From vjeansel at andrew.cmu.edu Wed Jul 1 08:24:22 2020 From: vjeansel at andrew.cmu.edu (Vincent Jeanselme) Date: Wed, 1 Jul 2020 08:24:22 -0400 Subject: Lov 9 - Scratch full Message-ID: <53f53778-83af-d810-8f3f-edaeae2c515f@andrew.cmu.edu> Hello all, Lov9 scratch is full, that would be great if you can do some cleaning, Thank you, Vincent -- Vincent Jeanselme ----------------- Analyst Researcher Auton Lab - Robotics Institute Carnegie Mellon University From awd at cs.cmu.edu Wed Jul 1 10:35:12 2020 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Wed, 1 Jul 2020 10:35:12 -0400 Subject: Auton Lab AI-based PMx showcased in a DoD blog Message-ID: Dear Autonians, Check this out: https://www.linkedin.com/posts/dod-joint-artificial-intelligence-center_mission-ready-how-the-joint-logistics-mi-activity-6684063509195710464-fiYp Congrats to everyone involved for making the predictive maintenance project a success! Cheers Artur -------------- next part -------------- An HTML attachment was scrubbed... URL: From ngisolfi at cs.cmu.edu Thu Jul 2 09:28:51 2020 From: ngisolfi at cs.cmu.edu (Nick Gisolfi) Date: Thu, 2 Jul 2020 09:28:51 -0400 Subject: [Lunch] Today @noon over Zoom Message-ID: https://cmu.zoom.us/j/492870487 We hope to see you there! - Nick -------------- next part -------------- An HTML attachment was scrubbed... URL: From vjeansel at andrew.cmu.edu Mon Jul 6 10:10:52 2020 From: vjeansel at andrew.cmu.edu (Vincent Jeanselme) Date: Mon, 6 Jul 2020 10:10:52 -0400 Subject: Lov 9 - Scratch full In-Reply-To: <53f53778-83af-d810-8f3f-edaeae2c515f@andrew.cmu.edu> References: <53f53778-83af-d810-8f3f-edaeae2c515f@andrew.cmu.edu> Message-ID: <0ed98270-a22c-dcf9-4a56-5610bdede629@andrew.cmu.edu> Hello, Please clean your home on lov9. We are reaching 100% use again Vincent Le 01/07/2020 ? 08:24, Vincent Jeanselme a ?crit?: > Hello all, > > Lov9 scratch is full, that would be great if you can do some cleaning, > > Thank you, > > Vincent > -- Vincent Jeanselme ----------------- Analyst Researcher Auton Lab - Robotics Institute Carnegie Mellon University From predragp at andrew.cmu.edu Mon Jul 6 14:31:52 2020 From: predragp at andrew.cmu.edu (Predrag Punosevac) Date: Mon, 06 Jul 2020 14:31:52 -0400 Subject: SSH key Question In-Reply-To: <27AD6086-CE35-4292-8080-D835FC0FC5E4@cmu.edu> References: <27AD6086-CE35-4292-8080-D835FC0FC5E4@cmu.edu> Message-ID: <20200706183152.HUohH%predragp@andrew.cmu.edu> Anthony Wertz wrote: > Predrag, > > I think lop1 might be down. I can???t reach it from my (loom) or other > (lop2, lov1, etc???) machines. > Hi Anthony, Yes, this is legit report. lop1 is cold turkey. Sorry, I should have sent an email earlier but I was busy with other stuff. I my crystal ball is correct AC adapter is fried. We had the problem with this little old machine in the past. I do have an off brand AC adapter for it but it is probably not worth the trouble. I was planning to retire lop1 soonish anyway. There are three shell-gateways available right now bash.autonlab.org (was stable for me for over a month) lop2.autonlab.org lion.auton.cs.cmu.edu hash-keys are posted on our Intrenet. I will probably add another virtual shell gateways soonish. Best, Predrag > > > - Anthony > > > On 6Jul2020, at 13:17, Willa Potosnak wrote: > > > > Hello Mr. Wertz, > > > > I'm having an issue using the ssh keys. when I try to log in by typing 'ssh lov7' for example, it responds with the error: > > 'ssh: connect to host lop1.autonlab.org port 22: Connection timed out > > ssh_exchange_identification: Connection closed by remote host' > > > > I've tried restarting my computer and wifi (which has worked once in the past for this error), but it keeps giving me the same error. I'm not sure if this is a firewall issue on the lab's end or an issue with the CPUs. > > > > Do you have any suggestions on how to fix this or should I consult Predrag? > > > > Thanks, > > Willa > From predragp at andrew.cmu.edu Mon Jul 6 14:34:59 2020 From: predragp at andrew.cmu.edu (Predrag Punosevac) Date: Mon, 06 Jul 2020 14:34:59 -0400 Subject: Can't login on lov9 In-Reply-To: <9D42FEC7-696B-45D6-A654-E04FCD32A71F@andrew.cmu.edu> References: <9D42FEC7-696B-45D6-A654-E04FCD32A71F@andrew.cmu.edu> Message-ID: <20200706183459.dGweh%predragp@andrew.cmu.edu> Arundhati Banerjee wrote: > Hi Predrag, > > Hope you are well. I want to report that I am unable to login on lov9 > since today morning. I am however able to login on all other lov > servers, so I am not sure what the error is. Fixed! predragp at lake$ ssh predragp at lov9 Host key fingerprint is SHA256:8xa6GjzQPoa/EalOpf3iI6TqIWsj5WoEj28JayBIuTw +---[ECDSA 256]---+ | | | | | . | |.o . . | |=o. . = S . | |*Eo .X . + . | |=B.+= X . o | |+*Bo.oo* o | |X=. .o==o | +----[SHA256]-----+ predragp at lov9's password: Last failed login: Mon Jul 6 14:13:58 EDT 2020 from 10.8.0.14 on ssh:notty There were 3 failed login attempts since the last successful login. Last login: Fri May 29 23:57:44 2020 from 10.8.0.14 predragp at lov9$ pwd /zfsauton2/home/predragp Predrag > > I would be obliged if you could kindly look into it. > > Thank you, > Best regards, > Arundhati From predragp at andrew.cmu.edu Wed Jul 8 15:13:06 2020 From: predragp at andrew.cmu.edu (Predrag Punosevac) Date: Wed, 08 Jul 2020 15:13:06 -0400 Subject: Unable to login into GPU21 In-Reply-To: References: Message-ID: <20200708191306.PIgxF%predragp@andrew.cmu.edu> Tanmay Agarwal wrote: > Hi Predrag, > > Good morning. Hope you are doing well. > > I noticed that I am unable to login into GPU 21 due to ssh failed > authentication. Can you please help us fix the issue at your earliest > convenience? Machine was in the vegetative state due to the abuse. This GPU node and GPU20 are not in our server rack. They are not connected to our IPMI server. Today I was lucky to find somebody in the Wean 3611 who could cold reboot this for us. Next time this operation could take few days. Cheers, Predrag > > > Thanking you, > > Warm Regards, > > Tanmay Agarwal | MSR Graduate Student > Robotics Institute @ CMU > mailto: tanmaya at andrew.cmu.edu From chiragn at cs.cmu.edu Thu Jul 9 08:04:23 2020 From: chiragn at cs.cmu.edu (Chirag Nagpal) Date: Thu, 9 Jul 2020 08:04:23 -0400 Subject: Fwd: Today, 7/9: LTI Summer Seminar Series Presents: Chirag Nagpal 9.30 AM In-Reply-To: References: Message-ID: Hello Perhaps this is a bit late and a lot of you would be already familiar with this work, but I would be presenting my research *TODAY at 9.30 AM* on Counterfactual Estimation and Subgroup Discovery for Causal Inference for the benefit of the new incoming students at LTI. I will also be talking a bit about Survival Analysis if time permits. Do join if it is of interest.... The zoom link is https://cmu.zoom.us/j/96306773691 *Note: TODAY at 9.30 AM* Thanks Chirag ---------- Forwarded message --------- From: Kate Schaich Date: Wed, Jul 8, 2020 at 9:03 AM Subject: Tomorrow, 7/9: LTI Summer Seminar Series Presents: Chirag Nagpal and Shikhar Vashishth To: , LTI Faculty Core < lti-faculty-core at cs.cmu.edu>, , < fall20-msaii at lists.andrew.cmu.edu>, , < miis-2020 at mailman.srv.cs.cmu.edu> Greetings all, The LTI is proud to announce tomorrow's Summer Seminar presenters: *Chirag Nagpal, "Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines"* *Abstract: *The dearth of prescribing guidelines for physicians is one key driver of the current opioid epidemic in the United States. In this work, we analyze medical and pharmaceutical claims data to draw insights on characteristics of patients who are more prone to adverse outcomes after an initial synthetic opioid prescription. Toward this end, we propose a generative model that allows discovery from observational data of subgroups that demonstrate an enhanced or diminished causal effect due to treatment. Our approach models these sub-populations as a mixture distribution, using sparsity to enhance interpretability, while jointly learning nonlinear predictors of the potential outcomes to better adjust for confounding. The approach leads to human-interpretable insights on discovered subgroups, improving the practical utility for decision support. Paper Link: https://arxiv.org/abs/1905.03297 *Bio: *Chirag is a 2nd Year PhD student (+MLT) student at LTI researching Machine Learning in Healthcare. His interests include Graphical Models and their applications in Survival Analysis, Causal Inference, and Uncertainty Estimation. During his PhD, he has been a Science for Social Good Fellow at IBM Research and a Summer Associate in JPMorgan AI Research. This summer he is remotely interning at Google Brain and Google Health. Personal Website: www.cs.cmu.edu/~chiragn *Shikhar Vashishth, "Improving Medical Entity Linking with Semantic Type Prediction"* *Abstract: *Medical entity linking is the task of identifying and standardizing medical concepts referred to in an unstructured text. Most of the existing methods adopt a three-step approach of (1) detecting mentions, (2) generating a list of candidate concepts, and finally (3) picking the best concept among them. In this paper, we probe into alleviating the problem of overgeneration of candidate concepts in the candidate generation module, the most under-studied component of medical entity linking. For this, we present MedType, a fully modular system that prunes out irrelevant candidate concepts based on the predicted semantic type of an entity mention. We incorporate MedType into five off-the-shelf toolkits for medical entity linking and demonstrate that it consistently improves entity linking performance across several benchmark datasets. To address the dearth of annotated training data for medical entity linking, we present WikiMed and PubMedDS, two large-scale medical entity linking datasets, and demonstrate that pre-training MedType on these datasets further improves entity linking performance. We make our source code and datasets publicly available for medical entity linking research. *Bio: *Shikhar Vashishth is a Postdoctoral Researcher at Language Technologies Institute, Carnegie Mellon University. Currently, working in the field of biomedical natural language processing under Prof. Carolyn Rose. Previously, he completed his Ph.D. from the Indian Insitute of Science under the guidance of Partha Pratim Talukdar, Chiranjib Bhattacharyya, and Manaal Faruqui. His thesis topic was on Neural Graph Embedding Methods for Natural Language Processing. Shikhar has been a recipient of the prestigious Google Ph.D. Fellowship and has interned at Google Research and Microsoft. He completed his graduation from BITS Pilani, Pilani in 2016. Webpage: http://shikhar-vashishth.github.io/ Presentations will begin promptly at 9am Eastern Time. Slides for previous presentations can be found here: https://lti.cs.cmu.edu/intranet/lti-summer-seminar-2020-slide-decks We hope to see you there! Kate Schaich Academic Program Manager, MLT Language Technologies Institute Carnegie Mellon University School of Computer Science GHC 6719 She/Her *T: 412-268-4788* -- *Chirag Nagpal* PhD Student, Auton Lab School of Computer Science Carnegie Mellon University cs.cmu.edu/~chiragn -------------- next part -------------- An HTML attachment was scrubbed... URL: From ngisolfi at cs.cmu.edu Thu Jul 9 09:21:49 2020 From: ngisolfi at cs.cmu.edu (Nick Gisolfi) Date: Thu, 9 Jul 2020 09:21:49 -0400 Subject: [Lunch] Today @noon over Zoom Message-ID: https://cmu.zoom.us/j/492870487 We hope to see you there! - Nick -------------- next part -------------- An HTML attachment was scrubbed... URL: From predragp at andrew.cmu.edu Fri Jul 10 19:28:37 2020 From: predragp at andrew.cmu.edu (Predrag Punosevac) Date: Fri, 10 Jul 2020 19:28:37 -0400 Subject: updates pushed Message-ID: <20200710232837.GF5Ci%predragp@andrew.cmu.edu> Dear Autonians, I just pushed bunch of security/stability patches to our infrastructure servers which required reboot dozen and a half machines. You might have noticed some blimps. The system appears to be stable. I am restarting OpenVPN daemons on your desktops. I hope you have great weekend. Cheers, Predrag From redman at andrew.cmu.edu Mon Jul 13 09:11:22 2020 From: redman at andrew.cmu.edu (Robert Edman) Date: Mon, 13 Jul 2020 09:11:22 -0400 Subject: Brainstorming candidate today Message-ID: Hi All, We have Dr. Ashraf Gaffar speaking at the brainstorming session this week at: Today at 3PM EDT. He will be discussing his work in machine learning with Dermatology and Cardiology and TBI in collaboration with the Mayo Clinic, Phoenix Childrens Hospital, and BrainCare. Hope to see you all there. The zoom info is: https://cmu.zoom.us/j/98367003048?pwd=OGR0ckIwc1g1NEJBbjNKbDBUVVZKUT09 Meeting ID: 983 6700 3048 Password: 041876 One tap mobile +16513728299,,98367003048#,,,,0#,,041876# US (St. Paul) +17866351003,,98367003048#,,,,0#,,041876# US (Miami) --Rob -------------- next part -------------- An HTML attachment was scrubbed... URL: From redman at andrew.cmu.edu Mon Jul 13 12:18:27 2020 From: redman at andrew.cmu.edu (Robert Edman) Date: Mon, 13 Jul 2020 12:18:27 -0400 Subject: Fwd: CMU Auton Lab In-Reply-To: References: Message-ID: Today's brainstorming session speaker just sent his title/abstract. Zoom info at the bottom. Hope to see you all there. Deep Intelligence Bridging Technical and Biological Complexities using AI Artificial intelligence depends heavily on complex computations and powerful hardware. Biology, on the other hand has its own complex behavior that starts with biochemical pathways and ends with medical practices. In this presentation, we briefly describe these two worlds of ?extreme? complexities, and show how we are identifying some common grounds that could use deep learning to solve difficult medical problems. With good command on recent ML hardware and software breakthroughs, we set out to collaborate with medical doctors to help them explicitly describe their medical work and experiences, then we isolated certain human-only medical practices and showed that they can benefit greatly from deep learning. Join Zoom Meeting https://cmu.zoom.us/j/98367003048?pwd=OGR0ckIwc1g1NEJBbjNKbDBUVVZKUT09 Meeting ID: 983 6700 3048 Password: 041876 One tap mobile +16513728299,,98367003048#,,,,0#,,041876# US (St. Paul) +17866351003,,98367003048#,,,,0#,,041876# US (Miami) ---------- Forwarded message --------- From: Ashraf Gaffar Date: Mon, Jul 13, 2020 at 10:50 AM Subject: Re: CMU Auton Lab To: Robert Edman Cc: Artur Dubrawski , Kyle Miller Hi PFA the title and abstract, Ashraf -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: Deep Intelligence-Abstract.docx Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document Size: 70394 bytes Desc: not available URL: From ngisolfi at cs.cmu.edu Thu Jul 16 10:50:50 2020 From: ngisolfi at cs.cmu.edu (Nick Gisolfi) Date: Thu, 16 Jul 2020 10:50:50 -0400 Subject: [Lunch] Today @noon over Zoom Message-ID: <42BF4888-6857-412B-AB6C-7232438F02D1@cs.cmu.edu> https://cmu.zoom.us/j/492870487 We hope to see you there! - Nick -------------- next part -------------- An HTML attachment was scrubbed... URL: From predragp at andrew.cmu.edu Fri Jul 17 17:32:27 2020 From: predragp at andrew.cmu.edu (Predrag Punosevac) Date: Fri, 17 Jul 2020 17:32:27 -0400 Subject: Fwd: Neocortex In-Reply-To: References: Message-ID: Dear Autonians, In the case you wonder what we could buy in the case you land a 200 million dollar grant this is your answer https://www.cmu.edu/psc/aibd/neocortex/introduction-webinar-post.html Enjoy, Predrag P.S. I actually heard the rumors during the webinar that the Tesla V100 we got for 37K are marginally worse in some situations from the above beast. AMD is coming back hard and that in turn means more hardware variety and better princess for us in the very near future. ---------- Forwarded message --------- From: Nick Nystrom Date: Fri, Jul 17, 2020 at 5:05 PM Subject: Thank you for your interest in the Introduction to Neocortex webinar - recording now available To: Predrag Punosevac Hi Predrag, Thank you for your interest in the Introduction to Neocortex webinar. We hope you were able to participate and enjoy it! In the webinar, we heard about Neocortex, an upcoming NSF-funded specialized supercomputer that is bound to transform the AI research landscape. Neocortex will be deployed by PSC in late 2020 and will be offered at no-cost for open (publishable) research. This webinar was presented by Paola A. Buitrago, Neocortex PI and PSC Director of AI and Big Data, and by Nicholas A. Nystrom, Neocortex co-PI and PSC Chief Scientist. The recording of the webinar, slides, and Q&A are now available for your convenience: Review the webinar recording, slides, and Q&A Your comments or questions are welcome at neocortex at psc.edu. For more information about Neocortex, please visit www.cmu.edu/psc/aibd/neocortex . We look forward to sharing upcoming Neocortex updates. Considering your interest in this webinar, you have been added to the *Neocortex Updates* mailing list. To unsubscribe, please click here to stop receiving our emails. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ngisolfi at cs.cmu.edu Thu Jul 23 09:47:33 2020 From: ngisolfi at cs.cmu.edu (Nick Gisolfi) Date: Thu, 23 Jul 2020 09:47:33 -0400 Subject: [Lunch] Today @noon over Zoom Message-ID: <50EDED91-01C3-46B0-980B-C6D4107904B3@cs.cmu.edu> https://cmu.zoom.us/j/492870487 We hope to see you there! - Nick -------------- next part -------------- An HTML attachment was scrubbed... URL: From awd at cs.cmu.edu Tue Jul 28 10:17:37 2020 From: awd at cs.cmu.edu (Artur Dubrawski) Date: Tue, 28 Jul 2020 10:17:37 -0400 Subject: Our own Emily Kennedy testifying in the US Congress on using technology against human trafficking Message-ID: Emily, President of Marinus Analytics, a CMU Auton Lab spinoff ocmpany providing technology solutions to combat human trafficking (Traffic Tam being their flagship tool we have originally developed here), is now testifying in front of the U.S. House Science subcommittee on the role of technology in countering trafficking in persons. The link to the online session is https://science.house.gov/hearings/the-role-of-technology-in-countering-trafficking-in-persons . The pdf of her statement can be found here: https://science.house.gov/imo/media/doc/Kennedy%20Testimony.pdf Way to go Emily! Cheers, Artur -------------- next part -------------- An HTML attachment was scrubbed... URL: From bspice at cs.cmu.edu Tue Jul 28 10:25:06 2020 From: bspice at cs.cmu.edu (Byron G Spice) Date: Tue, 28 Jul 2020 14:25:06 +0000 Subject: Our own Emily Kennedy testifying in the US Congress on using technology against human trafficking In-Reply-To: References: Message-ID: <2bf394068762483f9b1ced9febba5488@cs.cmu.edu> Thanks, Artur https://twitter.com/SCSatCMU/status/1288118138320519171 Byron Spice 412-268-9068 From: Artur Dubrawski Sent: Tuesday, July 28, 2020 10:18 AM To: users at autonlab.org Cc: Andrew W. Moore ; Martial Hebert ; James H Garrett Jr. ; Srinivasa G Narasimhan ; Byron G Spice ; Farnam Jahanian ; Michael McQuade Subject: Our own Emily Kennedy testifying in the US Congress on using technology against human trafficking Emily, President of Marinus Analytics, a CMU Auton Lab spinoff ocmpany providing technology solutions to combat human trafficking (Traffic Tam being their flagship tool we have originally developed here), is now testifying in front of the U.S. House Science subcommittee on the role of technology in countering trafficking in persons. The link to the online session is https://science.house.gov/hearings/the-role-of-technology-in-countering-trafficking-in-persons. The pdf of her statement can be found here: https://science.house.gov/imo/media/doc/Kennedy%20Testimony.pdf Way to go Emily! Cheers, Artur -------------- next part -------------- An HTML attachment was scrubbed... URL: From mmcquade at andrew.cmu.edu Tue Jul 28 11:52:57 2020 From: mmcquade at andrew.cmu.edu (Michael McQuade) Date: Tue, 28 Jul 2020 15:52:57 +0000 Subject: Our own Emily Kennedy testifying in the US Congress on using technology against human trafficking In-Reply-To: References: Message-ID: <70F04544-B549-4B9F-8C4E-4552E1558103@andrew.cmu.edu> Thanks for sharing such important work, Artur. Please pass on my very big thanks to Emily for both the technology Marinus is deploying and for her compelling testimony. Michael J. Michael McQuade, PhD. Vice President for Research Carnegie Mellon University 5000 Forbes Avenue | Warner Hall 624 | Pittsburgh, PA 15213 O: 412.268.2879 | mmcquade at andrew.cmu.edu From: Artur Dubrawski Date: Tuesday, July 28, 2020 at 10:17 AM To: "users at autonlab.org" Cc: "Andrew W. Moore" , Martial Hebert , James Garrett , Srinivasa G Narasimhan , Byron G Spice , Farnam Jahanian , Michael McQuade Subject: Our own Emily Kennedy testifying in the US Congress on using technology against human trafficking Emily, President of Marinus Analytics, a CMU Auton Lab spinoff ocmpany providing technology solutions to combat human trafficking (Traffic Tam being their flagship tool we have originally developed here), is now testifying in front of the U.S. House Science subcommittee on the role of technology in countering trafficking in persons. The link to the online session is https://science.house.gov/hearings/the-role-of-technology-in-countering-trafficking-in-persons. The pdf of her statement can be found here: https://science.house.gov/imo/media/doc/Kennedy%20Testimony.pdf Way to go Emily! Cheers, Artur -------------- next part -------------- An HTML attachment was scrubbed... URL: From ngisolfi at cs.cmu.edu Thu Jul 30 10:00:00 2020 From: ngisolfi at cs.cmu.edu (Nicholas Gisolfi) Date: Thu, 30 Jul 2020 10:00:00 -0400 Subject: [Lunch] Today @noon over Zoom Message-ID: https://cmu.zoom.us/j/492870487 We hope to see you there! - Nick -------------- next part -------------- An HTML attachment was scrubbed... URL: