Exploiting Hidden Layer Modular Redundancy for Fault-Tolerance in Neural Network Accelerators
|
|
- Julia Booth
- 6 years ago
- Views:
Transcription
1 Exploiting Hidden Layer Modular Redundancy for Fault-Tolerance in Neural Network Accelerators Schuyler Eldridge Ajay Joshi Department of Electrical and Computer Engineering, Boston University January 30, 2015 This work was supported by a NASA Office of the Chief Technologist s Space Technology Research Fellowship. schuye@bu.edu 30 Jan /12
2 Motivation Leveraging CMOS Scaling for Improved Performance is Becoming Increasingly Hard Contributing factors making it difficult include: Fixed power budgets An eventual slowdown of Moore s Law Computer engineers increasingly turn towards alternative designs Alternative Designs As an alternative, others are investigating general and special purpose accelerators One actively researched accelerator architecture is that of neural network accelerators schuye@bu.edu 30 Jan /12
3 Artificial Neural Networks Output Hidden Input H 1 H 2... H h bias I 1 X 1 Y 1 O 1... O o... I i bias X i Y o Figure: Two-layer neural network with i h o nodes. Artificial Neural Network Directed graph of neurons Edges between neurons are weighted Use in Applications Machine Learning Big Data Approximate Computing State Prediction schuye@bu.edu 30 Jan /12
4 Neural Networks and Fault-Tolerance The Brain is Fault-Tolerant! Ergo neural networks are fault-tolerant This isn t generally the case! Do Neural Networks have the potential for Fault-Tolerance? Neural networks have a redundant structure There are multiple paths from input to output Regression tasks often approximate smooth functions Small changes in inputs or internal computations may only cause small changes in the output However, there is no implicit guarantee of fault-tolerance unless you train a neural network to specifically demonstrate those properties schuye@bu.edu 30 Jan /12
5 N-MR Technique Y 1 Y 2 O 1 O 2 H 1 H 2 bias Steps for Amount of Redundancy N 1 Replicate each hidden neuron N times 2 Replicate each hidden neuron connection for each new neuron I 1 I 2 bias 3 Multiply all connection weights by 1 /N X 1 X 2 Figure: N-MR-1 schuye@bu.edu 30 Jan /12
6 N-MR Technique Y 1 Y 2 Y 1 Y 2 O 1 O 2 O 1 O 2 H 1 H 2 bias H 1 H 2 H 3 H 4 bias I 1 I 2 bias I 1 I 2 bias X 1 X 2 X 1 X 2 Figure: N-MR-1 Figure: N-MR-2 schuye@bu.edu 30 Jan /12
7 N-MR Technique Y 1 Y 2 Y 1 Y 2 O 1 O 2 O 1 O 2 H 1 H 2 bias H 1 H 2 H 3 H 4 H 5 H 6 bias I 1 I 2 bias I 1 I 2 bias X 1 X 2 X 1 X 2 Figure: N-MR-1 Figure: N-MR-3 schuye@bu.edu 30 Jan /12
8 N-MR Technique Y 1 Y 2 Y 1 Y 2 O 1 O 2 O 1 O 2 H 1 H 2 bias H 1 H 2 H 3 H 4 H 5 H 6 H 7 H 8 bias I 1 I 2 bias I 1 I 2 bias X 1 X 2 X 1 X 2 Figure: N-MR-1 Figure: N-MR-4 schuye@bu.edu 30 Jan /12
9 Neural Network Accelerator Architecture NN Config and Data Storage Unit Intermediate Storage Control Core Communication Figure: Block diagram of our neural network accelerator Basic Operation in a Multicore Environment Threads communicate neural network computation requests to this accelerator The accelerator allocates processing elements (s) to compute the outputs of all pending requests schuye@bu.edu 30 Jan /12
10 Neural Network Accelerator Architecture NN Config and Data Storage Unit Intermediate Storage Control Core Communication Figure: Block diagram of our neural network accelerator Basic Operation in a Multicore Environment Threads communicate neural network computation requests to this accelerator The accelerator allocates processing elements (s) to compute the outputs of all pending requests schuye@bu.edu 30 Jan /12
11 Neural Network Accelerator Architecture NN Config and Data Storage Unit Intermediate Storage Control Core Communication Figure: Block diagram of our neural network accelerator Basic Operation in a Multicore Environment Threads communicate neural network computation requests to this accelerator The accelerator allocates processing elements (s) to compute the outputs of all pending requests schuye@bu.edu 30 Jan /12
12 Neural Network Accelerator Architecture NN Config and Data Storage Unit Intermediate Storage Control Core Communication Figure: Block diagram of our neural network accelerator Basic Operation in a Multicore Environment Threads communicate neural network computation requests to this accelerator The accelerator allocates processing elements (s) to compute the outputs of all pending requests schuye@bu.edu 30 Jan /12
13 Neural Network Accelerator Architecture NN Config and Data Storage Unit Intermediate Storage Control Core Communication Figure: Block diagram of our neural network accelerator Basic Operation in a Multicore Environment Threads communicate neural network computation requests to this accelerator The accelerator allocates processing elements (s) to compute the outputs of all pending requests schuye@bu.edu 30 Jan /12
14 Evaluation Overview Table: Evaluated neural networks and their topologies Application NN Topology Description blackscholes (b) [1] Financial option pricing rsa (r) [2] Brute-force prime factorization sobel (s) [1] Sobel filter Methodology We vary the amount of N-MR for the applications in Table 1 running on our NN accelerator architecture We introduce a random fault into a neuron and measure the accuracy and latency R. St. Amant et al., General-purpose code acceleration with limited-precision analog computation, in ISCA, 2014, pp A. Waterland et al., Asc: Automatically scalable computation, in ASPLOS. ACM, 2014, pp schuye@bu.edu 30 Jan /12
15 Evaluation Normalized Latency Normalized Latency Amount of N-MR blackscholes sobel rsa Linear Baseline Figure: Latency normalized to N-MR-1 Latency Scaling with N-MR Work, where work is the number of edges to compute, scale with N-MR However, latency scales sublinearly for our accelerator Increasing N-MR means more work, but also more efficient use of the accelerator schuye@bu.edu 30 Jan /12
16 Evaluation Accuracy Percentage Error Increase Amount of N-MR Normalized Accuracy Amount of N-MR blackscholes (MSE) rsa (% correct) sobel (MSE) Figure: Left: percentage accuracy difference, Right: accuracy normalized to N-MR-1 Accuracy and N-MR Generally, accuracy improves with increasing N-MR schuye@bu.edu 30 Jan /12
17 Evaluation Combined Metrics Normalized EDP Amount of N-MR Cost of N-MR We evaluate the cost using Energy-Delay product (EDP) A high cost as N-MR increases both energy and delay blackscholes rsa sobel Figure: Energy-Delay Product (EDP) for varying N-MR schuye@bu.edu 30 Jan /12
18 Discussion and Conclusion An Initial Approach As neural network accelerators become mainstream, approaches to improve their fault-tolerance will have increased value N-MR is a preliminary step to leverage the potential for fault-tolerance in neural networks Other approaches do exist: Training with faults Splitting important neurons and pruning unimportant ones Future Directions Varying N-MR at run-time Faults are currently assumed to be intermittent, but by varying internal structure and enforcing scheduling neurons on different s, a more robust approach can be developed Run-time splitting of important nodes or not computing unimportant nodes schuye@bu.edu 30 Jan /12
19 Summary and Questions Figure: Latency, accuracy, and combined metrics Y 1 Y 2 O 1 O 2 H 1 H 2 bias I 1 X 1 I 2 X 2 bias Figure: A two-layer NN Intermediate Storage NN Config and Data Storage Unit Control Core Communication Figure: NN accelerator architecture schuye@bu.edu 30 Jan /12
Neural Network based Energy-Efficient Fault Tolerant Architect
Neural Network based Energy-Efficient Fault Tolerant Architectures and Accelerators University of Rochester February 7, 2013 References Flexible Error Protection for Energy Efficient Reliable Architectures
More informationNeural Networks as Function Primitives
Neural Networks as Function Primitives Software/Hardware Support with X-FILES/DANA Schuyler Eldridge 1 Tommy Unger 2 Marcia Sahaya Louis 1 Amos Waterland 3 Margo Seltzer 3 Jonathan Appavoo 2 Ajay Joshi
More informationDNN ENGINE: A 16nm Sub-uJ DNN Inference Accelerator for the Embedded Masses
DNN ENGINE: A 16nm Sub-uJ DNN Inference Accelerator for the Embedded Masses Paul N. Whatmough 1,2 S. K. Lee 2, N. Mulholland 2, P. Hansen 2, S. Kodali 3, D. Brooks 2, G.-Y. Wei 2 1 ARM Research, Boston,
More informationLECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS
LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Neural Networks Classifier Introduction INPUT: classification data, i.e. it contains an classification (class) attribute. WE also say that the class
More informationIndex. Springer Nature Switzerland AG 2019 B. Moons et al., Embedded Deep Learning,
Index A Algorithmic noise tolerance (ANT), 93 94 Application specific instruction set processors (ASIPs), 115 116 Approximate computing application level, 95 circuits-levels, 93 94 DAS and DVAS, 107 110
More informationBridging Analog Neuromorphic and Digital von Neumann Computing
Bridging Analog Neuromorphic and Digital von Neumann Computing Amir Yazdanbakhsh, Bradley Thwaites Advisors: Hadi Esmaeilzadeh and Doug Burger Qualcomm Mentors: Manu Rastogiand Girish Varatkar Alternative
More informationWrite a technical report Present your results Write a workshop/conference paper (optional) Could be a real system, simulation and/or theoretical
Identify a problem Review approaches to the problem Propose a novel approach to the problem Define, design, prototype an implementation to evaluate your approach Could be a real system, simulation and/or
More informationCHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN)
128 CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN) Various mathematical techniques like regression analysis and software tools have helped to develop a model using equation, which
More informationA Matlab Tool for Analyzing and Improving Fault Tolerance of Artificial Neural Networks
A Matlab Tool for Analyzing and Improving Fault Tolerance of Artificial Neural Networks Rui Borralho*. Pedro Fontes*. Ana Antunes*. Fernando Morgado Dias**. *Escola Superior de Tecnologia de Setúbal do
More informationUsing Process-Level Redundancy to Exploit Multiple Cores for Transient Fault Tolerance
Using Process-Level Redundancy to Exploit Multiple Cores for Transient Fault Tolerance Outline Introduction and Motivation Software-centric Fault Detection Process-Level Redundancy Experimental Results
More informationHardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?)
SKIP - May 2004 Hardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?) S. G. Hohmann, Electronic Vision(s), Kirchhoff Institut für Physik, Universität Heidelberg Hardware Neuronale Netzwerke
More informationKnowledge-Defined Networking: Towards Self-Driving Networks
Knowledge-Defined Networking: Towards Self-Driving Networks Albert Cabellos (UPC/BarcelonaTech, Spain) albert.cabellos@gmail.com 2nd IFIP/IEEE International Workshop on Analytics for Network and Service
More informationTowards General-Purpose Neural Network Computing
Towards General-Purpose Neural Network Computing Schuyler Eldridge, Jonathan Appavoo, and Ajay Joshi Department of Electrical and Computer Engineering Department of Computer Science Boston University Boston,
More informationUse of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine
Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine M. Vijay Kumar Reddy 1 1 Department of Mechanical Engineering, Annamacharya Institute of Technology and Sciences,
More informationA Software Architecture for Progressive Scanning of On-line Communities
A Software Architecture for Progressive Scanning of On-line Communities Roberto Baldoni, Fabrizio d Amore, Massimo Mecella, Daniele Ucci Sapienza Università di Roma, Italy Motivations On-line communities
More informationNeural Network-Based Accelerators for Transcendental Function Approximation
Neural Network-Based Accelerators for Transcendental Function Approximation Schuyler Eldridge, Florian Raudies, David Zou, and Ajay Joshi Department of Electrical and Computer Engineering, Boston University
More informationModel learning for robot control: a survey
Model learning for robot control: a survey Duy Nguyen-Tuong, Jan Peters 2011 Presented by Evan Beachly 1 Motivation Robots that can learn how their motors move their body Complexity Unanticipated Environments
More informationPARALLEL TRAINING OF NEURAL NETWORKS FOR SPEECH RECOGNITION
PARALLEL TRAINING OF NEURAL NETWORKS FOR SPEECH RECOGNITION Stanislav Kontár Speech@FIT, Dept. of Computer Graphics and Multimedia, FIT, BUT, Brno, Czech Republic E-mail: xkonta00@stud.fit.vutbr.cz In
More informationClustering algorithms and autoencoders for anomaly detection
Clustering algorithms and autoencoders for anomaly detection Alessia Saggio Lunch Seminars and Journal Clubs Université catholique de Louvain, Belgium 3rd March 2017 a Outline Introduction Clustering algorithms
More informationFast or furious? - User analysis of SF Express Inc
CS 229 PROJECT, DEC. 2017 1 Fast or furious? - User analysis of SF Express Inc Gege Wen@gegewen, Yiyuan Zhang@yiyuan12, Kezhen Zhao@zkz I. MOTIVATION The motivation of this project is to predict the likelihood
More informationAnalyzing Performance Asymmetric Multicore Processors for Latency Sensitive Datacenter Applications
Analyzing erformance Asymmetric Multicore rocessors for Latency Sensitive Datacenter Applications Vishal Gupta Georgia Institute of Technology vishal@cc.gatech.edu Ripal Nathuji Microsoft Research ripaln@microsoft.com
More informationPouya Kousha Fall 2018 CSE 5194 Prof. DK Panda
Pouya Kousha Fall 2018 CSE 5194 Prof. DK Panda 1 Observe novel applicability of DL techniques in Big Data Analytics. Applications of DL techniques for common Big Data Analytics problems. Semantic indexing
More informationSimulation of Zhang Suen Algorithm using Feed- Forward Neural Networks
Simulation of Zhang Suen Algorithm using Feed- Forward Neural Networks Ritika Luthra Research Scholar Chandigarh University Gulshan Goyal Associate Professor Chandigarh University ABSTRACT Image Skeletonization
More informationFrequent Item Set using Apriori and Map Reduce algorithm: An Application in Inventory Management
Frequent Item Set using Apriori and Map Reduce algorithm: An Application in Inventory Management Kranti Patil 1, Jayashree Fegade 2, Diksha Chiramade 3, Srujan Patil 4, Pradnya A. Vikhar 5 1,2,3,4,5 KCES
More informationNIGHTs-WATCH. A Cache-Based Side-Channel Intrusion Detector using Hardware Performance Counters
NIGHTs-WATCH A Cache-Based Side-Channel Intrusion Detector using Hardware Performance Counters Maria Mushtaq, Ayaz Akram, Khurram Bhatti, Maham Chaudhry, Vianney Lapotre, Guy Gogniat Contact: khurram.bhatti@itu.edu.pk
More informationUsing FPGAs as Microservices
Using FPGAs as Microservices David Ojika, Ann Gordon-Ross, Herman Lam, Bhavesh Patel, Gaurav Kaul, Jayson Strayer (University of Florida, DELL EMC, Intel Corporation) The 9 th Workshop on Big Data Benchmarks,
More informationThe Design and Implementation of a Low-Latency On-Chip Network
The Design and Implementation of a Low-Latency On-Chip Network Robert Mullins 11 th Asia and South Pacific Design Automation Conference (ASP-DAC), Jan 24-27 th, 2006, Yokohama, Japan. Introduction Current
More informationAR-SMT: A Microarchitectural Approach to Fault Tolerance in Microprocessors
AR-SMT: A Microarchitectural Approach to Fault Tolerance in Microprocessors Computer Sciences Department University of Wisconsin Madison http://www.cs.wisc.edu/~ericro/ericro.html ericro@cs.wisc.edu High-Performance
More informationDEEP LEARNING ACCELERATOR UNIT WITH HIGH EFFICIENCY ON FPGA
DEEP LEARNING ACCELERATOR UNIT WITH HIGH EFFICIENCY ON FPGA J.Jayalakshmi 1, S.Ali Asgar 2, V.Thrimurthulu 3 1 M.tech Student, Department of ECE, Chadalawada Ramanamma Engineering College, Tirupati Email
More informationAdaptive Regularization. in Neural Network Filters
Adaptive Regularization in Neural Network Filters Course 0455 Advanced Digital Signal Processing May 3 rd, 00 Fares El-Azm Michael Vinther d97058 s97397 Introduction The bulk of theoretical results and
More informationM.Tech Student, Department of ECE, S.V. College of Engineering, Tirupati, India
International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume 3 Issue 5 ISSN : 2456-3307 High Performance Scalable Deep Learning Accelerator
More informationLecture 17: Neural Networks and Deep Learning. Instructor: Saravanan Thirumuruganathan
Lecture 17: Neural Networks and Deep Learning Instructor: Saravanan Thirumuruganathan Outline Perceptron Neural Networks Deep Learning Convolutional Neural Networks Recurrent Neural Networks Auto Encoders
More informationAccelerated tokamak transport simulations
Accelerated tokamak transport simulations via Neural-Network based regression of TGLF turbulent energy, particle and momentum fluxes by Teobaldo Luda 1 O. Meneghini 2, S. Smith 2, G. Staebler 2 J. Candy
More informationECE 588/688 Advanced Computer Architecture II
ECE 588/688 Advanced Computer Architecture II Instructor: Alaa Alameldeen alaa@ece.pdx.edu Fall 2009 Portland State University Copyright by Alaa Alameldeen and Haitham Akkary 2009 1 When and Where? When:
More informationLearning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li
Learning to Match Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li 1. Introduction The main tasks in many applications can be formalized as matching between heterogeneous objects, including search, recommendation,
More informationARCHITECTURE DESIGN FOR SOFT ERRORS
ARCHITECTURE DESIGN FOR SOFT ERRORS Shubu Mukherjee ^ШВпШшр"* AMSTERDAM BOSTON HEIDELBERG LONDON NEW YORK OXFORD PARIS SAN DIEGO T^"ТГПШГ SAN FRANCISCO SINGAPORE SYDNEY TOKYO ^ P f ^ ^ ELSEVIER Morgan
More informationAlgorithm-Data Driven Optimization of Adaptive Communication Networks
Chair of Communication Networks Department of Electrical and Computer Engineering Technical University of Munich Algorithm-Data Driven Optimization of Adaptive Communication Networks IEEE ICNP 2017, ML@AI
More informationPRIME: A Novel Processing-in-memory Architecture for Neural Network Computation in ReRAM-based Main Memory
Scalable and Energy-Efficient Architecture Lab (SEAL) PRIME: A Novel Processing-in-memory Architecture for Neural Network Computation in -based Main Memory Ping Chi *, Shuangchen Li *, Tao Zhang, Cong
More informationFast and Concurrent RDF Queries with RDMA-Based Distributed Graph Exploration
Fast and Concurrent RDF Queries with RDMA-Based Distributed Graph Exploration JIAXIN SHI, YOUYANG YAO, RONG CHEN, HAIBO CHEN, FEIFEI LI PRESENTED BY ANDREW XIA APRIL 25, 2018 Wukong Overview of Wukong
More informationTETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory
TETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory Mingyu Gao, Jing Pu, Xuan Yang, Mark Horowitz, Christos Kozyrakis Stanford University Platform Lab Review Feb 2017 Deep Neural
More informationImage Compression: An Artificial Neural Network Approach
Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and
More informationSNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training
SNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training John Sum and Kevin Ho Institute of Technology Management, National Chung Hsing University Taichung 4, Taiwan. pfsum@nchu.edu.tw
More informationValue-driven Synthesis for Neural Network ASICs
Value-driven Synthesis for Neural Network ASICs Zhiyuan Yang University of Maryland, College Park zyyang@umd.edu ABSTRACT In order to enable low power and high performance evaluation of neural network
More informationCS 61C: Great Ideas in Computer Architecture. MapReduce
CS 61C: Great Ideas in Computer Architecture MapReduce Guest Lecturer: Justin Hsia 3/06/2013 Spring 2013 Lecture #18 1 Review of Last Lecture Performance latency and throughput Warehouse Scale Computing
More informationZHT: Const Eventual Consistency Support For ZHT. Group Member: Shukun Xie Ran Xin
ZHT: Const Eventual Consistency Support For ZHT Group Member: Shukun Xie Ran Xin Outline Problem Description Project Overview Solution Maintains Replica List for Each Server Operation without Primary Server
More informationParallelization and Synchronization. CS165 Section 8
Parallelization and Synchronization CS165 Section 8 Multiprocessing & the Multicore Era Single-core performance stagnates (breakdown of Dennard scaling) Moore s law continues use additional transistors
More informationEnergy-Efficiency Prediction of Multithreaded Workloads on Heterogeneous Composite Cores Architectures using Machine Learning Techniques
Energy-Efficiency Prediction of Multithreaded Workloads on Heterogeneous Composite Cores Architectures using Machine Learning Techniques Hossein Sayadi Department of Electrical and Computer Engineering
More informationEnergy Consumption in Mobile Phones: A Measurement Study and Implications for Network Applications (IMC09)
Energy Consumption in Mobile Phones: A Measurement Study and Implications for Network Applications (IMC09) Niranjan Balasubramanian Aruna Balasubramanian Arun Venkataramani University of Massachusetts
More informationCSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning Fall 2018/19 7. Recurrent Neural Networks (Some figures adapted from NNDL book) 1 Recurrent Neural Networks 1. Recurrent Neural Networks (RNNs) 2. RNN Training
More informationApplication-Aware SDN Routing for Big-Data Processing
Application-Aware SDN Routing for Big-Data Processing Evaluation by EstiNet OpenFlow Network Emulator Director/Prof. Shie-Yuan Wang Institute of Network Engineering National ChiaoTung University Taiwan
More informationCore. Error Predictor. Figure 1: Architectural overview of our quality control approach. Approximate Accelerator. Precise.
Prediction-Based Quality Control for Approximate Accelerators Divya Mahajan Amir Yazdanbakhsh Jongse Park Bradley Thwaites Hadi Esmaeilzadeh Georgia Institute of Technology Abstract Approximate accelerators
More information5 Learning hypothesis classes (16 points)
5 Learning hypothesis classes (16 points) Consider a classification problem with two real valued inputs. For each of the following algorithms, specify all of the separators below that it could have generated
More informationCS6303 Computer Architecture Regulation 2013 BE-Computer Science and Engineering III semester 2 MARKS
CS6303 Computer Architecture Regulation 2013 BE-Computer Science and Engineering III semester 2 MARKS UNIT-I OVERVIEW & INSTRUCTIONS 1. What are the eight great ideas in computer architecture? The eight
More informationCOMPUTATIONAL INTELLIGENCE SEW (INTRODUCTION TO MACHINE LEARNING) SS18. Lecture 6: k-nn Cross-validation Regularization
COMPUTATIONAL INTELLIGENCE SEW (INTRODUCTION TO MACHINE LEARNING) SS18 Lecture 6: k-nn Cross-validation Regularization LEARNING METHODS Lazy vs eager learning Eager learning generalizes training data before
More informationIdentification of Multisensor Conversion Characteristic Using Neural Networks
Sensors & Transducers 3 by IFSA http://www.sensorsportal.com Identification of Multisensor Conversion Characteristic Using Neural Networks Iryna TURCHENKO and Volodymyr KOCHAN Research Institute of Intelligent
More informationSimplifying the Datacenter with Hyper-Convergence. Bob O Donnell, Founder and Chief Analyst
Simplifying the Datacenter with Hyper-Convergence Bob O Donnell, Founder and Chief Analyst Agenda Hyper-Converged Infrastructure (HCI) Definition The Current IT Landscape Benefits of HCI Real-World Challenges
More informationData Mining on Agriculture Data using Neural Networks
Data Mining on Agriculture Data using Neural Networks June 26th, 28 Outline Data Details Data Overview precision farming cheap data collection GPS-based technology divide field into small-scale parts treat
More informationMapReduce. U of Toronto, 2014
MapReduce U of Toronto, 2014 http://www.google.org/flutrends/ca/ (2012) Average Searches Per Day: 5,134,000,000 2 Motivation Process lots of data Google processed about 24 petabytes of data per day in
More informationAcoustic to Articulatory Mapping using Memory Based Regression and Trajectory Smoothing
Acoustic to Articulatory Mapping using Memory Based Regression and Trajectory Smoothing Samer Al Moubayed Center for Speech Technology, Department of Speech, Music, and Hearing, KTH, Sweden. sameram@kth.se
More informationLinear Regression Optimization
Gradient Descent Linear Regression Optimization Goal: Find w that minimizes f(w) f(w) = Xw y 2 2 Closed form solution exists Gradient Descent is iterative (Intuition: go downhill!) n w * w Scalar objective:
More informationSeismic regionalization based on an artificial neural network
Seismic regionalization based on an artificial neural network *Jaime García-Pérez 1) and René Riaño 2) 1), 2) Instituto de Ingeniería, UNAM, CU, Coyoacán, México D.F., 014510, Mexico 1) jgap@pumas.ii.unam.mx
More informationMikko Ohvo Business Development Manager Nokia
HW Solution for distributed edge data centers Mikko Ohvo Business Development Manager Nokia HW Solution for distributed edge data centers Introduction In this presentation Nokia will share design considerations
More informationONOS OVERVIEW. Architecture, Abstractions & Application
ONOS OVERVIEW Architecture, Abstractions & Application WHAT IS ONOS? Open Networking Operating System (ONOS) is an open source SDN network operating system (controller). Mission: to enable Service Providers
More informationFOR HIERARCHICAL SIGNAL FLOW GRAPHS
26th ACM/IEEE Design Automation Conference Paper 2.3 A SCHEDULING AND RESOURCE ALLOCATION ALGORITHM FOR HIERARCHICAL SIGNAL FLOW GRAPHS Miodrag Potkonjak and Jan Rabaey Department 0/ EECS University o/california,
More informationINTELLIGENT SEISMIC STRUCTURAL HEALTH MONITORING SYSTEM FOR THE SECOND PENANG BRIDGE OF MALAYSIA
INTELLIGENT SEISMIC STRUCTURAL HEALTH MONITORING SYSTEM FOR THE SECOND PENANG BRIDGE OF MALAYSIA Reni Suryanita Faculty of Engineering Civil Engineering Department University of Riau, Pekanbaru reni.suryanita@lecturer.unri.ac.id
More informationFault Tolerant and Secure Architectures for On Chip Networks With Emerging Interconnect Technologies. Mohsin Y Ahmed Conlan Wesson
Fault Tolerant and Secure Architectures for On Chip Networks With Emerging Interconnect Technologies Mohsin Y Ahmed Conlan Wesson Overview NoC: Future generation of many core processor on a single chip
More informationThe Procedure Proposal of Manufacturing Systems Management by Using of Gained Knowledge from Production Data
The Procedure Proposal of Manufacturing Systems Management by Using of Gained Knowledge from Production Data Pavol Tanuska Member IAENG, Pavel Vazan, Michal Kebisek, Milan Strbo Abstract The paper gives
More informationNIC FastICA Implementation
NIC-TR-2004-016 NIC FastICA Implementation Purpose This document will describe the NIC FastICA implementation. The FastICA algorithm was initially created and implemented at The Helsinki University of
More informationSESDAD. Desenvolvimento de Aplicações Distribuídas Project (IST/DAD): MEIC-A / MEIC-T / METI. October 1, 2015
SESDAD Desenvolvimento de Aplicações Distribuídas Project - 2015-16 (IST/DAD): MEIC-A / MEIC-T / METI October 1, 2015 Abstract The DAD project aims at implementing a simplified (and therefore far from
More informationCS6220: DATA MINING TECHNIQUES
CS6220: DATA MINING TECHNIQUES Image Data: Classification via Neural Networks Instructor: Yizhou Sun yzsun@ccs.neu.edu November 19, 2015 Methods to Learn Classification Clustering Frequent Pattern Mining
More informationA Scalable, Commodity Data Center Network Architecture
A Scalable, Commodity Data Center Network Architecture B Y M O H A M M A D A L - F A R E S A L E X A N D E R L O U K I S S A S A M I N V A H D A T P R E S E N T E D B Y N A N X I C H E N M A Y. 5, 2 0
More informationSIMPLIFY IT. Transform IT with VCE and Vblock TM Infrastructure Platforms. Copyright 2011 VCE Company LLC, All rights reserved.
SIMPLIFY IT Transform IT with VCE and Vblock TM Infrastructure Platforms I.T. BUDGET DILEMMA 73% Maintain 27% Invest Source: Forrester Research, Inc., IT Budget Allocations: Planning For 2011, December
More informationVisual object classification by sparse convolutional neural networks
Visual object classification by sparse convolutional neural networks Alexander Gepperth 1 1- Ruhr-Universität Bochum - Institute for Neural Dynamics Universitätsstraße 150, 44801 Bochum - Germany Abstract.
More informationNeural Computer Architectures
Neural Computer Architectures 5kk73 Embedded Computer Architecture By: Maurice Peemen Date: Convergence of different domains Neurobiology Applications 1 Constraints Machine Learning Technology Innovations
More informationFOR A WALL STREET INVESTMENT BANK JOSH WEST SOLUTIONS ARCHITECT RED HAT FINANCIAL SERVICES
TRADING PLATFORM ARCHITECTURE FOR A WALL STREET INVESTMENT BANK JOSH WEST SOLUTIONS ARCHITECT RED HAT FINANCIAL SERVICES USE CASE ORDER PROCESSING AND MARKET DELIVERY EMERGENCY ORDER ENTRY UPSTREAM ORDER
More informationIntroduction to ANSYS DesignXplorer
Lecture 4 14. 5 Release Introduction to ANSYS DesignXplorer 1 2013 ANSYS, Inc. September 27, 2013 s are functions of different nature where the output parameters are described in terms of the input parameters
More informationHigh Performance Computing
High Performance Computing 9th Lecture 2016/10/28 YUKI ITO 1 Selected Paper: vdnn: Virtualized Deep Neural Networks for Scalable, MemoryEfficient Neural Network Design Minsoo Rhu, Natalia Gimelshein, Jason
More informationComputer Architecture: Parallel Processing Basics. Prof. Onur Mutlu Carnegie Mellon University
Computer Architecture: Parallel Processing Basics Prof. Onur Mutlu Carnegie Mellon University Readings Required Hill, Jouppi, Sohi, Multiprocessors and Multicomputers, pp. 551-560 in Readings in Computer
More informationCS229 Final Project: Predicting Expected Response Times
CS229 Final Project: Predicting Expected Email Response Times Laura Cruz-Albrecht (lcruzalb), Kevin Khieu (kkhieu) December 15, 2017 1 Introduction Each day, countless emails are sent out, yet the time
More informationDo we need a crystal ball for task migration?
Do we need a crystal ball for task migration? Brandon {Myers,Holt} University of Washington bdmyers@cs.washington.edu 1 Large data sets Data 2 Spread data Data.1 Data.2 Data.3 Data.4 Data.0 Data.1 Data.2
More informationClassification Lecture Notes cse352. Neural Networks. Professor Anita Wasilewska
Classification Lecture Notes cse352 Neural Networks Professor Anita Wasilewska Neural Networks Classification Introduction INPUT: classification data, i.e. it contains an classification (class) attribute
More informationAchieving Lightweight Multicast in Asynchronous Networks-on-Chip Using Local Speculation
Achieving Lightweight Multicast in Asynchronous Networks-on-Chip Using Local Speculation Kshitij Bhardwaj Dept. of Computer Science Columbia University Steven M. Nowick 2016 ACM/IEEE Design Automation
More informationJVM Performance Study Comparing Java HotSpot to Azul Zing Using Red Hat JBoss Data Grid
JVM Performance Study Comparing Java HotSpot to Azul Zing Using Red Hat JBoss Data Grid Legal Notices JBoss, Red Hat and their respective logos are trademarks or registered trademarks of Red Hat, Inc.
More informationData-Centric Architecture for Space Systems
Data-Centric Architecture for Space Systems 3 rd Annual Workshop on Flight Software, Nov 5, 2009 The Real-Time Middleware Experts Rajive Joshi, Ph.D. Real-Time Innovations Our goals are the same but not
More informationProblem 1: Complexity of Update Rules for Logistic Regression
Case Study 1: Estimating Click Probabilities Tackling an Unknown Number of Features with Sketching Machine Learning for Big Data CSE547/STAT548, University of Washington Emily Fox January 16 th, 2014 1
More informationA Data Classification Algorithm of Internet of Things Based on Neural Network
A Data Classification Algorithm of Internet of Things Based on Neural Network https://doi.org/10.3991/ijoe.v13i09.7587 Zhenjun Li Hunan Radio and TV University, Hunan, China 278060389@qq.com Abstract To
More informationA Scalable Speech Recognizer with Deep-Neural-Network Acoustic Models
A Scalable Speech Recognizer with Deep-Neural-Network Acoustic Models and Voice-Activated Power Gating Michael Price*, James Glass, Anantha Chandrakasan MIT, Cambridge, MA * now at Analog Devices, Cambridge,
More informationEMC CLARiiON CX3 UltraScale Series The Proven Midrange Storage
EMC CLARiiON CX3 UltraScale Series The Proven Midrange Storage Erez Etzyon Senior Technology Consultant CLARiiON CX3 UltraScale Series Breakthrough Architecture and Innovation Designed to Deliver New Levels
More informationBigData and Map Reduce VITMAC03
BigData and Map Reduce VITMAC03 1 Motivation Process lots of data Google processed about 24 petabytes of data per day in 2009. A single machine cannot serve all the data You need a distributed system to
More informationDesign and Performance Analysis of and Gate using Synaptic Inputs for Neural Network Application
IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 12 May 2015 ISSN (online): 2349-6010 Design and Performance Analysis of and Gate using Synaptic Inputs for Neural
More informationReservoir Computing with Emphasis on Liquid State Machines
Reservoir Computing with Emphasis on Liquid State Machines Alex Klibisz University of Tennessee aklibisz@gmail.com November 28, 2016 Context and Motivation Traditional ANNs are useful for non-linear problems,
More informationPERFORMANCE OF GRID COMPUTING FOR DISTRIBUTED NEURAL NETWORK. Submitted By:Mohnish Malviya & Suny Shekher Pankaj [CSE,7 TH SEM]
PERFORMANCE OF GRID COMPUTING FOR DISTRIBUTED NEURAL NETWORK Submitted By:Mohnish Malviya & Suny Shekher Pankaj [CSE,7 TH SEM] All Saints` College Of Technology, Gandhi Nagar, Bhopal. Abstract: In this
More informationProgramming Models for Supercomputing in the Era of Multicore
Programming Models for Supercomputing in the Era of Multicore Marc Snir MULTI-CORE CHALLENGES 1 Moore s Law Reinterpreted Number of cores per chip doubles every two years, while clock speed decreases Need
More informationClaude TADONKI. MINES ParisTech PSL Research University Centre de Recherche Informatique
Got 2 seconds Sequential 84 seconds Expected 84/84 = 1 second!?! Got 25 seconds MINES ParisTech PSL Research University Centre de Recherche Informatique claude.tadonki@mines-paristech.fr Séminaire MATHEMATIQUES
More informationKey Features. High-performance data replication. Optimized for Oracle Cloud. High Performance Parallel Delivery for all targets
To succeed in today s competitive environment, you need real-time information. This requires a platform that can unite information from disparate systems across your enterprise without compromising availability
More informationCPSC 340: Machine Learning and Data Mining. Logistic Regression Fall 2016
CPSC 340: Machine Learning and Data Mining Logistic Regression Fall 2016 Admin Assignment 1: Marks visible on UBC Connect. Assignment 2: Solution posted after class. Assignment 3: Due Wednesday (at any
More informationSupervised Learning (contd) Linear Separation. Mausam (based on slides by UW-AI faculty)
Supervised Learning (contd) Linear Separation Mausam (based on slides by UW-AI faculty) Images as Vectors Binary handwritten characters Treat an image as a highdimensional vector (e.g., by reading pixel
More informationChapter 1: Fundamentals of Quantitative Design and Analysis
1 / 12 Chapter 1: Fundamentals of Quantitative Design and Analysis Be careful in this chapter. It contains a tremendous amount of information and data about the changes in computer architecture since the
More informationANN-Based Modeling for Load and Main Steam Pressure Characteristics of a 600MW Supercritical Power Generating Unit
ANN-Based Modeling for Load and Main Steam Pressure Characteristics of a 600MW Supercritical Power Generating Unit Liangyu Ma, Zhiyuan Gao Automation Department, School of Control and Computer Engineering
More informationMeet in the Middle: Leveraging Optical Interconnection Opportunities in Chip Multi Processors
Meet in the Middle: Leveraging Optical Interconnection Opportunities in Chip Multi Processors Sandro Bartolini* Department of Information Engineering, University of Siena, Italy bartolini@dii.unisi.it
More information