Exploiting the Unused Part of the Brain
|
|
- Cathleen Daniel
- 5 years ago
- Views:
Transcription
1 Exploiting the Unused Part of the Brain Deep Learning and Emerging Technology For High Energy Physics Jean-Roch Vlimant
2 A 10 Megapixel Camera
3 CMS 100 Megapixel Camera
4 CMS Detector
5 CMS Readout Highly heterogeneous system Raw data is 100M channels sampled every 25 ns : 1Pb/s 50EB per day in readout and online processing.
6 HLT 1-3 khz 1000 Gb/s L1 105 Hz 40 MHz Event Filtering 1000 Gb/s From Big Data to Smart Data with ultra fast decision
7 Why Deep Learning LHC Data Processing may use deep learning methods in many aspects (attend other relevant talk at the Caltech booth) Large volume of data and simulated data to analyze Several class of LHC Data analysis make use of classifier for signal versus background discrimination. Use of BDT on high level features Increasing use of MLP-like deep neural net Deep learning has delivered super-human performance at certain class of tasks (computer vision, speech recognition,...) Use of convolutional neural net, recurrent topologies, long-short-term-memory cells,... Deep learning has advantage at training on raw data Several levels of data distillation in LHC data processing Neural net computation is highly parallelizable Going beyond fully connected networks with advanced deep neural net topologies Multi-classification of LHC events from particle-level information Charged particle tracking with recurrent and convolutional topologies Particle identification and energy regression in highly granular future calorimeter... 7
8 Advanced Machine Learning and Deep Learning (my selection) 8
9 Machine Learning in a Nutshell Balazs Kegl, CERN
10 Scene Labeling Karpathy, Fei-Fei, CVPR 2015 Create a description of images Generate a decay process description from collision representation, with application to triggers 10
11 Scenery Interpretation Farabet et al. ICML 2012, PAMI 2013 Group and classify what each pixel belongs to Real-time video processing with deep learning Multiple applications to pileup mitigation, object identification, tracking. All from raw data 11
12 Attention Learning Identify people from faces with multiple attention filters Object identification, noise subtraction,... 12
13 Text Processing Question and Answer machine, language translation, semantic arithmetic,... Can the raw data of detector be interpreted as texts and translated into physics descriptions? 13
14 Embedded Symmetries p4 group Introduction of convolutional layers was a ground-breaking advancement Research on embedding more fundamental symmetries into neural nets p4m group T.S. Cohen, M. Welling ICML2016 Symmetries operate on the data or internal representation of data Next is to implement symmetries of physics to build physics-specific NN 14
15 Toolkit and Services Lots of libraries out there, several key components in each major languages. Lots of big-data analytics services offered Common theme of going for spark-hdfs support Question of having in-house software or embracing external libraries is very much alive 15
16 Application to Intensity and Energy Frontiers (a selected few) 16
17 NOVA Event Classification Slides on Paolo 17
18 Particle Jet Identification Top Tagger arxiv: Almeida, Backovic, Cliche, Lee, Perelstein Neural net W tagger arxiv: , Oliveira, Kagan, Mackey, Nachman, Schwartzman W to QCD discrimination Train 18
19 3D Calorimetry Imaging 100GeV Photon 100GeV Pi0 LCD Calorimeter configuration 5x5 mm Pixel calorimeter 28 layer deep for Ecal 70 layer deep for Hcal Photon and pion particle gun Classification, regression and combined models 19
20 Irregular Geometry Challenge Projective Geometry Hexagonal cells The images we are dealing with are not as regular as standard images. Need for specific new treatment and methods to feed neural nets Variable Depth Segmentation 20
21 Collision Event Classification Full event classification using reconstructed particle 4-vectors Recurrent neural nets, Long short term memory cells Dedicated layer with Lorentz boosting Step toward event classification with lower level data : low level feature as opposed to analysis level variables 21
22 Ordering Challenge Text have natural order. RNN/LSTM can correlate the information to internal representation There is underlying order in collision events. Smeared through timing resolution. No natural order in observable 22
23 Charged Particle Tracking Perfect example of pattern recognition Data sparsity is not common in image processing Several angles to tackle the problem. Deep Kalman filter, RNN to learn dynamics, sparse image processing,... Kaggle challenge in preparation 23
24 Challenge of Tracking 24
25 HEP Trk.X LBL, FNAL, Caltech consortium sponsored by the DOE Preparation of simulated data Accurate, fast and light Explore new approaches to charged particle tracking using advanced pattern recognition techniques Recurrent neural nets in learning track kinematics Convolutional neural nets for pattern recognition Hough-like transformation from hit position space to track parameter space Advanced Kalman filter parallelization... exploration has started Tracking competition (a la kaggle) in preparation 25
26 Other Applications Outliers selection Anomaly detection Data quality automation Detector control Experiment control Data popularity prediction Computing grid control Denoising with auto-encoder Fast simulation... 26
27 Accelerating and Emerging Technologies 27
28 Supermicro Server Caltech Servers 2 compute nodes : Intel Xeon CPU E GHz processors per node (28 cores per CPU) with 8 NVIDIA Pascal GTX 1080 Theoretical Peak Performance : 80 Tflops Theano, Tensorflow, Keras MPI training Spearmint hyper-optimization Many thanks to our partners Nvidia and Supermicro 28
29 ALCF Cooley 126 compute nodes : Two 2.4 GHz Intel Haswell E v3 processors per node (6 cores per CPU, 12 cores total) and NVIDIA Tesla K80 Theoretical Peak Performance : 293 Tflops Development Project with 8k core hours Theano, Tensorflow, Keras MPI ready Spearmint experimental 29
30 CSCS Piz Daint 5272 compute nodes : Intel Xeon 2.60GHz (8 cores, 16 virtual cores with hyperthreading enabled, 32GB RAM) and NVIDIA Tesla K20X Theoretical Peak Performance : Pfops Scratch capacity : 2.7 PB Development Project with 36k core hours Theano, Tensorflow, Keras MPI ready Spark experimental stage 30
31 OLCF Titan compute nodes : 2.2GHz AMD Opteron 6274 processors per node (16 cores per CPU) and NVIDIA Tesla K20X Theoretical Peak Performance : 20 Pflops Allocation in preparation
32 Distributed Learning Titan X GTX 1080 Deep learning with elastic averaging SGD Revisiting Distributed Synchronous SGD Implementation with Spark and MPI for the Keras framework
33 Performance Ran on the supermicro 8GPU server here at SC16 Normalized to 2 GPU performance point Please add a factor 2x 7x max speedup Linear speedup with number of workers Saturation in co-scheduling GPU (2 workers on the same GPU) 33
34 Performance Ran on ALCF Cooley 126 GPU cluster Normalized to 2 GPU performance point Please add a factor 2x 14x max speedup Non-linear speedup with number of GPU Linear speedup with number of GPU 34
35 Applicability 35
36 Training vs Inference GPUs are the workhorse for parallel computing Enable training large models, with large dataset Deep learning facility clusters Emergence of smaller GPU Not dedicated to training Strike the balance between Tflops/$ for inference Deployment on the grid 36
37 Neuromorphic Hardware Implementing plasticity in hardware Process signal from detector and adapt to categories of pattern (unsupervised) Post-classified from data analysis or rate throttling NCCR consortium assembling to develop this technology further, with our use case in mind 37
38 Cognitive Computing Spiking neural net as processing units : Cognitive Computing Processing Unit : CCPU Adopt a new programming scheme, translate existing software See Rebecca Carney's talk for more details 38
39 Summary Impressive achievement and promise of modern machine learning and deep learning From realistic to speculative applicability to field of High Energy and Frontier Physics Emerging tools and technology to embrace Thanks to our sponsors 39
Radio Deep Learning Efforts Showcase Presentation
Radio Deep Learning Efforts Showcase Presentation November 2016 hume@vt.edu www.hume.vt.edu Tim O Shea Senior Research Associate Program Overview Program Objective: Rethink fundamental approaches to how
More informationProposers Day Workshop
Proposers Day Workshop Monday, January 23, 2017 @srcjump, #JUMPpdw Cognitive Computing Vertical Research Center Mandy Pant Academic Research Director Intel Corporation Center Motivation Today s deep learning
More informationMonte Carlo integration and event generation on GPU and their application to particle physics
Monte Carlo integration and event generation on GPU and their application to particle physics Junichi Kanzaki (KEK) GPU2016 @ Rome, Italy Sep. 26, 2016 Motivation Increase of amount of LHC data (raw &
More informationROAD RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS
Bulletin of the Transilvania University of Braşov Vol. 10 (59) No. 2-2017 Series I: Engineering Sciences ROAD RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS E. HORVÁTH 1 C. POZNA 2 Á. BALLAGI 3
More informationCUDA-Accelerated Satellite Communication Demodulation
CUDA-Accelerated Satellite Communication Demodulation Renliang Zhao, Ying Liu, Liheng Jian, Zhongya Wang School of Computer and Control University of Chinese Academy of Sciences Outline Motivation Related
More informationLHC Experiments - Trigger, Data-taking and Computing
Physik an höchstenergetischen Beschleunigern WS17/18 TUM S.Bethke, F. Simon V6: Trigger, data taking, computing 1 LHC Experiments - Trigger, Data-taking and Computing data rates physics signals ATLAS trigger
More informationData acquisi*on and Trigger - Trigger -
Experimental Methods in Par3cle Physics (HS 2014) Data acquisi*on and Trigger - Trigger - Lea Caminada lea.caminada@physik.uzh.ch 1 Interlude: LHC opera3on Data rates at LHC Trigger overview Coincidence
More informationGPU ACCELERATED DEEP LEARNING WITH CUDNN
GPU ACCELERATED DEEP LEARNING WITH CUDNN Larry Brown Ph.D. March 2015 AGENDA 1 Introducing cudnn and GPUs 2 Deep Learning Context 3 cudnn V2 4 Using cudnn 2 Introducing cudnn and GPUs 3 HOW GPU ACCELERATION
More informationLecture 23 Deep Learning: Segmentation
Lecture 23 Deep Learning: Segmentation COS 429: Computer Vision Thanks: most of these slides shamelessly adapted from Stanford CS231n: Convolutional Neural Networks for Visual Recognition Fei-Fei Li, Andrej
More informationWhere do we use Machine learning and where do want to improve?
Tracking@LHCb Where do we use Machine learning and where do want to improve? Sascha Stahl, CERN Paul Seyfert, INFN On behalf of LHCb DS@HEP 07.07.2016 The LHCb detector Vertex and track finding Particle
More informationNeural Networks The New Moore s Law
Neural Networks The New Moore s Law Chris Rowen, PhD, FIEEE CEO Cognite Ventures December 216 Outline Moore s Law Revisited: Efficiency Drives Productivity Embedded Neural Network Product Segments Efficiency
More informationGPU-accelerated track reconstruction in the ALICE High Level Trigger
GPU-accelerated track reconstruction in the ALICE High Level Trigger David Rohr for the ALICE Collaboration Frankfurt Institute for Advanced Studies CHEP 2016, San Francisco ALICE at the LHC The Large
More informationChallenges in Transition
Challenges in Transition Keynote talk at International Workshop on Software Engineering Methods for Parallel and High Performance Applications (SEM4HPC 2016) 1 Kazuaki Ishizaki IBM Research Tokyo kiszk@acm.org
More informationData acquisition and Trigger (with emphasis on LHC)
Lecture 2 Data acquisition and Trigger (with emphasis on LHC) Introduction Data handling requirements for LHC Design issues: Architectures Front-end, event selection levels Trigger Future evolutions Conclusion
More information23270: AUGMENTED REALITY FOR NAVIGATION AND INFORMATIONAL ADAS. Sergii Bykov Technical Lead Machine Learning 12 Oct 2017
23270: AUGMENTED REALITY FOR NAVIGATION AND INFORMATIONAL ADAS Sergii Bykov Technical Lead Machine Learning 12 Oct 2017 Product Vision Company Introduction Apostera GmbH with headquarter in Munich, was
More informationComputational Efficiency of the GF and the RMF Transforms for Quaternary Logic Functions on CPUs and GPUs
5 th International Conference on Logic and Application LAP 2016 Dubrovnik, Croatia, September 19-23, 2016 Computational Efficiency of the GF and the RMF Transforms for Quaternary Logic Functions on CPUs
More informationDEEP LEARNING ON RF DATA. Adam Thompson Senior Solutions Architect March 29, 2018
DEEP LEARNING ON RF DATA Adam Thompson Senior Solutions Architect March 29, 2018 Background Information Signal Processing and Deep Learning Radio Frequency Data Nuances AGENDA Complex Domain Representations
More informationAI Application Processing Requirements
AI Application Processing Requirements 1 Low Medium High Sensor analysis Activity Recognition (motion sensors) Stress Analysis or Attention Analysis Audio & sound Speech Recognition Object detection Computer
More informationCALICE Software. Data handling, prototype reconstruction, and physics analysis. Niels Meyer, DESY DESY DV Seminar June 29, 2009
CALICE Software Data handling, prototype reconstruction, and physics analysis Niels Meyer, DESY DESY DV Seminar June 29, 2009 The ILC Well, the next kid around the block (hopefully...) Precision physics
More informationDeep Learning for Human Activity Recognition: A Resource Efficient Implementation on Low-Power Devices
Deep Learning for Human Activity Recognition: A Resource Efficient Implementation on Low-Power Devices Daniele Ravì, Charence Wong, Benny Lo and Guang-Zhong Yang To appear in the proceedings of the IEEE
More informationarxiv: v2 [physics.ins-det] 13 Oct 2015
Preprint typeset in JINST style - HYPER VERSION Level-1 pixel based tracking trigger algorithm for LHC upgrade arxiv:1506.08877v2 [physics.ins-det] 13 Oct 2015 Chang-Seong Moon and Aurore Savoy-Navarro
More informationData acquisition and Trigger (with emphasis on LHC)
Lecture 2! Introduction! Data handling requirements for LHC! Design issues: Architectures! Front-end, event selection levels! Trigger! Upgrades! Conclusion Data acquisition and Trigger (with emphasis on
More informationTrigger Overview. Wesley Smith, U. Wisconsin CMS Trigger Project Manager. DOE/NSF Review April 12, 2000
Overview Wesley Smith, U. Wisconsin CMS Project Manager DOE/NSF Review April 12, 2000 1 TriDAS Main Parameters Level 1 Detector Frontend Readout Systems Event Manager Builder Networks Run Control System
More informationDecoding Brainwave Data using Regression
Decoding Brainwave Data using Regression Justin Kilmarx: The University of Tennessee, Knoxville David Saffo: Loyola University Chicago Lucien Ng: The Chinese University of Hong Kong Mentor: Dr. Xiaopeng
More informationDeep Learning. Dr. Johan Hagelbäck.
Deep Learning Dr. Johan Hagelbäck johan.hagelback@lnu.se http://aiguy.org Image Classification Image classification can be a difficult task Some of the challenges we have to face are: Viewpoint variation:
More informationMicromegas calorimetry R&D
Micromegas calorimetry R&D June 1, 214 The Micromegas R&D pursued at LAPP is primarily intended for Particle Flow calorimetry at future linear colliders. It focuses on hadron calorimetry with large-area
More informationThe Compact Muon Solenoid Experiment. Conference Report. Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland
Available on CMS information server CMS CR -2017/308 The Compact Muon Solenoid Experiment Conference Report Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland 28 September 2017 (v2, 11 October 2017)
More informationOperation and Performance of the ATLAS Level-1 Calorimeter and Level-1 Topological Triggers in Run 2 at the LHC
Operation and Performance of the ATLAS Level-1 Calorimeter and Level-1 Topological Triggers in Run 2 at the LHC Kirchhoff-Institute for Physics (DE) E-mail: sebastian.mario.weber@cern.ch ATL-DAQ-PROC-2017-026
More informationThe LHCb Upgrade BEACH Simon Akar on behalf of the LHCb collaboration
The LHCb Upgrade BEACH 2014 XI International Conference on Hyperons, Charm and Beauty Hadrons! University of Birmingham, UK 21-26 July 2014 Simon Akar on behalf of the LHCb collaboration Outline The LHCb
More information8.882 LHC Physics. Detectors: Muons. [Lecture 11, March 11, 2009] Experimental Methods and Measurements
8.882 LHC Physics Experimental Methods and Measurements Detectors: Muons [Lecture 11, March 11, 2009] Organization Project 1 (charged track multiplicity) no one handed in so far... well deadline is tomorrow
More informationDemystifying Machine Learning
Demystifying Machine Learning By Simon Agius Muscat Software Engineer with RightBrain PyMalta, 19/07/18 http://www.rightbrain.com.mt 0. Talk outline 1. Explain the reasoning behind my talk 2. Defining
More informationDAQ & Electronics for the CW Beam at Jefferson Lab
DAQ & Electronics for the CW Beam at Jefferson Lab Benjamin Raydo EIC Detector Workshop @ Jefferson Lab June 4-5, 2010 High Event and Data Rates Goals for EIC Trigger Trigger must be able to handle high
More informationUse Nvidia Performance Primitives (NPP) in Deep Learning Training. Yang Song
Use Nvidia Performance Primitives (NPP) in Deep Learning Training Yang Song Outline Introduction Function Categories Performance Results Deep Learning Specific Further Information What is NPP? Image+Signal
More informationSemantic Segmentation on Resource Constrained Devices
Semantic Segmentation on Resource Constrained Devices Sachin Mehta University of Washington, Seattle In collaboration with Mohammad Rastegari, Anat Caspi, Linda Shapiro, and Hannaneh Hajishirzi Project
More informationThe design and performance of the ATLAS jet trigger
th International Conference on Computing in High Energy and Nuclear Physics (CHEP) IOP Publishing Journal of Physics: Conference Series () doi:.88/7-696/// he design and performance of the ALAS jet trigger
More informationLHCb Preshower(PS) and Scintillating Pad Detector (SPD): commissioning, calibration, and monitoring
LHCb Preshower(PS) and Scintillating Pad Detector (SPD): commissioning, calibration, and monitoring Eduardo Picatoste Olloqui on behalf of the LHCb Collaboration Universitat de Barcelona, Facultat de Física,
More informationA new single channel readout for a hadronic calorimeter for ILC
A new single channel readout for a hadronic calorimeter for ILC Peter Buhmann, Erika Garutti,, Michael Matysek, Marco Ramilli for the CALICE collaboration University of Hamburg E-mail: sebastian.laurien@desy.de
More informationThe LHCb trigger system: performance and outlook
: performance and outlook Scuola Normale Superiore and INFN Pisa E-mail: simone.stracka@cern.ch The LHCb experiment is a spectrometer dedicated to the study of heavy flavor at the LHC. The rate of proton-proton
More informationThe Compact Muon Solenoid Experiment. Conference Report. Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland
Available on CMS information server CMS CR -2017/349 The Compact Muon Solenoid Experiment Conference Report Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland 09 October 2017 (v4, 10 October 2017)
More informationCan you tell a face from a HEVC bitstream?
Can you tell a face from a HEVC bitstream? Saeed Ranjbar Alvar, Hyomin Choi and Ivan V. Bajić School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada Email: {saeedr,chyomin, ibajic}@sfu.ca
More informationData Quality Monitoring of the CMS Pixel Detector
Data Quality Monitoring of the CMS Pixel Detector 1 * Purdue University Department of Physics, 525 Northwestern Ave, West Lafayette, IN 47906 USA E-mail: petra.merkel@cern.ch We present the CMS Pixel Data
More informationA DAQ readout for the digital HCAL
LC-DET-2004-029 A DAQ readout for the digital HCAL Jean-Claude Brient brient@poly.in2p3.fr Laboratoire Leprince Ringuet Ecole Polytechnique CNRS-IN2P3 Abstract: Considerations on the size of the digital
More informationAutonomous driving made safe
tm Autonomous driving made safe Founder, Bio Celite Milbrandt Austin, Texas since 1998 Founder of Slacker Radio In dash for Tesla, GM, and Ford. 35M active users 2008 Chief Product Officer of RideScout
More informationArtificial Intelligence and Deep Learning
Artificial Intelligence and Deep Learning Cars are now driving themselves (far from perfectly, though) Speaking to a Bot is No Longer Unusual March 2016: World Go Champion Beaten by Machine AI: The Upcoming
More informationThe CMS HGCAL detector for HL-LHC upgrade
on behalf of the CMS collaboration. National Taiwan University E-mail: arnaud.steen@cern.ch The High Luminosity LHC (HL-LHC) will integrate 10 times more luminosity than the LHC, posing significant challenges
More informationTransformation to Artificial Intelligence with MATLAB Roy Lurie, PhD Vice President of Engineering MATLAB Products
Transformation to Artificial Intelligence with MATLAB Roy Lurie, PhD Vice President of Engineering MATLAB Products 2018 The MathWorks, Inc. 1 A brief history of the automobile First Commercial Gas Car
More informationCALICE AHCAL overview
International Workshop on the High Energy Circular Electron-Positron Collider in 2018 CALICE AHCAL overview Yong Liu (IHEP), on behalf of the CALICE collaboration Nov. 13, 2018 CALICE-AHCAL Progress, CEPC
More informationMitigating high energy anomalous signals in the CMS barrel Electromagnetic Calorimeter
Mitigating high energy anomalous signals in the CMS barrel Electromagnetic Calorimeter Summary report Ali Farzanehfar University of Southampton University of Southampton Spike mitigation May 28, 2015 1
More informationCreating Intelligence at the Edge
Creating Intelligence at the Edge Vladimir Stojanović E3S Retreat September 8, 2017 The growing importance of machine learning Page 2 Applications exploding in the cloud Huge interest to move to the edge
More informationThe ATLAS Trigger in Run 2: Design, Menu, and Performance
he ALAS rigger in Run 2: Design, Menu, and Performance amara Vazquez Schroeder, on behalf of the ALAS Collaboration McGill University E-mail: tamara.vazquez.schroeder@cern.ch he ALAS trigger system is
More informationReal-time flavour tagging selection in ATLAS. Lidija Živković, Insttut of Physics, Belgrade
Real-time flavour tagging selection in ATLAS Lidija Živković, Insttut of Physics, Belgrade On behalf of the collaboration Outline Motivation Overview of the trigger b-jet trigger in Run 2 Future Fast TracKer
More informationBen Baker. Sponsored by:
Ben Baker Sponsored by: Background Agenda GPU Computing Digital Image Processing at FamilySearch Potential GPU based solutions Performance Testing Results Conclusions and Future Work 2 CPU vs. GPU Architecture
More informationThe CMS electromagnetic calorimeter barrel upgrade for High-Luminosity LHC
Journal of Physics: Conference Series OPEN ACCESS The CMS electromagnetic calorimeter barrel upgrade for High-Luminosity LHC To cite this article: Philippe Gras and the CMS collaboration 2015 J. Phys.:
More informationDetection and Segmentation. Fei-Fei Li & Justin Johnson & Serena Yeung. Lecture 11 -
Lecture 11: Detection and Segmentation Lecture 11-1 May 10, 2017 Administrative Midterms being graded Please don t discuss midterms until next week - some students not yet taken A2 being graded Project
More informationCMS SLHC Tracker Upgrade: Selected Thoughts, Challenges and Strategies
: Selected Thoughts, Challenges and Strategies CERN Geneva, Switzerland E-mail: marcello.mannelli@cern.ch Upgrading the CMS Tracker for the SLHC presents many challenges, of which the much harsher radiation
More informationLevel-1 Track Trigger R&D. Zijun Xu Peking University
Level-1 Trigger R&D Zijun Xu Peking University 2016-12 1 Level-1 Trigger for CMS Phase2 Upgrade HL-LHC, ~2025 Pileup 140-250 Silicon based Level 1 Trigger Be crucial for trigger objects reconstruction
More informationEnhancing Symmetry in GAN Generated Fashion Images
Enhancing Symmetry in GAN Generated Fashion Images Vishnu Makkapati 1 and Arun Patro 2 1 Myntra Designs Pvt. Ltd., Bengaluru - 560068, India vishnu.makkapati@myntra.com 2 Department of Electrical Engineering,
More informationLHCb Trigger & DAQ Design technology and performance. Mika Vesterinen ECFA High Luminosity LHC Experiments Workshop 8/10/2016
LHCb Trigger & DAQ Design technology and performance Mika Vesterinen ECFA High Luminosity LHC Experiments Workshop 8/10/2016 2 Introduction The LHCb upgrade will allow 5x higher luminosity and with greatly
More informationAttention-based Multi-Encoder-Decoder Recurrent Neural Networks
Attention-based Multi-Encoder-Decoder Recurrent Neural Networks Stephan Baier 1, Sigurd Spieckermann 2 and Volker Tresp 1,2 1- Ludwig Maximilian University Oettingenstr. 67, Munich, Germany 2- Siemens
More informationMATLAB DIGITAL IMAGE/SIGNAL PROCESSING TITLES
MATLAB DIGITAL IMAGE/SIGNAL PROCESSING TITLES -2018 S.NO PROJECT CODE 1 ITIMP01 2 ITIMP02 3 ITIMP03 4 ITIMP04 5 ITIMP05 6 ITIMP06 7 ITIMP07 8 ITIMP08 9 ITIMP09 `10 ITIMP10 11 ITIMP11 12 ITIMP12 13 ITIMP13
More informationSCAI SuperComputing Application & Innovation. Sanzio Bassini October 2017
SCAI SuperComputing Application & Innovation Sanzio Bassini October 2017 The Consortium Private non for Profit Organization Founded in 1969 by Ministry of Public Education now under the control of Ministry
More informationCounterfeit Bill Detection Algorithm using Deep Learning
Counterfeit Bill Detection Algorithm using Deep Learning Soo-Hyeon Lee 1 and Hae-Yeoun Lee 2,* 1 Undergraduate Student, 2 Professor 1,2 Department of Computer Software Engineering, Kumoh National Institute
More informationA MAPS-based readout for a Tera-Pixel electromagnetic calorimeter at the ILC
A MAPS-based readout for a Tera-Pixel electromagnetic calorimeter at the ILC STFC-Rutherford Appleton Laboratory Y. Mikami, O. Miller, V. Rajovic, N.K. Watson, J.A. Wilson University of Birmingham J.A.
More informationHPC + AI. Mike Houston
HPC + AI Mike Houston PRACTICAL DEEP LEARNING EXAMPLES Image Classification, Object Detection, Localization, Action Recognition, Scene Understanding Speech Recognition, Speech Translation, Natural Language
More informationMACHINE LEARNING Games and Beyond. Calvin Lin, NVIDIA
MACHINE LEARNING Games and Beyond Calvin Lin, NVIDIA THE MACHINE LEARNING ERA IS HERE And it is transforming every industry... including Game Development OVERVIEW NVIDIA Volta: An Architecture for Machine
More informationPoS(EPS-HEP2017)476. The CMS Tracker upgrade for HL-LHC. Sudha Ahuja on behalf of the CMS Collaboration
UNESP - Universidade Estadual Paulista (BR) E-mail: sudha.ahuja@cern.ch he LHC machine is planning an upgrade program which will smoothly bring the luminosity to about 5 34 cm s in 228, to possibly reach
More informationMachine Learning Practical Part 2: Group Projects. MLP Lecture 11 MLP Part 2: Group Projects 1
Machine Learning Practical Part 2: Group Projects MLP Lecture 11 MLP Part 2: Group Projects 1 MLP Part 2: Group Projects Steve Renals Machine Learning Practical MLP Lecture 11 24 January 2018 http://www.inf.ed.ac.uk/teaching/courses/mlp/
More informationTrigger and DAQ at the LHC. (Part II)
Trigger and DAQ at the LHC (Part II) Tulika Bose Brown University NEPPSR 2007 August 16, 2007 1 The LHC Trigger Challenge σ mb μb nb pb fb σ inelastic bb W Z t t OBSERVED gg H SM qq qqh SM H SM γγ h γγ
More informationATLAS Muon Trigger and Readout Considerations. Yasuyuki Horii Nagoya University on Behalf of the ATLAS Muon Collaboration
ATLAS Muon Trigger and Readout Considerations Yasuyuki Horii Nagoya University on Behalf of the ATLAS Muon Collaboration ECFA High Luminosity LHC Experiments Workshop - 2016 ATLAS Muon System Overview
More informationDeep Learning Overview
Deep Learning Overview Eliu Huerta Gravity Group gravity.ncsa.illinois.edu National Center for Supercomputing Applications Department of Astronomy University of Illinois at Urbana-Champaign Data Visualization
More informationCSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning Fall 2018/19 6. Convolutional Neural Networks (Some figures adapted from NNDL book) 1 Convolution Neural Networks 1. Convolutional Neural Networks Convolution,
More informationThe LHCb trigger system
IL NUOVO CIMENTO Vol. 123 B, N. 3-4 Marzo-Aprile 2008 DOI 10.1393/ncb/i2008-10523-9 The LHCb trigger system D. Pinci( ) INFN, Sezione di Roma - Rome, Italy (ricevuto il 3 Giugno 2008; pubblicato online
More informationContinuous Gesture Recognition Fact Sheet
Continuous Gesture Recognition Fact Sheet August 17, 2016 1 Team details Team name: ICT NHCI Team leader name: Xiujuan Chai Team leader address, phone number and email Address: No.6 Kexueyuan South Road
More informationReal-time use of GPUs in High-Energy Physics experiments
Real-time use of GPUs in High-Energy Physics experiments Marco S. Sozzi University of Pisa Istituto Nazionale di Fisica Nucleare CERN With: G. Lamanna, J. Pinzino, F. Pantaleo (Pisa U. and CERN) The frontiers
More informationThe Compact Muon Solenoid Experiment. Conference Report. Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland. CMS detector performance.
Available on CMS information server CMS CR -2017/412 The Compact Muon Solenoid Experiment Conference Report Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland 08 November 2017 (v3, 17 November 2017)
More informationDriving Using End-to-End Deep Learning
Driving Using End-to-End Deep Learning Farzain Majeed farza@knights.ucf.edu Kishan Athrey kishan.athrey@knights.ucf.edu Dr. Mubarak Shah shah@crcv.ucf.edu Abstract This work explores the problem of autonomously
More informationStreaming Readout for EIC Experiments
Streaming Readout for EIC Experiments Douglas Hasell Detectors, Computing, and New Technologies Parallel Session EIC User Group Meeting Catholic University of America August 1, 2018 Introduction Goal of
More informationMachine learning and parallelism in the reconstruction of LHCb and its upgrade
Machine learning and parallelism in the reconstruction of LHCb and its upgrade Marian Stahl on behalf of the LHCb collaboration Physikalisches Institut der Universität Heidelberg, Germany E-mail: marian.stahl@cern.ch
More informationCMS Note Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland
Available on CMS information server CMS NOTE 1997/084 The Compact Muon Solenoid Experiment CMS Note Mailing address: CMS CERN, CH-1211 GENEVA 23, Switzerland 29 August 1997 Muon Track Reconstruction Efficiency
More informationStudies of Jet-Track Correlations in PbPb collisions with CMS
Studies of Jet-Track Correlations in collisions with CMS Hard Probes 2015 Dragos Velicanu, MIT for the CMS Collaboration 6/30/2015 Dragos Velicanu 1 Questions this talk will address How are charged particles
More informationLandmark Recognition with Deep Learning
Landmark Recognition with Deep Learning PROJECT LABORATORY submitted by Filippo Galli NEUROSCIENTIFIC SYSTEM THEORY Technische Universität München Prof. Dr Jörg Conradt Supervisor: Marcello Mulas, PhD
More informationChapter 2 Distributed Consensus Estimation of Wireless Sensor Networks
Chapter 2 Distributed Consensus Estimation of Wireless Sensor Networks Recently, consensus based distributed estimation has attracted considerable attention from various fields to estimate deterministic
More informationCS6700: The Emergence of Intelligent Machines. Prof. Carla Gomes Prof. Bart Selman Cornell University
EMERGENCE OF INTELLIGENT MACHINES: CHALLENGES AND OPPORTUNITIES CS6700: The Emergence of Intelligent Machines Prof. Carla Gomes Prof. Bart Selman Cornell University Artificial Intelligence After a distinguished
More informationRecent Advances in Simulation Techniques and Tools
Recent Advances in Simulation Techniques and Tools Yuyang Li, li.yuyang(at)wustl.edu (A paper written under the guidance of Prof. Raj Jain) Download Abstract: Simulation refers to using specified kind
More informationLearning Pixel-Distribution Prior with Wider Convolution for Image Denoising
Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising Peng Liu University of Florida pliu1@ufl.edu Ruogu Fang University of Florida ruogu.fang@bme.ufl.edu arxiv:177.9135v1 [cs.cv]
More informationDevelopment and Test of a Demonstrator for a First-Level Muon Trigger based on the Precision Drift Tube Chambers for ATLAS at HL-LHC
Development and Test of a Demonstrator for a First-Level Muon Trigger based on the Precision Drift Tube Chambers for ATLAS at HL-LHC K. Schmidt-Sommerfeld Max-Planck-Institut für Physik, München K. Schmidt-Sommerfeld,
More informationPost K Supercomputer of. FLAGSHIP 2020 Project. FLAGSHIP 2020 Project. Schedule
Post K Supercomputer of FLAGSHIP 2020 Project The post K supercomputer of the FLAGSHIP2020 Project under the Ministry of Education, Culture, Sports, Science, and Technology began in 2014 and RIKEN has
More informationTable of Contents HOL EMT
Table of Contents Lab Overview - - Machine Learning Workloads in vsphere Using GPUs - Getting Started... 2 Lab Guidance... 3 Module 1 - Machine Learning Apps in vsphere VMs Using GPUs (15 minutes)...9
More informationResearch on Hand Gesture Recognition Using Convolutional Neural Network
Research on Hand Gesture Recognition Using Convolutional Neural Network Tian Zhaoyang a, Cheng Lee Lung b a Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China E-mail address:
More information11/13/18. Introduction to RNNs for NLP. About Me. Overview SHANG GAO
Introduction to RNNs for NLP SHANG GAO About Me PhD student in the Data Science and Engineering program Took Deep Learning last year Work in the Biomedical Sciences, Engineering, and Computing group at
More informationBackground suppression with neural networks at the Belle II trigger
Background suppression with neural networks at the Belle II trigger Sebastian Skambraks Max-Planck-Institut für Physik March 28, 2017 Outline Introduction Motivation Trigger NeuroTrigger Background Neuro
More informationMobile Cognitive Indoor Assistive Navigation for the Visually Impaired
1 Mobile Cognitive Indoor Assistive Navigation for the Visually Impaired Bing Li 1, Manjekar Budhai 2, Bowen Xiao 3, Liang Yang 1, Jizhong Xiao 1 1 Department of Electrical Engineering, The City College,
More information신경망기반자동번역기술. Konkuk University Computational Intelligence Lab. 김강일
신경망기반자동번역기술 Konkuk University Computational Intelligence Lab. http://ci.konkuk.ac.kr kikim01@kunkuk.ac.kr 김강일 Index Issues in AI and Deep Learning Overview of Machine Translation Advanced Techniques in
More informationQ1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4 Q1-2 Q3-4. Final design and pre-production.
high-granularity sfcal Performance simulation, option selection and R&D Figure 41. Overview of the time-line and milestones for the implementation of the high-granularity sfcal. tooling and cryostat modification,
More informationPrototyping Vision-Based Classifiers in Constrained Environments
Prototyping Vision-Based Classifiers in Constrained Environments Ted Hromadka 1 and Cameron Hunt 2 1, 2 SOFWERX (DEFENSEWERX, Inc.) Presented at GTC 2018 Company Overview SM UNCLASSIFIED 2 Capabilities
More informationCreating the Right Environment for Machine Learning Codesign. Cliff Young, Google AI
Creating the Right Environment for Machine Learning Codesign Cliff Young, Google AI 1 Deep Learning has Reinvigorated Hardware GPUs AlexNet, Speech. TPUs Many Google applications: AlphaGo and Translate,
More informationIntroduction to Machine Learning
Introduction to Machine Learning Deep Learning Barnabás Póczos Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio Geoffrey Hinton Yann LeCun 2
More informationTarget detection in side-scan sonar images: expert fusion reduces false alarms
Target detection in side-scan sonar images: expert fusion reduces false alarms Nicola Neretti, Nathan Intrator and Quyen Huynh Abstract We integrate several key components of a pattern recognition system
More informationCMS electron and _ photon performance at s = 13 TeV. Francesco Micheli on behalf of CMS Collaboration
CMS electron and _ photon performance at s = 13 TeV on behalf of CMS Collaboration 2 Electrons and Photons @ CMS Electrons and photons are crucial for CMS physics program: SM precision physics, Higgs coupling
More informationTOOLS & PROCESSORS FOR COMPUTER VISION. Selected Results from the Embedded Vision Alliance s Fall 2017 Computer Vision Developer Survey
TOOLS & PROCESSORS FOR COMPUTER VISION Selected Results from the Embedded Vision Alliance s Fall 2017 Computer Vision Developer Survey ABOUT THE EMBEDDED VISION ALLIANCE EXECUTIVE SUMMA Y Since 2015, the
More information