From predragp at cs.cmu.edu  Fri Mar  3 14:11:28 2017
From: predragp at cs.cmu.edu (Predrag Punosevac)
Date: Fri, 03 Mar 2017 14:11:28 -0500
Subject: Fwd: [Power Outage] SCS Wean Hall machine room - March 8th
Message-ID: <20170303191128.YZujSZ86z%predragp@cs.cmu.edu>

Dear Autonians,

This is a gentle reminder that power outage in the Wean Hall machine
room has been scheduled for Wednesday March 8th. I am planning to
gracefully shut down all our servers Tuesday March 7 around 9:00 PM.
Please plan on not being able to use servers for 48h (worse case
scenario).

Best,
Predrag

-------- Original Message --------
Subject: [Power Outage] SCS Wean Hall machine room - March 8th
To: Edward J Walter <ewalter+ at cs.cmu.edu>
From: Edward Walter <ewalter at cs.cmu.edu>
Date: Wed, 22 Feb 2017 10:34:22 -0500

Hi All,

Thank you to everyone who provided feedback.  The power outage in the 
Wean Hall machine room has been scheduled for Wednesday March 8th.

New equipment is coming in the door this week and there is a pressing 
need to get it into production as quickly as possible.  We can't deploy 
new GPU servers until this work is completed.

We expect all systems/clusters to be back online and functional before 
the end of the day on March 8th... this should be a relatively short 
interruption in service.

Thank you once again for your patience and your feedback.

-Ed

-- 

Ed Walter
Technical Manager - Unix Engineering
SCS Computing Facilities
Carnegie Mellon University


On 02/09/2017 10:04 AM, Edward Walter wrote:
> Hello,
>
> SCS Computing Facilities is working with CMU FMS to schedule the final
> round of work for our Wean Hall machine room - power expansion project.
> This will involve provisioning approximately 11x high capacity circuits
> to accommodate the influx of GPU servers and cluster expansions that is
> expected to continue through 2017.
>
> We're planning to schedule this work for the end of February or the
> beginning of March.  The outage is expected to take 1 business day and
> will need to be scheduled mid-week (preferably on a Tuesday or Wednesday).
>
> If there are specific days/dates we should avoid (due to deadlines,
> etc); please let us know ASAP so that we can coordinate this with FMS
> and the electrical contractors.
>
> Thank you.
>
> -Ed
>
>
> Affected clusters:
>     ACTR.HPC1.CS.CMU.EDU
>     AUTON
>     COMA.HPC1.CS.CMU.EDU
>     CORTEX.ML.CMU.EDU
>     LATEDAYS.ANDREW.CMU.EDU
>     MATRIX.ML.CMU.EDU
>     PSYCH-O.HPC1.CS.CMU.EDU
>     PERCEPTRON.RI.CMU.EDU
>     ROCKS.IS.CS.CMU.EDU
>     WORKHORSE.LTI.CS.CMU.EDU
>     YODA.GRAPHICS.CS.CMU.EDU
>     TRINITY.VISION.CS.CMU.EDU
>
>
> Affected servers:
>     ACTR-SERVER
>     ARNOUT.ML
>     DENVER.LTI
>     DGX-1.ML
>     FLORIS.ML
>     GPUSERVER.PERCEPTION
>     GPUSERVER2.PERCEPTION
>     GPUSERVER3.PERCEPTION
>     GPUSERVER5.PERCEPTION
>     GPUSERVER6.PERCEPTION
>     GPUSERVER7.PERCEPTION
>     ISLR0S0
>     ISLR0S14
>     ISLR1S10
>     JAN.ML
>     LOR.LTI
>     LYSBET.ML
>     MARTEN.ML
>     MIAMI.LTI
>     PACIFIC.DB
>     SASKIA.ML
>     SLIF.COMPBIO
>
>


From predragp at cs.cmu.edu  Tue Mar  7 14:43:31 2017
From: predragp at cs.cmu.edu (Predrag Punosevac)
Date: Tue, 07 Mar 2017 14:43:31 -0500
Subject: Power outage reminder
Message-ID: <20170307194331.zkgRTqrl5%predragp@cs.cmu.edu>

Dear Autonians,

Just a friendly reminder that I will start shutting all server tonight
around 9:00 PM for planned electric work in the server room. Please plan
on 48h down time.

Best,
Predrag

From predragp at cs.cmu.edu  Wed Mar  8 14:15:45 2017
From: predragp at cs.cmu.edu (Predrag Punosevac)
Date: Wed, 08 Mar 2017 14:15:45 -0500
Subject: Power restored
Message-ID: <20170308191545.hvN8AWc4S%predragp@cs.cmu.edu>

Dear Autonians,

Power in the server room is now restored. All our servers appear to be
up and running (lou1 has a dead memory module). I am restoring services
according to their priority. Remote shell access to the lab
infrastructure is also restored. You can use computing nodes but you
will have to give me another 30-45 minutes to restart MATLAB licensing
server on the computing nodes.

Best,
Predrag

From joliva at cs.cmu.edu  Wed Mar  8 16:14:56 2017
From: joliva at cs.cmu.edu (Junier Oliva)
Date: Wed, 8 Mar 2017 16:14:56 -0500
Subject: Fwd: Thesis Proposal - 3/10/17 - Junier Oliva - Distribution and
 Histogram (DisH) Learning
In-Reply-To: <d464852b-5c18-9e84-2ff0-b25b9f49ca59@cs.cmu.edu>
References: <d464852b-5c18-9e84-2ff0-b25b9f49ca59@cs.cmu.edu>
Message-ID: <CAPGQ=J05edj+kom0aTebDE7Vs0zGTtgnWJMM21WyqFOK7-zt6g@mail.gmail.com>

ICYMI I'll be proposing my thesis this Friday! Feel free to come by :)

Best,
Junier

---------- Forwarded message ----------
From: Diane Stidle <diane+ at cs.cmu.edu>
Date: Fri, Mar 3, 2017 at 4:30 PM
Subject: Thesis Proposal - 3/10/17 - Junier Oliva - Distribution and
Histogram (DisH) Learning
To: "ml-seminar at cs.cmu.edu" <ML-SEMINAR at cs.cmu.edu>, Le Song <
lsong at cc.gatech.edu>


*Thesis Proposal*

Date: 3/10/17
Time: 3:00pm
Place: 8102 GHC
Speaker: Junier Oliva

Title: Distribution and Histogram (DisH) Learning

Abstract:
This thesis advances the explicit use of distributions in machine learning.
We develop algorithms that consider distributions as functional
covariates/responses, and methods that use distributions as internal
representations. We consider distributions since they are a straightforward
characterization of many natural phenomena and provide a richer description
than simple point data by detailing information at an aggregate level. Our
approach may be seen as addressing two sides of the same coin: on one side,
we use traditional machine learning algorithms adjusted to directly operate
on inputs and outputs that are probability functions (and sample sets); on
the other side, we develop better estimators for traditional vector data by
making use of, and adjusting internal distributions.

We begin by developing algorithms for traditional machine learning tasks
for the cases when one's input (and/or possibly output) is not a finite
point, but is instead a distribution, or sample set drawn from a
distribution. We develop a scalable nonparametric estimator for regressing
a real valued response given an input that is a distribution, a case which
we coin distribution to real regression (DRR). Furthermore, we extend this
work to the case when both the output response and the input covariate are
distributions; a task we call distribution to distribution regression
(DDR). Moreover, we propose flexible and scalable techniques for
conditional density estimation where one regresses an output response that
is a distribution given a real valued covariate.

After, we look to expand the versatility and efficacy of traditional
machine learning tasks through novel methods that operate with implicit or
latent distributions. Take for example kernel methods that use a
shift-invariant kernel. Here, one's kernel uniquely determines a
distribution, the spectral density, that controls the frequencies
considered over inputs. We show that one may improve the performance of
kernel learning tasks by learning this spectral distribution in a
data-driven fashion using Bayesian nonparametric techniques. Furthermore,
we recast classification as a task on distributions. Namely, the Bayes
classification risk is minimized when the distributions of features of
instances from each particular class are non-overlapping. Hence, we propose
a distribution based task with ties to a Bayes risk to perform supervised
feature learning.

Leveraging the high-level, aggregate information provided by distributions
in these algorithms allows us to improve performance in a broad range of
domains including: cosmology, neuroscience, computer vision, and natural
language processing. Furthermore, the scalable nature of our algorithms are
such that we may scale to millions, even billions of instances.

Thesis Committee:
Barnabas Poczos (Co-Chair)
Jeff Schneider (Co-Chair)
Ruslan Salakhutdinov
Le Song (Georgia Institute of Technology)

Link to draft document:
https://www.dropbox.com/s/tbxj4v0oy35omky/Thesis_Proposal.pdf?dl=0

-- 
Diane Stidle
Graduate Programs Manager
Machine Learning Department
Carnegie Mellon Universitydiane at cs.cmu.edu412-268-1299 <(412)%20268-1299>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20170308/62778b17/attachment.html>

From awd at cs.cmu.edu  Fri Mar 10 17:13:59 2017
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Fri, 10 Mar 2017 17:13:59 -0500
Subject: Fwd: Fwd: Post Hoc Presentation Follow Up
In-Reply-To: <C27E9EED-2684-4F72-87CF-183117EA997E@andrew.cmu.edu>
References: <C27E9EED-2684-4F72-87CF-183117EA997E@andrew.cmu.edu>
Message-ID: <461d4c6e-eaab-aab7-cc62-d1ad5e17bda9@cs.cmu.edu>

Congrats to the Auton Lab DARPA Memex team.
Apparently, it continues topping - or helping others top - various 
performance evaluations.

Cheers!
Artur


-------- Forwarded Message --------
Subject: 	Fwd: Post Hoc Presentation Follow Up
Date: 	Fri, 10 Mar 2017 16:54:05 -0500
From: 	Benedikt Boecking <boecking at andrew.cmu.edu>
To: 	Artur Dubrawski <awd at cs.cmu.edu>



See David?s comment on the inclusion of our clustering results at last QPR.

Best,
Ben

> Begin forwarded message:
>
> *From: *David Schroh <dschroh at uncharted.software 
> <mailto:dschroh at uncharted.software>>
> *Subject: **Fwd: Post Hoc Presentation Follow Up*
> *Date: *March 10, 2017 at 4:51:35 PM EST
> *To: *Benedikt Boecking <boecking at andrew.cmu.edu 
> <mailto:boecking at andrew.cmu.edu>>
>
> Ben,
>
> Thanks again for helping with the clustering at the Fall QPR.  In case 
> you missed the bottom line....
>
> Conclusion on Slide 53: "The union of Uncharted and Lattice 
> Extractions, in combination with CMU Clusters where applicable, 
> performed the best of all configurations for all question types."
>
> David
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20170310/f10a132f/attachment.html>

From mbarnes1 at andrew.cmu.edu  Fri Mar 10 19:12:33 2017
From: mbarnes1 at andrew.cmu.edu (Matthew Barnes)
Date: Sat, 11 Mar 2017 00:12:33 +0000
Subject: Google ML job
Message-ID: <CAB7OVwCQgG62h8qCVxN9uxdrwxENLM=HcnVEB25W_A7=Z-i1XA@mail.gmail.com>

My brother's team at Google is looking for a full time ML deployment
engineer. Posting says Washington, but I'm pretty sure the job is actually
for the SF bay area. I think it would involve working on lots of different
customer projects, using tensorflow and some of their other cloud services.
For anyone graduating soon, let me know if you're interested I can put you
in touch.

https://careers.google.com/jobs#!t=jo&jid=/google/big-data-or-machine-learning-deployment-building-c-747-6th-st-s-kirkland-wa-usa-2483850475

- Matt
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20170311/d29353dd/attachment.html>

From awm at cs.cmu.edu  Sat Mar 11 15:15:11 2017
From: awm at cs.cmu.edu (Andrew Moore)
Date: Sat, 11 Mar 2017 15:15:11 -0500
Subject: Fwd: Post Hoc Presentation Follow Up
In-Reply-To: <461d4c6e-eaab-aab7-cc62-d1ad5e17bda9@cs.cmu.edu>
References: <C27E9EED-2684-4F72-87CF-183117EA997E@andrew.cmu.edu>
 <461d4c6e-eaab-aab7-cc62-d1ad5e17bda9@cs.cmu.edu>
Message-ID: <CAPQV5HRF=BhsCJBHkXHg0+cNc26DhJR0itU5QEkTQN+HQ_fv9Q@mail.gmail.com>

You-all continue to amaze me. Thank you for being amazing.

In the meantime Artur, can you point me to the details and let me know
if/when we can talk about this publicly?


On Fri, Mar 10, 2017 at 5:13 PM, Artur Dubrawski <awd at cs.cmu.edu> wrote:

> Congrats to the Auton Lab DARPA Memex team.
> Apparently, it continues topping - or helping others top - various
> performance evaluations.
>
> Cheers!
> Artur
>
>
> -------- Forwarded Message --------
> Subject: Fwd: Post Hoc Presentation Follow Up
> Date: Fri, 10 Mar 2017 16:54:05 -0500
> From: Benedikt Boecking <boecking at andrew.cmu.edu>
> <boecking at andrew.cmu.edu>
> To: Artur Dubrawski <awd at cs.cmu.edu> <awd at cs.cmu.edu>
>
> See David?s comment on the inclusion of our clustering results at last
> QPR.
>
> Best,
> Ben
>
> Begin forwarded message:
>
> *From: *David Schroh <dschroh at uncharted.software>
> *Subject: **Fwd: Post Hoc Presentation Follow Up*
> *Date: *March 10, 2017 at 4:51:35 PM EST
> *To: *Benedikt Boecking <boecking at andrew.cmu.edu>
>
> Ben,
>
> Thanks again for helping with the clustering at the Fall QPR.  In case you
> missed the bottom line....
>
> Conclusion on Slide 53: "The union of Uncharted and Lattice Extractions,
> in combination with CMU Clusters where applicable, performed the best of
> all configurations for all question types."
>
> David
>
>


-- 
Andrew Moore <http://www.cs.cmu.edu/~awm/>, Dean, School of Computer Science
<http://www.cs.cmu.edu/>, Carnegie Mellon. Twitter feed
<https://twitter.com/awmcmu>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20170311/34e94f4c/attachment.html>

From awd at cs.cmu.edu  Mon Mar 13 09:30:18 2017
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 13 Mar 2017 09:30:18 -0400
Subject: Fwd: funding for ML for Social Good
In-Reply-To: <912de34738124dbd9895655aa2b3d410@PGH-MSGMLT-01.andrew.ad.cmu.edu>
References: <912de34738124dbd9895655aa2b3d410@PGH-MSGMLT-01.andrew.ad.cmu.edu>
Message-ID: <ca6d54ea-9714-6dad-78c2-5278adeb010c@cs.cmu.edu>

FYI, please let me know your thoughts and/or interests especially if 
they relate to topics we have not studied deeply yet.

Thanks
Artur


-------- Forwarded Message --------
Subject: 	funding for ML for Social Good
Date: 	Mon, 13 Mar 2017 13:21:30 +0000
From: 	Roni Rosenfeld <roni at cs.cmu.edu>
To: 	ml-faculty at cs.cmu.edu <ml-faculty at cs.cmu.edu>, 
ml-students at cs.cmu.edu <ml-students at cs.cmu.edu>
CC: 	Roni Rosenfeld <roni at cs.cmu.edu>



Dear MLD faculty and students,

We received some funding to support the study and use of machine 
learning for social good.   This includes problems in government (local, 
state or federal), NGOs (domestic or international), or any other area 
where you think you can make a positive difference with thoughtful and 
skillful use of data.  A more detailed public announcement is forthcoming.

If you (or another ML-savvy SCS student or faculty you know) are 
interesting in working on such a problem _this summer_, whether or not 
you have a particular project in mind, please drop me a quick line.

Best wishes,

-Roni

---------------------------------------------------------------------------------

Roni Rosenfeld, Professor

School of Computer Science, Carnegie Mellon University

http://www.cs.cmu.edu/~roni <http://www.cs.cmu.edu/%7Eroni>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20170313/6f534cf6/attachment.html>

From awd at cs.cmu.edu  Thu Mar 16 12:45:36 2017
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Thu, 16 Mar 2017 12:45:36 -0400
Subject: Congrats to every Autonian involved in PHIS and other food safety
 related projects!
Message-ID: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>

This is very cool :D
I am really pleased that finally the government themselves decided to go 
public
about our hard work over the past several years (for some reason, they 
wanted
to stay relatively quiet for a long while):

https://www.aphl.org/aboutAPHL/publications/action/Pages/APHL-in-Action-Winter-2017-Foodborne-Outbreak-Portal.aspx

Congrats to everyone involved in the process! Lately, it was primarily Jarod
who did an outstanding job making all the users of our tools extremely 
happy.
It took us many years to develop the technology, prove it and get it to 
the current
level of user acceptance, and many Autonians and our friends contributed,
including our respected Dean who sparked the Lab's involvement in this 
application
domain all the way back in 2003 (yes, I know, he is _that_ old!).

Cheers!
Artur

From awm at cs.cmu.edu  Thu Mar 16 12:57:40 2017
From: awm at cs.cmu.edu (Andrew Moore)
Date: Thu, 16 Mar 2017 11:57:40 -0500
Subject: Congrats to every Autonian involved in PHIS and other food safety
 related projects!
In-Reply-To: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>
References: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>
Message-ID: <CAPQV5HQ5L-PNQVW_zp8PW-nSScwLOpZPhLyF+9yk=Ex7gvzNdA@mail.gmail.com>

+jim dougherty (0to5)

This is a very interesting story that someone out there might be interested
in. The same kinds of machine learning algorithms used by big banks and
internet companies can help keep us safe from foodborne disease outbreaks.


On Thu, Mar 16, 2017 at 11:45 AM, Artur Dubrawski <awd at cs.cmu.edu> wrote:

> This is very cool :D
> I am really pleased that finally the government themselves decided to go
> public
> about our hard work over the past several years (for some reason, they
> wanted
> to stay relatively quiet for a long while):
>
> https://www.aphl.org/aboutAPHL/publications/action/Pages/
> APHL-in-Action-Winter-2017-Foodborne-Outbreak-Portal.aspx
>
> Congrats to everyone involved in the process! Lately, it was primarily
> Jarod
> who did an outstanding job making all the users of our tools extremely
> happy.
> It took us many years to develop the technology, prove it and get it to
> the current
> level of user acceptance, and many Autonians and our friends contributed,
> including our respected Dean who sparked the Lab's involvement in this
> application
> domain all the way back in 2003 (yes, I know, he is _that_ old!).
>
> Cheers!
> Artur
>



-- 
Andrew Moore <http://www.cs.cmu.edu/~awm/>, Dean, School of Computer Science
<http://www.cs.cmu.edu/>, Carnegie Mellon. Twitter feed
<https://twitter.com/awmcmu>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20170316/2d61b869/attachment.html>

From jim at 0to5.com  Thu Mar 16 13:36:26 2017
From: jim at 0to5.com (Jim Dougherty)
Date: Thu, 16 Mar 2017 13:36:26 -0400
Subject: Congrats to every Autonian involved in PHIS and other food safety
 related projects!
In-Reply-To: <CAPQV5HQ5L-PNQVW_zp8PW-nSScwLOpZPhLyF+9yk=Ex7gvzNdA@mail.gmail.com>
References: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>
 <CAPQV5HQ5L-PNQVW_zp8PW-nSScwLOpZPhLyF+9yk=Ex7gvzNdA@mail.gmail.com>
Message-ID: <6B57DABD-E043-4086-B09E-DA0B44CBF035@0to5.com>

Hi Andrew,

 

This is great stuff! Thanks for sending this along. 

 

Artur, would you be available for potential media interviews surrounding this topic in April?

 

Thanks!
Jim

_____________________

 

Jim Dougherty, Strategist

Z E R O T O 5 I V E  |  www.0to5.com

570.239.4954

jim at 0to5.com

@jdart0to5

 

From: <awmcmu at gmail.com> on behalf of Andrew Moore <awm at cs.cmu.edu>
Date: Thursday, March 16, 2017 at 12:57 PM
To: Artur Dubrawski <awd at cs.cmu.edu>, Jim Dougherty <jim at 0to5.com>
Cc: <users at autonlab.org>, Martial Hebert <hebert+ at cs.cmu.edu>, Byron Spice <bspice at cs.cmu.edu>, Kimberly Elenberg <kbkimberlybishop at gmail.com>, Manuela Veloso <mmv at cs.cmu.edu>
Subject: Re: Congrats to every Autonian involved in PHIS and other food safety related projects!

 

+jim dougherty (0to5)

 

This is a very interesting story that someone out there might be interested in. The same kinds of machine learning algorithms used by big banks and internet companies can help keep us safe from foodborne disease outbreaks.

 

 

On Thu, Mar 16, 2017 at 11:45 AM, Artur Dubrawski <awd at cs.cmu.edu> wrote:

This is very cool :D
I am really pleased that finally the government themselves decided to go public
about our hard work over the past several years (for some reason, they wanted
to stay relatively quiet for a long while):

https://www.aphl.org/aboutAPHL/publications/action/Pages/APHL-in-Action-Winter-2017-Foodborne-Outbreak-Portal.aspx

Congrats to everyone involved in the process! Lately, it was primarily Jarod
who did an outstanding job making all the users of our tools extremely happy.
It took us many years to develop the technology, prove it and get it to the current
level of user acceptance, and many Autonians and our friends contributed,
including our respected Dean who sparked the Lab's involvement in this application
domain all the way back in 2003 (yes, I know, he is _that_ old!).

Cheers!
Artur



 

-- 

Andrew Moore, Dean, School of Computer Science, Carnegie Mellon. Twitter feed

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20170316/46436f40/attachment.html>

From hebert at cs.cmu.edu  Thu Mar 16 15:05:39 2017
From: hebert at cs.cmu.edu (Martial Hebert)
Date: Thu, 16 Mar 2017 15:05:39 -0400
Subject: Congrats to every Autonian involved in PHIS and other food safety
 related projects!
In-Reply-To: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>
References: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>
Message-ID: <cfe964dc-c9b8-1dfc-f5f2-c43184c720f8@cs.cmu.edu>

Outstanding. Congratulations to all! Let's hope we can  publicize this.

-----M

PS: Might you share with us how many lines of code were written by our 
esteem Dean?

On 3/16/2017 12:45 PM, Artur Dubrawski wrote:
> This is very cool :D
> I am really pleased that finally the government themselves decided to 
> go public
> about our hard work over the past several years (for some reason, they 
> wanted
> to stay relatively quiet for a long while):
>
> https://www.aphl.org/aboutAPHL/publications/action/Pages/APHL-in-Action-Winter-2017-Foodborne-Outbreak-Portal.aspx 
>
>
> Congrats to everyone involved in the process! Lately, it was primarily 
> Jarod
> who did an outstanding job making all the users of our tools extremely 
> happy.
> It took us many years to develop the technology, prove it and get it 
> to the current
> level of user acceptance, and many Autonians and our friends contributed,
> including our respected Dean who sparked the Lab's involvement in this 
> application
> domain all the way back in 2003 (yes, I know, he is _that_ old!).
>
> Cheers!
> Artur


From mmv at cs.cmu.edu  Thu Mar 16 15:29:24 2017
From: mmv at cs.cmu.edu (Manuela Veloso)
Date: Thu, 16 Mar 2017 15:29:24 -0400
Subject: Congrats to every Autonian involved in PHIS and other food safety
 related projects!
In-Reply-To: <cfe964dc-c9b8-1dfc-f5f2-c43184c720f8@cs.cmu.edu>
References: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>
 <cfe964dc-c9b8-1dfc-f5f2-c43184c720f8@cs.cmu.edu>
Message-ID: <707521E0-A8F0-480F-BB38-9787EC38F297@cs.cmu.edu>

Remarkable!! 
Congratulations!!
Best,
Manuela

Sent from my iPhone

> On Mar 16, 2017, at 3:05 PM, Martial Hebert <hebert at cs.cmu.edu> wrote:
> 
> Outstanding. Congratulations to all! Let's hope we can  publicize this.
> 
> -----M
> 
> PS: Might you share with us how many lines of code were written by our esteem Dean?
> 
>> On 3/16/2017 12:45 PM, Artur Dubrawski wrote:
>> This is very cool :D
>> I am really pleased that finally the government themselves decided to go public
>> about our hard work over the past several years (for some reason, they wanted
>> to stay relatively quiet for a long while):
>> 
>> https://www.aphl.org/aboutAPHL/publications/action/Pages/APHL-in-Action-Winter-2017-Foodborne-Outbreak-Portal.aspx 
>> 
>> Congrats to everyone involved in the process! Lately, it was primarily Jarod
>> who did an outstanding job making all the users of our tools extremely happy.
>> It took us many years to develop the technology, prove it and get it to the current
>> level of user acceptance, and many Autonians and our friends contributed,
>> including our respected Dean who sparked the Lab's involvement in this application
>> domain all the way back in 2003 (yes, I know, he is _that_ old!).
>> 
>> Cheers!
>> Artur
> 


From kbkimberlybishop at gmail.com  Thu Mar 16 17:17:49 2017
From: kbkimberlybishop at gmail.com (kbkimberlybishop at gmail.com)
Date: Thu, 16 Mar 2017 16:17:49 -0500
Subject: Congrats to every Autonian involved in PHIS and other food safety
 related projects!
In-Reply-To: <707521E0-A8F0-480F-BB38-9787EC38F297@cs.cmu.edu>
References: <5a941489-d1cd-d975-8162-7477ee2fb773@cs.cmu.edu>
 <cfe964dc-c9b8-1dfc-f5f2-c43184c720f8@cs.cmu.edu>
 <707521E0-A8F0-480F-BB38-9787EC38F297@cs.cmu.edu>
Message-ID: <740ED33C-03F9-462F-9B7D-7C2065F7B939@gmail.com>

Awesome. There are some upcoming opportunities to apply same concepts in DoD for optimizing human performance. Artur- heading to Australia. Will call the first week of April. 

Best regards, 
Kimberly 

Sent from my iPhone

> On Mar 16, 2017, at 2:29 PM, Manuela Veloso <mmv at cs.cmu.edu> wrote:
> 
> Remarkable!! 
> Congratulations!!
> Best,
> Manuela
> 
> Sent from my iPhone
> 
>> On Mar 16, 2017, at 3:05 PM, Martial Hebert <hebert at cs.cmu.edu> wrote:
>> 
>> Outstanding. Congratulations to all! Let's hope we can  publicize this.
>> 
>> -----M
>> 
>> PS: Might you share with us how many lines of code were written by our esteem Dean?
>> 
>>> On 3/16/2017 12:45 PM, Artur Dubrawski wrote:
>>> This is very cool :D
>>> I am really pleased that finally the government themselves decided to go public
>>> about our hard work over the past several years (for some reason, they wanted
>>> to stay relatively quiet for a long while):
>>> 
>>> https://www.aphl.org/aboutAPHL/publications/action/Pages/APHL-in-Action-Winter-2017-Foodborne-Outbreak-Portal.aspx 
>>> 
>>> Congrats to everyone involved in the process! Lately, it was primarily Jarod
>>> who did an outstanding job making all the users of our tools extremely happy.
>>> It took us many years to develop the technology, prove it and get it to the current
>>> level of user acceptance, and many Autonians and our friends contributed,
>>> including our respected Dean who sparked the Lab's involvement in this application
>>> domain all the way back in 2003 (yes, I know, he is _that_ old!).
>>> 
>>> Cheers!
>>> Artur
>> 


From yichongx at andrew.cmu.edu  Wed Mar 22 00:49:44 2017
From: yichongx at andrew.cmu.edu (Yichong Xu)
Date: Wed, 22 Mar 2017 00:49:44 -0400
Subject: Space on GPU machines?
Message-ID: <ED687341-735F-46E3-848A-6574E65B192A@andrew.cmu.edu>

Hi all,
Currently I?ve got a small job to run on GPU machines. It?s a bit urgent so can someone leave some space for me on one machine, GPU4 the best (it?s currently installed there)? It seems all machines are busy right now. It won?t take too long to run.



Yichong Xu
Machine Learning Department, CMU
yichongx at cs.cmu.edu
412-652-8309