From predragp at imap.srv.cs.cmu.edu Wed Apr 6 16:39:38 2016 From: predragp at imap.srv.cs.cmu.edu (predragp) Date: Wed, 06 Apr 2016 16:39:38 -0400 Subject: Scientific Computing Library Message-ID: Dear Autonians, Some of you were asking me about GCC-5.*, Python 3.5, latest Git 2.8.1 and similar software. I just added springdale-SCL repo http://puias.princeton.edu/data/puias/SCL/7-2.1/x86_64/ and started adding some of above software. The software is located in /opt/rh/ for gcc look at /opt/rh/devtoolset-4/root/usr/bin You will have to specify full path in your profile and in your Makefiles to use these things. It looks like I will have to compile latest git from the source but that is not a big deal and I am already running it on my machine. I am also fully aware that MATLAB 2016a is released. I installed on my desktop today and I am using it right now (all 11GB of binaries which require 8GB of RAM just to start). I will need to create headless installation package before I can start replacing our current MATLAB on computing nodes. I will try to do in a minimally disruptive way. Best, PRedrag From tw at andrew.cmu.edu Fri Apr 8 10:26:06 2016 From: tw at andrew.cmu.edu (Terrence Wong) Date: Fri, 8 Apr 2016 10:26:06 -0400 (EDT) Subject: Created slack team for Auton Message-ID: A few months ago some of us started using Slack for coordination and it seemed pretty useful, especially since our group is so spread out. If you would like to join the Auton slack team, please go here: https://auton.slack.com/signup andrew.cmu.edu and cs.cmu.edu email addresses should be able to join automatically. I can invite any other addresses. Terrence From predragp at cs.cmu.edu Wed Apr 13 14:40:47 2016 From: predragp at cs.cmu.edu (Predrag Punosevac) Date: Wed, 13 Apr 2016 14:40:47 -0400 Subject: Friday 04/15/16 1:30PM at NSH 3001 Message-ID: <20160413184047.O-JS5la6g%predragp@cs.cmu.edu> Dear Autonians, This is a friendly remainder that this Friday's brainstorming session speaker is Junier Oliva. The title and the abstract of his talk can be found below. Lunch will be served as usual. Best, Predrag Functional Linear Models for Brain Data *Background.* Modern neuroimaging data has provided a much needed window into the intricacies of the human brain. Neuroimaging techniques such as functional magnetic resonance imaging (fMRI), magnetoencephalography (MEG), and diffusion tensor imaging (DTI), often contain many thousands of functional observations per subject. While some success has been had using heuristical summary statistics of neuroimaging functional observations to build predictive models, there is a lack of a flexible and principled framework to build models from neuroimaging techniques. *Aim.* Our aim is to develop a general, principled framework for supervised learning that scales to many thousands of neuroimaging functional observations per subject without resorting to heuristical summary statistics. In particular, we look to regress a subject???s age given neuroimaging data. *Data.*Diffusion MR images were acquired from a total of 90 subjects. The subjects ranged in age from 13 to 60 years old, and included 45 males and 45 females. The subjects had no known history of neurological or mental disorder. We used per-voxel functional covariates of diffusion orientation distribution functions (dODFs) in our models and real-valued fractional anisotropy (FA) covariates as a baseline. dODFs are functions that represent the amount of water molecules, or spins, undergoing diffusion indifferent orientations over the S 2 sphere. FA values are the peak of the dODF and have previously been used as a summary statistic of dODFs for age regression. In total, 25K voxels were considered in a shared template-space. *Methods.* We develop and empirically test linear functional models for neuroimaging data. We use a model that represents neuroimaging functional observations nonparametrically using orthonormal basis projections. The age response is modeled as a sparse additive linear combination of inner products. We show that our model may be optimized using a group-LASSO approach.*Results.* Our functional sparse linear model was able to predict age with a 29.15% lower MSE than previous heuristic-based methods. Results were found to be statistically significant with a p-value of 0.04 using a paired t-test. *Conclusions.* In this work we have developed and tested a principled framework for building predictive supervised models with functional neuroimaging data. This framework allows one to use functional neuro-data in a statistically principled fashion without resorting to heuristical summary statistics. From predragp at cs.cmu.edu Wed Apr 13 17:28:39 2016 From: predragp at cs.cmu.edu (Predrag Punosevac) Date: Wed, 13 Apr 2016 17:28:39 -0400 Subject: Fwd: [Network Outage] SCS Wired Network in Gates-Hillman Centers and Newell Simon Hall Message-ID: <20160413212839.yYmMn3HK_%predragp@cs.cmu.edu> -------- Original Message -------- From: "SCS Help Desk" To: Subject: [Network Outage] SCS Wired Network in Gates-Hillman Centers and Newell Simon Hall Date: Wed, 13 Apr 2016 16:28:53 -0400 TIME: Tuesday April 19, 2016 at 6:00 AM - 8:00 AM SERVICES AFFECTED: Network connectivity at the Gates-Hillman Centers and Newell Simon Hall Details: SCS Computing Facilities will be upgrading the operating system on the Juniper network switches that provide network connectivity to Gates-Hillman Centers (GHC) and Newell-Simon Hall (NSH). This upgrade is necessary to address security issues reported by the vendor. Each floor in GHC will experience a loss of network connectivity for approximately 10 minutes while the switch is upgraded.?Additionally, machines in GHC and NSH may experience brief network outages as the building switches are upgraded. Please contact the SCS Help Desk at x8-4231 or send mail to?help+ at cs.cmu.edu?with any questions or concerns regarding this maintenance period.