we will have a special meeting this week! Message-ID: <000401c646bb$2f0d0950$7df0ed80@scs.ad.cs.cmu.edu> It is going to be on Friday, March 17th at 2pm in NSH 3305 and it will be our own Ting Liu's thesis defense! She's done tons of cool research into nonparametric classification and clustering (as evident from the abstract of her talk below). Let's crowd the room and give Ting our support. Artur Abstract: Nonparametric methods have become increasingly popular in the statistics communities and probabilistic AI communities. One simple and well-known nonparametric method is called k-nearest-neighbor or k-NN. Despite its simplicity, k-NN and its variants have been successful in a large number of machine learning problems. However, k-NN and many related nonparametric methods remain hampered by their computational complexity. Many spatial methods, such as metric-trees, have been proposed to alleviate the computational cost, but the effectiveness of these methods decreases as the number of dimensions of feature vectors increases. From another direction, researchers are trying to develop ways to find approximate answers and some approximate methods show pretty good performance in a number of applications. However, when facing hundreds or thousands dimensionalities, many algorithms do not work very well in reality. I propose four new spatial methods for fast k-NN and its variants, namely KNS2, KNS3, IOC and spill-tree. The first three algorithms are designed to speed up k-NN classification problems, and they all share the same insight that finding the majority class among the k-NN of q need not require us to explicitly find those k-NNs. Spill-tree is designed for approximate-nearest-neighbor search. By adapting metric-trees to a more flexible data structure, spill-tree is able to automatically adapt to the distribution of data and it scales well even for huge high-dimensional data sets. The new methods have been applied to many real-world applications, including video segmentation, drug discovery and image clustering for 1.5 billion images. Significant efficiency improvement has been observed in all these applications. From awd at cs.cmu.edu Mon Mar 13 11:28:38 2006 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Mon, 13 Mar 2006 11:28:38 -0500 Subject: [Research] no lab mtg during regular hours, but we will have a special meeting this week! Message-ID: <000501c646bb$2f1c4b90$7df0ed80@scs.ad.cs.cmu.edu> It is going to be on Friday, March 17th at 2pm in NSH 3305 and it will be our own Ting Liu's thesis defense! She's done tons of cool research into nonparametric classification and clustering (as evident from the abstract of her talk below). Let's crowd the room and give Ting our support. Artur Abstract: Nonparametric methods have become increasingly popular in the statistics communities and probabilistic AI communities. One simple and well-known nonparametric method is called k-nearest-neighbor or k-NN. Despite its simplicity, k-NN and its variants have been successful in a large number of machine learning problems. However, k-NN and many related nonparametric methods remain hampered by their computational complexity. Many spatial methods, such as metric-trees, have been proposed to alleviate the computational cost, but the effectiveness of these methods decreases as the number of dimensions of feature vectors increases. From another direction, researchers are trying to develop ways to find approximate answers and some approximate methods show pretty good performance in a number of applications. However, when facing hundreds or thousands dimensionalities, many algorithms do not work very well in reality. I propose four new spatial methods for fast k-NN and its variants, namely KNS2, KNS3, IOC and spill-tree. The first three algorithms are designed to speed up k-NN classification problems, and they all share the same insight that finding the majority class among the k-NN of q need not require us to explicitly find those k-NNs. Spill-tree is designed for approximate-nearest-neighbor search. By adapting metric-trees to a more flexible data structure, spill-tree is able to automatically adapt to the distribution of data and it scales well even for huge high-dimensional data sets. The new methods have been applied to many real-world applications, including video segmentation, drug discovery and image clustering for 1.5 billion images. Significant efficiency improvement has been observed in all these applications. From kristens at cs.cmu.edu Fri Mar 17 07:23:27 2006 From: kristens at cs.cmu.edu (Kristen Schrauder) Date: Fri, 17 Mar 2006 07:23:27 -0500 Subject: [Research] Good Morning! Message-ID: <000001c649bd$9b9ca9e0$fadc0280@adm.ri.cmu.edu> Happy St. Patrick's Day! Help yourself to a doughnut in the 3rd floor kitchen (NSH 3129). Kristen Schrauder, Administrative Coordinator Carnegie Mellon University - Robotics Institute Newell-Simon Hall, Room 3128 5000 Forbes Avenue Pittsburgh, PA 15213 Phone: 412.268.7551 Fax: 412.268.7350 -------------- next part -------------- An HTML attachment was scrubbed... URL: From awm at cs.cmu.edu Fri Mar 17 18:08:57 2006 From: awm at cs.cmu.edu (Andrew W Moore) Date: Fri, 17 Mar 2006 18:08:57 -0500 Subject: [Research] FW: data mining job opening Message-ID: <200603172309.k2HN93p7025182@chokecherry.srv.cs.cmu.edu> _____ From: Niklas Karlsson [mailto:nkarlsson at advertising.com] Sent: Thursday, March 16, 2006 1:34 PM To: awm at cs.cmu.edu Subject: data mining job opening Dear Andrew, We don't know each other, but I happened to find your excellent tutorial slides on Data Mining and since our R&D team is looking for a Data Mining Expert I figured I'd ask if you know of some good and available candidates. My name is Niklas Karlsson I and lead the R&D in control systems at Advertising.com. Advertising.com is the largest internet advertising network in the world, serving over one billion ads per day, reaching over 80% of the internet population each month (for comparison, Yahoo reaches 70% and Google 48%). We have worked with hundreds of clients including 14 of the largest 20 advertisers in the US, and all of the top ten advertisers in the UK. We maintain offices in Baltimore, San Francisco, New York, Chicago, Los Angeles, Mountain View, London, Paris, Oslo, Stockholm, Copenhagen, Hamburg, and Madrid. Advertising.com is a performance-based network. Generally, the advertisers pay only when a consumer not only clicks on an ad, but actually purchases the product being advertised. Conversely, we typically pay websites every time we show an ad on their site. That is, we bear all the risk. To turn this into a viable business, our Research and Development team in Mountain View, CA, has developed an advanced system based on optimization that determines which ad to show to which person. The research involves modeling of complex, nonlinear, stochastic systems; as well as, design of efficient control schemes to meet several conflicting goals. The R&D department is located in Mountain View, CA (Silicon Valley) where I lead the research on control. Advertising.com is dealing with online advertisement and is a profitable and all-around financially sound company. I write to you is to see if you know of some strong candidates for our team. We are expanding and are looking for strong additions to the R&D team here in Mountain View, California (Silicon Valley). What we currently are looking for is a Data Mining Expert. It's a research position, so we hope to find someone with a Ph.D. in statistics, computer science, or similar, with a knowledge in statistics and for example, tree-based methods, generalized models, learning algorithms, model validation, and the like. If you happen to know of some strong candidate it would be great if you can forward this information to him or her. I have attached a more formal job description. More information about the company can be found at http://www.advertising.com, but if there are any questions about the job opening or Advertising.com, I'll be more than happy to answer those. Anyone interested can contact me at nkarlsson at advertising.com. Take care! Best regards, Niklas Karlsson The information transmitted in this email is intended only for the person(s) or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this email in error, please contact the sender and permanently delete the email from any computer. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: data mining expert.doc Type: application/msword Size: 41984 bytes Desc: not available URL: From jkomarek at cs.cmu.edu Tue Mar 21 11:25:58 2006 From: jkomarek at cs.cmu.edu (Jeanie Komarek) Date: Tue, 21 Mar 2006 11:25:58 -0500 Subject: [Research] Get together Wednesday night at Gullifty's Message-ID: <44202916.7010003@cs.cmu.edu> Paul and I are in town this week and would like to get together with whoever is interested at Gullifty's tomorrow night for dinner. Proposed Time: 7pm. Bringing significant others and kids is highly recommended. :) Let me know if you think you can make it so I can call ahead with the size of our group. Let me know if you would need a ride and we'll work out the details. Thanks! -Jeanie P.S. If you don't know what/where Gullifty's is, here's some info: http://www.gulliftysrestaurant.com/location.htm -- Jeanie Komarek Project Manager, Auton Lab http://www.autonlab.org Carnegie Mellon University From awd at cs.cmu.edu Tue Mar 21 12:41:58 2006 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Tue, 21 Mar 2006 12:41:58 -0500 Subject: [Research] Lab Meeting this Thursday Message-ID: <1142962918.28974.38.camel@logo.auton.cs.cmu.edu> A triumphant return!!! Jeanie Komarek (Auton Lab West) will present the ASL (A Super-Lovely thing everyone would like to use). When: Thu Mar 23 4:30pm--5:50pm Where: NSH 1507 Food: Yes Webcast availability: Please contact Mike. From jkomarek at cs.cmu.edu Wed Mar 22 15:59:11 2006 From: jkomarek at cs.cmu.edu (Jeanie Komarek) Date: Wed, 22 Mar 2006 15:59:11 -0500 Subject: [Research] Get together Wednesday night at Gullifty's In-Reply-To: <44202916.7010003@cs.cmu.edu> References: <44202916.7010003@cs.cmu.edu> Message-ID: <4421BA9F.5000100@cs.cmu.edu> Hey - just checking if anyone else thinks they might be able to come tonight so I can call ahead and let them know we have a group coming. Right now we are at least 7, possibly 10. -Jeanie Jeanie Komarek wrote: > Paul and I are in town this week and would like to get together with > whoever is interested at Gullifty's tomorrow night for dinner. > > Proposed Time: 7pm. > > Bringing significant others and kids is highly recommended. :) > > > Let me know if you think you can make it so I can call ahead with the > size of our group. Let me know if you would need a ride and we'll work > out the details. > > Thanks! > -Jeanie > > P.S. If you don't know what/where Gullifty's is, here's some info: > http://www.gulliftysrestaurant.com/location.htm > -- Jeanie Komarek Project Manager, Auton Lab http://www.autonlab.org Carnegie Mellon University From jkomarek at cs.cmu.edu Fri Mar 24 10:44:29 2006 From: jkomarek at cs.cmu.edu (Jeanie Komarek) Date: Fri, 24 Mar 2006 10:44:29 -0500 Subject: [Research] Goodbye party for Joey today Message-ID: <442413DD.2050209@cs.cmu.edu> Hi All - Today is Joey's last day with the Auton Lab. He will be starting work with another group at the University on Monday. Let's get together at 2:00 today in NSH 1507 to wish him good luck and thank him for all the work he's done for the lab. Hope to see you there! - Jeanie -- Jeanie Komarek Project Manager, Auton Lab http://www.autonlab.org Carnegie Mellon University From mjbaysek at cs.cmu.edu Fri Mar 24 15:45:52 2006 From: mjbaysek at cs.cmu.edu (Michael J. Baysek) Date: Fri, 24 Mar 2006 15:45:52 -0500 Subject: [Research] If you missed the lab meeting Thursday Message-ID: <44245A80.905@cs.cmu.edu> Hi Everyone, In case you missed the lab meeting on Thursday, we have posted slides and audio on the Intranet. The AVI file can be retrieved from the Lab Meetings section of the site. This weeks meeting, given by Jeanie Komarek, demonstrated ASL and the many cool things it can do with datasets and algorithms. You definitely will want to check this out! If you are running the Auton Fedora Core 4 Linux installation, your machine is already enabled to play this file, using the Xine media player. If you are running Windows or Mac, you will need the DivX codec installed, if you do not have it already. It can be obtained for free at www.divx.com. Intranet Home http://www.autonlab.org/auton_intranet/ Lab meetings page http://www.autonlab.org/auton_intranet/meetings.html DivX Website http://www.divx.com Enjoy! -- Michael J. Baysek Systems Analyst Carnegie Mellon University, Auton Lab http://www.autonlab.org mjbaysek at cs.cmu.edu From awm at google.com Sun Mar 26 08:03:29 2006 From: awm at google.com (Andrew Moore) Date: Sun, 26 Mar 2006 05:03:29 -0800 Subject: [Research] Andrew's email Message-ID: Sometimes it's not easy for me to check my cs email daily so you guys are welcome to send stuff directly to awm at google.com (and it's fine to do so for minor things as well as major). But don't extend this invitation beyond the lab! I go through my cs email every couple days usually but sometimes lag behind! See you, Andrew -------------------------- Sent from my BlackBerry Wireless Handheld From jkomarek at cs.cmu.edu Mon Mar 27 23:49:14 2006 From: jkomarek at cs.cmu.edu (Jeanie Komarek) Date: Mon, 27 Mar 2006 20:49:14 -0800 Subject: [Research] Goodbye party for Ashwin and Patrick Message-ID: <4428C04A.1050200@cs.cmu.edu> Ashwin and Patrick will both be leaving the lab at the end of the month. We'd like to thank them for all they've done for the lab and wish them luck for the future. Please join us for a goodbye party today (Tuesday) at 2:00 in NSH 3305. Thanks, Jeanie -- Jeanie Komarek Project Manager, Auton Lab http://www.autonlab.org Carnegie Mellon University From awd at cs.cmu.edu Wed Mar 29 16:03:02 2006 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Wed, 29 Mar 2006 16:03:02 -0500 Subject: [Research] upcoming lab meetings Message-ID: <1143666182.25008.829.camel@logo.auton.cs.cmu.edu> Tomorrow: "Three Months After: Review of the State of the Lab" (standard time and place: 4:30pm, NSH 1507) Next Thursday: David Tolliver will talk about Spectral Clustering. See you all there, Artur From anya at cs.cmu.edu Fri Mar 31 13:52:30 2006 From: anya at cs.cmu.edu (Anna Goldenberg) Date: Fri, 31 Mar 2006 13:52:30 -0500 Subject: [Research] registration at NESCAI Message-ID: <630880D9-AB53-4C20-A071-2FCB35D10EAB@cs.cmu.edu> For students: This is a quick reminder that even if you didn't submit a paper, you could still go to NESCAI. It's free and we're trying to figure out how to provide transportation to Cornell for all that want to come. If you are planning to go it would be great if you could register (it's a different registration process from the paper submission). The registration deadline is April 6th, but the earlier you register the better, since we need to start figuring out accommodations asap. The link is here: http://www.cs.cornell.edu/Conferences/nescai/ Have a good weekend! Anna From smsiddiq at andrew.cmu.edu Fri Mar 31 17:00:37 2006 From: smsiddiq at andrew.cmu.edu (Sajid Siddiqi) Date: Fri, 31 Mar 2006 17:00:37 -0500 Subject: [Research] FW: Summer internship (reply ASAP) Message-ID: <005201c6550e$8b0d3700$6ac70280@sp.cs.cmu.edu> Xerox Labs is looking for an intern to fill a last-minute vacancy. Please send your resume ASAP if interested since they want to fill it by early next week. Sajid ----------------------------------------- Project: Diagonstics and prognostics for complex systems. Xerox is faced with a serious and continuing challenge to increase the efficiency of its service and increase customer satisfaction. Understanding and predicting fault patterns in printers in the field is essential to this effort. This requires modeling and data mining of a plethora of data from a variety of sources, few of which have been exploited. In this project, the summer intern would spearhead an investigation into novel approaches to modeling causally interconnected and dependent time series data from a complex system. Distributed printing systems such as iGen3 are hard to model and according to engineers get into "chaotic regions" that are hard to analyze. The approach of using complex systems to analyze time series behavior of these systems is expected to produce new insights into failures. Although the immediate interest would be to exploit currently collected data, we envision the benefits of this work to influence document workflow modeling in the enterprise. Requirements: Ph.D. student in computer science, systems engineering, statistics or mathematics. Knowledge and experience in time series analysis, data mining and databases. John C. Handley, Ph.D. Xerox Innovation Group 800 Phillips Road, MS 128-27E Webster, NY 14580 585 265 8900 JHandley at xeroxlabs.com -------------- next part -------------- An HTML attachment was scrubbed... URL: