Memory devices for neuromorphic computing
|
|
- Barrie Johnson
- 6 years ago
- Views:
Transcription
1 Memory devices for neuromorphic computing Fabien ALIBART IEMN-CNRS, Lille Trad: Toutes les questions que je me suis posé sur le neuromorphique sans jamais (oser) les poser
2 Introduction: Why ANNet New needs for computing Recognition, Mining, Synthesis (Intel) Increase of Fault (nanoscale engineering) SEMICONDUCTOR TECHNOLOGY CHALLENGES Saturation of clock frequency + Energy consumption Von Neumann bottleneck Shift toward a new paradigm for computation BIO-INSPIRED COMPUTING to match the brain performances (low power consumption, fault tolerant, performances for RMS)
3 Supercomputer resources Purely digital NNET directions neurons synapses Emerging nanotechnologies New architecture concepts and integration strategies Custom IC, Mix analog/digital Multichip approach, i.e. with conventional technologies
4 BNNs vs ANNs Biological neural network Artificial neural network NEURON: Summation Thresholding Output activation SYNAPSES: Input weighting Weight adaptation The memory is in the processing unit (Direct solution to Von Neumann bottleneck!)
5 Neuromorphic in between BNNs Neuromorphic Eng. ANNs
6 Outline Intro to Artificial Neural Network (ANNs) Intro to biological Neural Network (BNNs) Nanodevices for ANNs Nanodevices for BNNs STDP: somewhere in between
7 Rosenblatt, 1957 Classification of vectors (datas) sgn() ANNs: basics after training Δw x 1 Input (+1 or -1) +1 0 input Perceptron rule x 2-1 x 3 Output after training Δw x 4 x 5 sgn() y= +1 if +1 if -1 if 1 n w i x i > 0-1 if 1 n w i x i < 0 Delta rule Post-neurons x n Pre-neurons Training/learning: find the optimal weight No analytical solution Learning algorithms: iterative correction based on known data Backpropagation
8 Practically, we can do: Pattern classification, Clustering, Prediction x 1 Input (+1 or -1) Two classes Multiple classes ANNs: basics x 1 x 2 x 3 x 4 input Synaptic weight output y 1 y 2 y 3 x 2 x 3 Output x 5 x 4 sgn() y= +1 if -1 if y m x 5 Post-neurons x n x n Pre-neurons Non linearly separable ensembles
9 ANNs: applications 28x28 pixel array 10 classes 7840 symapses 256x256 pixel array 1000 classes synapses
10 ANNs ANNs: Practical application will required ulra high density of nanodevices Main challenge: GPU or FPGA are serious challengers
11 BNNs: neurons The neuron membrane can be seen as a transmission line (RC) When the membrane potential reach a threshold, a spike is triggered Currents are ionic Low speed of propagation Active devices (soma and Ranvier s node)
12 BNNs: synapses The AP release neurotransmitters from the preneuron to the post neuron receptors Neurotransmitters open ionic channels Ionic concentration change the polarization of the post-neuron Various time scale of plasticity Complex dynamics with many species (ions,nt,..) Unidirectionnal
13 BNNs: learning Learning in BNNs: wij ai aj Who fire together wire together, (Hebbs) Synaptic fixe aj Synaptic adaptation Example, the BCM learning fixe aj
14 Variation of Hebbs rule Unsupervised BNNs: learning with STDP
15 BNNs: No charges (i.e. electrons), only ions Slow, with rich dynamics Still unsolved issues Basics of computing in the brain (coding, ) What do we really need for computing (for practical applictions)
16 Neuromorphic: Main stream for nanodevices The crossbar structure is the perfect architecture for massively parallel processing x 1 input Synaptic weight output x 2 x 3 x 4 x 5 y 1 y 2 y 3 y m It is compatible with back end process on top of a CMOS substrate x n x 1 x 2 x 3 x 4 Development SoC x 5 y 1 y 2 y 3 y 4 y 5 Strukov, PNAS 2009 Footprint 4F devices/cm 2
17 NANO FOR ANNs
18 Crossnet ANNs: synapse, digital or analog? Beck, 2000 Chanthbouala, 2012 L= 2n² +1 states From binary to multilevel to analog
19 ANNs: the analog synapse Papandreou, 2011 (A) 1E-4 1E-5 voltage 0 reset read Decrease Weight Increase set Weight Stand-by (Read only) -200mV ( A) time Pulse Number 120 A 60 A 30 A 15 A 7 A
20 W. Lu, Nanoletters,2011 ANNs: implementations 50x50 pasive crossbar array Binary operation (multilevel, more or less) CBRAM technology
21 Strukov, 2015 ANNs: implementations 12x12 Xbar array (TiO2 memristive devices) Online training (variation of delta rule) Three classes, 60 synapses
22 Burr, IEDM 2014 ANNs: implementations Demo of multilayer perceptron (with backprop) PCM analog synapses
23 Crossbar, IEDM, 2014 ANNs: implementations Record density 4Mb Binary only 100nm half pitch Fully functionnal!
24 Nano for ANNs Still a huge gap betwen requirements and what is available (from the memory perspectives) Do we need learning (i.e. smart memory) or pure memory (i.e. storage + analog) Co-integration still not demonstrated
25 NANO FOR BNNs
26 BNNs: synaptic plasticity (1) STP N n neurotransmiter (NT) activated at spike n S D Recovery of NT with a time t d I f N ) n ( n V IN V OUT charge of N n holes in the NP at spike n Pentacene thin film I n f ( N ) n (Alibart, Adv. Funct. Mat, 2011 Gold nanoparticles Discharge of the holes with a time t d
27 BNNs: synaptic plasticity (2)
28 BNNs: network scale implementations
29 Nano for BNNs Still very emerging No clear idea of applications but a very complex (and exciting!) field Can we map BNNs (ionic systems) with electronic devices (instead of ionic)
30 NANO IN BETWEEN: STDP
31 STDP with memristors pre post
32 STDP: practical implementations
33 STDP: triplet rule
34 STDP No hardware demo at the network level One layer OK, what about multi-layers? STDP but what else?
35 Concluding remarks Neuromorphic in between BNNs and ANNs. Maybe an issue for visibility (what is our community?) Neuromorphic as a bridge between ANNs and BNNs? Doing more than identifying neuromorphic in nano, it is time to built it!
36 Thank you! (One final tip: The hippocampus is not an animal)
Reliability enhancement of phase change
Reliability enhancement of phase change memory for neuromorphic applications SangBum Kim, Ph.D. Research Staff Member Novel memory and cognitive applications IBM T.J. Watson Research Center SangBum.Kim@us.ibm.com
More informationPhotonic Neuromorphic computing
Photonic Neuromorphic computing Presenter: Rafatul Faria PhD student, ECE, Purdue University Major: Micro and Nanoelectronics (MN) Outline General Overview of Neuromorphic computing What is neuromorphic
More informationComputing with Emerging Non- Volatile Memory Devices. Omid Kavehei 2013JULY11
Computing with Emerging Non- Volatile Memory Devices Omid Kavehei 2013JULY11 1 History of Non-volatile Memory Technology Large operational current (~100mA) Slow programming (~10ms) Technological advancement
More informationBrain Inspired Semiconductor Device Technology
US-KOREA NANO FORUM SEOUL, SEPTEMBER 26, 2016 Brain Inspired Semiconductor Device Technology Byoung Hun Lee Director, Center for Emerging Electronic Materials and Systems (CEEDS) School of Material Science
More informationResistive-switching memory
Resistive-switching memory Daniele Ielmini DEI - Politecnico di Milano, Milano, Italy ielmini@elet.polimi.it Flash scaling overview 1. Flash scaling: 2. Evolutionary scenario: T. Kamaigaichi, et al., IEDM
More informationBeyond the crossbar: materials based design and emulation of neuromemristive devices and architectures
Beyond the crossbar: materials based design and emulation of neuromemristive devices and architectures Angel Yanguas-Gil Argonne National Laboratory Drosophila melanogaster Complex visual, olfactory systems
More informationNeural Networks and Applications in Bioinformatics. Yuzhen Ye School of Informatics and Computing, Indiana University
Neural Networks and Applications in Bioinformatics Yuzhen Ye School of Informatics and Computing, Indiana University Contents Biological problem: promoter modeling Basics of neural networks Perceptrons
More informationNeural Networks and Applications in Bioinformatics
Contents Neural Networks and Applications in Bioinformatics Yuzhen Ye School of Informatics and Computing, Indiana University Biological problem: promoter modeling Basics of neural networks Perceptrons
More informationA Review on CMOL Cell Assignment Problem
A Review on CMOL Cell Assignment Problem Tanvi Vaidya 1, Er. Abhijeet Kumar 2 1 M.Tech (regular), M. M. Engg. College Mullana (Ambala) 2 Lecturer ECE Deptt. M.M.Engg.College Mullana (Ambala) Abstract -
More informationRECONFIGURABLE NEUROMORPHIC SYNAPSE INTERCONNECTS WITH TFT
RECONFIGURABLE NEUROMORPHIC SYNAPSE INTERCONNECTS WITH TFT JAN GENOE PUBLIC Every neuron in a human brain is connected via its synapses to 10-15.000 other neurons. Those connections can be over time reconfigured
More informationPREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING
PREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING Abbas Heiat, College of Business, Montana State University, Billings, MT 59102, aheiat@msubillings.edu ABSTRACT The purpose of this study is to investigate
More informationSupporting Information
Electronic Supplementary Material (ESI) for Nanoscale. This journal is The Royal Society of Chemistry 218 Supporting Information Fully imitation synaptic metaplasticity based on memristor device Quantan
More informationFor personal use only
18 February 2016 Major Technological Advancement of BrainChip Artificial Intelligence Autonomous Feature Extraction (AFE) System Developed In a major advancement to its existing and patented SNAP (Spiking
More informationThe Neuro-Bit Memristor. User Manual Version 2.0 July 2015
The Neuro-Bit Memristor User Manual Version 2.0 July 2015 Dear Customer, We at Bio Inspired Technologies believe that the future of electronics is based on adaptive intelligence technologies - technologies
More informationIn order to have GA, you must have a way to rate a given solution (fitness function). The fitness function must be continuous.
Disclaimer This document is a summary of Prof. Floreano s Bio-inspired Adaptive Machines course. The purpose is to help the student revise for the oral examination. This document should not be considered
More informationA light-stimulated neuromorphic device based on graphene hybrid phototransistor
A light-stimulated neuromorphic device based on graphene hybrid phototransistor Shuchao Qin #, Fengqiu Wang # *, Yujie Liu, Qing Wan, Xinran Wang, Yongbing Xu, Yi Shi, Xiaomu Wang*, Rong Zhang* School
More informationUPSIDE / Cortical Processor Study Dr. Dan Hammerstrom Program Manager / MTO
UPSIDE / Cortical Processor Study Dr. Dan Hammerstrom Program Manager / MTO Distribution A. Approved for public release: distribution unlimited. The Unconventional Processing of Signals for Intelligent
More informationComputing with Unreliable Nanodevices
GDR BIOCOMP Summer School Roscoff, June 2017 Computing with Unreliable Nanodevices Damien Querlioz Chargé de recherche CNRS, https://sites.google.com/site/damienquerlioz/ Centre de Nanosciences et de Nanotechnologies
More informationBrainChip Holdings Ltd. Corporate Presentation
BrainChip Holdings Ltd. Corporate Presentation 1 BrainChip Overview BrainChip is a leading developer of software and hardware-accelerated neural networking solutions for advanced artificial intelligence
More informationMachine Learning Models for Pattern Classification. Comp 473/6731
Machine Learning Models for Pattern Classification Comp 473/6731 November 17 th 2016 Prof. Neamat El Gayar Topics Introduction on Machine Learning Neural Networks Single Layer Perceptron and Discriminant
More informationData Analytics for Semiconductor Manufacturing The MathWorks, Inc. 1
Data Analytics for Semiconductor Manufacturing 2016 The MathWorks, Inc. 1 Competitive Advantage What do we mean by Data Analytics? Analytics uses data to drive decision making, rather than gut feel or
More informationASX Code: BRN An AI Processor Company
ASX Code: BRN An AI Processor Company Louis DiNardo President and CEO Ryan Benton Chief Financial Officer September 2017 1 Disclaimer This presentation is not a prospectus nor an offer for securities in
More informationMASTISK : к. Reduced pre-print version. Full extended version of this work will be published in the proceedings of IJCNN 2018
Reduced pre-print version. Full extended version of this work will be published in the proceedings of IJCNN 2018 MASTISK : к Tinish Bhattacharya, Vivek Parmar and Manan Suri Department of Electrical Engineering,
More informationTitle: Ultrafast Synaptic Events in a Chalcogenide Memristor
Title: Ultrafast Synaptic Events in a Chalcogenide Memristor Authors: Yi Li 1,2, Yingpeng Zhong 1,2, Lei Xu 1,2, Jinjian Zhang 1,2, Xiaohua Xu 1,2, Huajun Sun 1,2, Xiangshui Miao 1,2, Affiliations: 1 Wuhan
More informationIs Machine Learning the future of the Business Intelligence?
Is Machine Learning the future of the Business Intelligence Fernando IAFRATE : Sr Manager of the BI domain Fernando.iafrate@disney.com Tel : 33 (0)1 64 74 59 81 Mobile : 33 (0)6 81 97 14 26 What is Business
More informationThe Global Market for Intelligent Video Analytics
The Global Market for Intelligent Video Analytics 2018 to 2023 Published: Q3 2018 Global Market for Intell Video Analytics 2018 to 2023 Synopsis This report aims to assist all stakeholders and investors
More informationI. INTRODUCTION. Hyungjin Kim 1, Seongjae Cho 2, Min-Chul Sun 3, Jungjin Park 1, Sungmin Hwang, and Byung-Gook Park 1
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE, VOL.16, NO.5, OCTOBER, 2016 ISSN(Print) 1598-1657 http://dx.doi.org/10.5573/jsts.2016.16.5.657 ISSN(Online) 2233-4866 Simulation Study on Silicon-Based
More informationImplantable Microelectronic Devices
ECE 8803/4803 Implantable Microelectronic Devices Fall - 2015 Maysam Ghovanloo (mgh@gatech.edu) School of Electrical and Computer Engineering Georgia Institute of Technology 2015 Maysam Ghovanloo 1 Outline
More informationTech Trends. Big Data, IOT, Security, Machine Learning, Search engines... Anant Asthana: github.com/anantasty
Tech Trends Big Data, IOT, Security, Machine Learning, Search engines... Anant Asthana: asthana@pythian.com github.com/anantasty Buzz words and emerging trends: What have we heard about IOT, AI, Neural
More informationExperimental design on product development
Experimental design on product development Introduction What is the traditional developing method? What is experimental design? What do we need and what kind of possibilities do we have for designing?
More informationClass Presentation of CSC481 - Artificial Neural Networks. Outline
page 1 of 34 Class Presentation of CSC481 - Artificial Neural Networks Tiegeng Ren Dept. of Computer Science 04/19/2004 page 2 of 34 Outline Problems in classification systems Introduction of neural networks
More informationFrom microelectronics down to nanotechnology.
From microelectronics down to nanotechnology sami.franssila@tkk.fi Contents Lithography: scaling x- and y-dimensions MOS transistor physics Scaling oxide thickness (z-dimension) CNT transistors Conducting
More informationSEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE NETWORK ALGORITHM
Journal of Engineering Science and Technology Vol. 13, No. 3 (2018) 755-765 School of Engineering, Taylor s University SEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE
More informationThe Ovonic Cognitive Computer - A New Paradigm
The Ovonic Cognitive Computer - A New Paradigm Stanford R. Ovshinsky Energy Conversion Devices, Inc. 2956 Waterview Drive - Rochester Hills, MI 48309 (USA) Abstract Paul Davies, a well-known theoretical
More informationDeep Learning for Anomaly Detection in Manufacturing
Deep Learning for Anomaly Detection in Manufacturing July, 2018 David Katz, Data Scientist, TIBCO Software Mike Alperin, Manufacturing Industry Consultant, TIBCO Software Agenda Anomaly Detection in Manufacturing
More informationDesign for Low-Power at the Electronic System Level Frank Schirrmeister ChipVision Design Systems
Frank Schirrmeister ChipVision Design Systems franks@chipvision.com 1. Introduction 1.1. Motivation Well, it happened again. Just when you were about to beat the high score of your favorite game your portable
More information6.1 Summary. Summary and Scope for Further Study
Summary and scope for further study Summary and Scope for Further Study 6.1 Summary Detecting gases and determining their composition has constantly been on the increase in recent years. The demand for
More informationControlling life with photons A new tool based on conjugated polymers
Controlling life with photons A new tool based on conjugated polymers Maria Rosa Antognazza Center for Nanoscience and Technology @PoliMi The Italian Institute of Technology Controlling life with photons:
More informationArtificial Neural Networks Modelling for Monitoring and Performance Analysis of a Heat and Power Plant
ISRN LUTMDN/TMHP 06/5084 SE ISSN 0282-1990 Artificial Neural Networks Modelling for Monitoring and Performance Analysis of a Heat and Power Plant Mehrzad Kaiadi Thesis for the Degree of Master of Science
More informationRADIATION HARDNESS OF MEMRISTIVE SYSTEMS
RADIATION HARDNESS OF MEMRISTIVE SYSTEMS A. FANTINI ON BEHALF OF IMEC RRAM TEAM AND VU ISDE TEAM Workshop on Memristive systems for Space applications ESTEC - 30/04/2015 OUTLINE Introduction RRAM for space
More informationProcessor. A Brief Introduction Micron Technology, Inc. March 13, 2014
Micron Automata Processor A Brief Introduction 2013 Micron Technology, Inc. All rights reserved. Products are warranted only to meet Micron s production data sheet specifications. Information, products,
More informationSOFTWARE DEVELOPMENT PRODUCTIVITY FACTORS IN PC PLATFORM
SOFTWARE DEVELOPMENT PRODUCTIVITY FACTORS IN PC PLATFORM Abbas Heiat, College of Business, Montana State University-Billings, Billings, MT 59101, 406-657-1627, aheiat@msubillings.edu ABSTRACT CRT and ANN
More informationReverse-Engineering the Brain
Prof. Henry Markram Dr. Felix Schürmann felix.schuermann@epfl.ch http://bluebrainproject.epfl.ch Reverse-Engineering the Brain Brain Mind Institute The Electrophysiologist s View Accurate Models that Relate
More informationCross-bar architectures
Cross-bar architectures Daniele Ielmini DEI - Politecnico di Milano, Milano, Italy ielmini@elet.polimi.it Flash scaling overview 1. Flash scaling: 2. Evolutionary scenario: T. Kamaigaichi, et al., IEDM
More informationUsing FPGAs to Accelerate Neural Network Inference
Using FPGAs to Accelerate Neural Network Inference 1 st FPL Workshop on Reconfigurable Computing for Deep Learning (RC4DL) 8. September 2017, Ghent, Belgium Associate Professor Magnus Jahre Department
More informationNEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE
NEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE 1 I. Skitzi, 1 E. Paleologos and 2 K. Katsifarakis 1 Technical University of Crete 2 Aristotle University of Thessaloniki ABSTRACT A multi-layer perceptron
More informationApplication of Artificial Neural Networks in Prediction: A Case Study in Consumer Propensity to Buy Insurance
Application of Artificial Neural Networks in Prediction: A Case Study in Consumer Propensity to Buy Insurance Rosmayati Mohemad 609-6683106 rosmayati@umtedumy Noor Azliza Che Mat 609-6683106 azliza@umtedumy
More informationEnhancing Innovation & Competitiveness Through Investments In Fundamental Research
Enhancing Innovation & Competitiveness Through Investments In Fundamental Research Measurement, Instrumentation and Applications Agilent Laboratories Darlene J.S. Solomon, Ph.D. Agilent Chief Technology
More informationGTC. S Create Deep Intelligence TM in the Internet of Things (IoT) Nobuyuki Ota
GTC S5813 - Create Deep Intelligence TM in the Internet of Things (IoT) Nobuyuki Ota Preferred Networks Preferred Networks, Inc. (PFN) founded in 2014, located at Tokyo, Japan. Subsidiary company, PFN
More informationA 256-by-256 CMOS Microelectrode Array for Extracellular Neural Stimulation of Acute Brain Slices. Columbia University, New York, NY
A 256-by-256 CMOS Microelectrode Array for Extracellular Neural Stimulation of Acute Brain Slices Na Lei 1, K L Shepard 1, Brendon O Watson 2, Jason N MacLean 2, Rafael Yuste 2 1 Department of Electrical
More informationUNIT I PHYSIOLOGYAND TRANSDUCERS
SRI VENKATESWARA COLLEGE OF ENGINEERING AND TECHNOLOGY TIRUPACHUR DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING 1. What is meant by cell? EI 2311 BIOMEDICAL INSTRUMENTATION 2 Mark Questions With
More informationCray and Allinea. Maximizing Developer Productivity and HPC Resource Utilization. SHPCP HPC Theater SEG 2016 C O M P U T E S T O R E A N A L Y Z E 1
Cray and Allinea Maximizing Developer Productivity and HPC Resource Utilization SHPCP HPC Theater SEG 2016 10/27/2016 C O M P U T E S T O R E A N A L Y Z E 1 History Cluster Computing to Super Computing
More informationBiomimetic Computational Systems: Understanding Informational Processing in the Brain
Institute of Medicine "Grand Challenges" 2008 Biomimetic Computational Systems: Understanding Informational Processing in the Brain Theodore W. Berger, Ph.D. David Packard Professor of Engineering Professor
More informationDigital Design Methodology (Revisited)
Digital Design Methodology (Revisited)! Design Methodology " Design Specification " Verification " Synthesis! Technology Options " Full Custom VLSI " Standard Cell ASIC " FPGA CS 150 Spring 2007 - Lec
More informationNatural Gas Market Prediction via Statistical and Neural Network Methods
2nd AIEE Energy Symposium Natural Gas Market Prediction via Statistical and Neural Network Methods Dr. Mona Shokripour, Energy Statistician Gas Exporting Countries Forum (GECF) Data and Information Services
More informationEstimation of environmental risks in construction projects in Puebla (Mexico): a neural network approach
Estimation of environmental risks in construction projects in Puebla (Mexico): a neural network approach P. María-Sánchez Department of Civil Engineering, Universidad de las Américas-Puebla, Mexico Abstract
More informationOptical Observation - Hyperspectral Characterization of Nano-scale Materials In-situ
Optical Observation - Hyperspectral Characterization of Nano-scale Materials In-situ Research at the nanoscale is more effective, when research teams can quickly and easily observe and characterize a wide
More informationNanosciences, Nanotechnology and Nanosystems. ICT department
Nanosciences, Nanotechnology and Nanosystems ICT department Content ANR overview Nanotechnology development 2 Organisation of the ANR 7 scientific departments : 1 department in charge of the non thematic
More informationUse of deep learning for contamination detection on glass vials and syringes
Use of deep learning for contamination detection on glass vials and syringes Andre Villemaire, Francois-Michel De Rainville, Simon Levasseur, Alexandre ValliEres, NovaSyst, Quebec City, Qc, Canada Jean-Maxime
More informationMACHINE LEARNING IN THE OIL AND GAS INDUSTRY
MACHINE LEARNING IN THE OIL AND GAS INDUSTRY Transforming Data Into Performance Mehrzad Mahdavi Vice President, Digital Solutions 19 April 2017 1 WHAT IS MACHINE LEARNING? A method of data analysis that
More informationContents. From microelectronics down to nanotechnology
Contents From microelectronics down to nanotechnology sami.franssila@tkk.fi Lithography: scaling x- and y-dimensions MOS transistor physics Scaling oxide thickness (z-dimension) CNT transistors Conducting
More informationContents. From microelectronics down to nanotechnology. Top down nanotechnology. Writing patterns
Contents From microelectronics down to nanotechnology sami.franssila@tkk.fi Lithography: scaling x- and y-dimensions MOS transistor physics Scaling oxide thickness (z-dimension) CNT transistors Conducting
More informationJournal of Asian Scientific Research PREDICTION OF MECHANICAL PROPERTIES OF TO HEAT TREATMENT BY ARTIFICIAL NEURAL NETWORKS
Journal of Asian Scientific Research journal homepage: http://aessweb.com/journal-detail.php?id=5003 PREDICTION OF MECHANICAL PROPERTIES OF TO HEAT TREATMENT BY ARTIFICIAL NEURAL NETWORKS Esmaeil Alibeiki
More informationFabrication of Highly Ordered Al 2 O 3 Nanohole Arrays As a Nanostructured Template
Fabrication of Highly Ordered Al 2 O 3 Nanohole Arrays As a Nanostructured Template Jie Gong, Bill Butler and Giovanni Zangari Materials Science Program University of Alabama at Tuscaloosa This work was
More informationLOAD FORECASTING FOR POWER SYSTEM PLANNING AND OPERATION USING ARTIFICIAL NEURAL NETWORK AT AL BATINAH REGION OMAN
Journal of Engineering Science and Technology Vol. 7, No. 4 (01) 498-504 School of Engineering, Taylor s University LOAD FORECASTING FOR POWER SYSTEM PLANNING AND OPERATION USING ARTIFICIAL NEURAL NETWORK
More informationImplementation of Artificial Immune System Algorithms
Implementation of Artificial Immune System Algorithms K. Sri Lakshmi Associate Professor, Department of CSE Abstract An artificial immune system (AIS) that is distributed, robust, dynamic, diverse and
More informationGenetic Algorithm and Application in training Multilayer Perceptron Model
Genetic Algorithm and Application in training Multilayer Perceptron Model Tuan Dung Lai Faculty of Science, Engineering and Technology Swinburne University of Technology Hawthorn, Victoria 3122 Email:
More informationRealization of tunable artificial synapse and memory based on amorphous oxide semiconductor transistor
www.nature.com/scientificreports Received: 13 February 217 Accepted: 15 May 217 Published: xx xx xxxx OPEN Realization of tunable artificial synapse and memory based on amorphous oxide semiconductor transistor
More informationPhotonic Drying Pulsed Light as a low Temperature Sintering Process
Photonic Drying Pulsed Light as a low Temperature Sintering Process Lou Panico Xenon Corporation W E S T E R N M I C H I G A N U N I V E R S I T Y PRESENTATION OVERVIEW What is Printed Electronics Materials
More informationDesign Virtualization and Its Impact on SoC Design
Design Virtualization and Its Impact on SoC Design Advanced SoC projects present the designer with a large number of options for technology, IP, foundation libraries, memory and operating conditions. Finding
More informationIonizing Radiation Effects on Nonvolatile Memory Properties of Programmable Metallization Cells
IEEE TRANSACTIONS ON NUCLEAR SCIENCE 1 Ionizing Radiation Effects on Nonvolatile Memory Properties of Programmable Metallization Cells J. L. Taggart, Student Member, IEEE, Y. Gonzalez-Velo, Member, IEEE,
More informationBiologically-Inspired Pattern Recognition For Odor Detection
Biologically-Inspired Pattern Recognition For Odor Detection Thaddeus Roppel (uburn University), and Denise. Wilson (University of Washington) Correspondence: troppel@eng.auburn.edu Keywords: Odor recognition,
More informationIntel s Machine Learning Strategy. Gary Paek, HPC Marketing Manager, Intel Americas HPC User Forum, Tucson, AZ April 12, 2016
Intel s Machine Learning Strategy Gary Paek, HPC Marketing Manager, Intel Americas HPC User Forum, Tucson, AZ April 12, 2016 Taxonomic Foundations AI Sense, learn, reason, act, and adapt to the real world
More informationLiveReceptor AMPAR <Endogenous AMPAR Labeling Reagent>
9-7 Hongo 2-Chome, Bunkyo-Ku Tokyo 113-0033, Japan LiveReceptor AMPAR Product Background Neurotransmitter receptors including glutamate receptors and GABA receptors
More informationAlternative Approaches to 3-Dimensional Packaging and Interconnection
Alternative Approaches to 3-Dimensional Packaging and Interconnection Joseph Fjelstad SiliconPipe, Inc. www.sipipe.com IC Packaging a Technology in Transition In the past, IC packaging has been considered
More informationMoS 2 film thinning on high-temperature sputtering for enhancement-mode nmosfets
IEEE MQ: WIMNACT-45 MoS 2 film thinning on high-temperature sputtering for enhancement-mode nmosfets Takumi Ohashi 1*, Kohei Suda 2, Seiya Ishihara 2, Naomi Sawamoto 2, Shimpei Yamaguchi 1, Kentaro Matsuura
More informationHarnessing Machine Data with Data-Driven Machine Learning
Harnessing Machine Data with Data-Driven Machine Learning (White Paper) Executive Summary Petabytes of machine data are generated by billions of machines every single day. Traditional data processing techniques
More informationCourse Objectives. This course gives an introduction to basic neural network architectures and learning rules.
Introduction 1 Course Objectives This course gives an introduction to basic neural network architectures and learning rules. Emphasis is placed on the mathematical analysis of these networks, on methods
More informationMODERN COMPUTER TENDING TOWARDS NANOTECHNOLOGY MAKING GRATE GROWTH IN 21 ST CENTURY
MODERN COMPUTER TENDING TOWARDS NANOTECHNOLOGY MAKING GRATE GROWTH IN 21 ST CENTURY Mrs. Jayashree Yadannavar Department of Information Technology,MIT AOE, Alandi(D),Pune ABSTRACT At present in the field
More informationPlasmonics using Metal Nanoparticles. Tammy K. Lee and Parama Pal ECE 580 Nano-Electro-Opto-Bio
Plasmonics using Metal Nanoparticles Tammy K. Lee and Parama Pal ECE 580 Nano-Electro-Opto-Bio April 1, 2007 Motivation Why study plasmonics? Miniaturization of optics and photonics to subwavelength scales
More informationFabrication and modeling of thin-film anodic titania memristors
Graduate Theses and Dissertations Graduate College 2010 Fabrication and modeling of thin-film anodic titania memristors Kyle James Miller Iowa State University Follow this and additional works at: http://lib.dr.iastate.edu/etd
More informationExpansion Circuits. Brain Tissue as a Computational Substrate
Expansion Circuits Brain Tissue as a Computational Substrate BrainMaker Thanks to the many collaborators, consultants and supporters who helped: Ed Boyden, Jae-Byum Chang, Manos Karagiannis, Adam Marblestone
More informationDigital Transformation of Energy Systems
DNV GL Energy Digital Transformation of Energy Systems A holistic approach to digitization of utility system operations through effective data management 1 SAFER, SMARTER, GREENER DNV GL: Global classification,
More informationDATA SCIENCE: HYPE AND REALITY PATRICK HALL
DATA SCIENCE: HYPE AND REALITY PATRICK HALL About me SAS Enterprise Miner, 2012 Cloudera Data Scientist, 2014 Do you use Kolmogorov Smirnov often? Statistician No, I mix my martinis with gin. Data Scientist
More informationWallenberg Autonomous Systems Program WASP. Karl-Erik Årzén Lund University
Wallenberg Autonomous Systems Program WASP Karl-Erik Årzén Lund University Background In Oct 2014 the Knut and Alice Wallenberg Foundation (KAW) decided to issue a large initiative on Autonomous Systems
More informationResistive switching of CeO x /SiO 2 stacked film based on anodic oxidation and breakdown
Feb. 19 th, 2015 WIMNACT-45 Resistive switching of /SiO 2 stacked film based on anodic oxidation and breakdown K. Kakushima Tokyo Institute of Technology 1 Introduction to resistive RAM (RRAM) Reset OFF
More informationAN EVALUATION OF BACKPROPAGATION NEURAL NETWORK MODELING AS AN ALTERNATIVE METHODOLOGY FOR CRITERION VALIDATION OF EMPLOYEE SELECTION TESTING
37^ M&U Ma.Ht7 C AN EVALUATION OF BACKPROPAGATION NEURAL NETWORK MODELING AS AN ALTERNATIVE METHODOLOGY FOR CRITERION VALIDATION OF EMPLOYEE SELECTION TESTING DISSERTATION Presented to the Graduate Council
More informationPrediction of organic matter removal from pulp and paper mill wastewater using artificial neural network
FEDERAL UNIVERSITY OF BAHIA, BRAZIL POLYTECHNIC SCHOOL DEPARTMENT OF ENVIRONMENTAL ENGINEERING RESEARCH GROUP ON SOLID WASTE AND WASTEWATER RESEARCH NETWORK ON CLEAN TECHNOLOGIES http://www.teclim.ufba.br
More information5. Packaging Technologies Trends
5. Packaging Technologies Trends Electronic products and microsystems continue to find new applications in personal, healthcare, home, automotive, environmental and security systems. Advancements in packaging
More informationEnterprise Artificial Intelligence
Ron Bodkin VP and GM, Artificial Intelligence Enterprise Artificial Intelligence Applications and Approaches 1 2015 Teradata 2016 Teradata Evolution of Analytics Prescriptive Predictive Descriptive REPORTING
More informationSingle Phase Grid Connected Photovoltaic System
Single Phase Grid Connected Photovoltaic System 1 Kavya S A, 2 Komal T, 3 Pooja A, 3 Sahana S N and 4 Mr Sachin Angadi 1 ankalakote.kavya@gmail.com Abstract Due to global environmental concerns, photovoltaic
More informationGoya Deep Learning Inference Platform. Rev. 1.2 November 2018
Goya Deep Learning Inference Platform Rev. 1.2 November 2018 Habana Goya Deep Learning Inference Platform Table of Contents 1. Introduction 2. Deep Learning Workflows Training and Inference 3. Goya Deep
More informationFundamentals of Central Nervous System Recording. Joseph E. O Doherty BME Neural Prosthetic Systems
Fundamentals of Central Nervous System Recording Joseph E. O Doherty BME 265 - Neural Prosthetic Systems The Problem Spaghetti & Meatballs Rall 1962 (after Ramon y Cajal) Outline 1. Origin of Extracellular
More informationTHE MATRIX IS ALWAYS COMPLEX!
THE MATRIX IS ALWAYS COMPLEX! Prof. Kenneth Dawson Centre for BioNano Interactions University College Dublin http://www.ucd.ie/cbni/ 1 Around this month 2 NEW SCIENCE 3 Engineered Nanoscale written in
More informationSuper Resolution Imaging Solution Provider. Imaging Future
Super Resolution Imaging Solution Provider Imaging Future Imaging Solution More Than Equipment NanoBioImaging(NBI) is the Industrial Partner of HKUST Super Resolution Imaging Center (SRIC). NBI aims to
More informationKnowledge-based Short-Term Load Forecasting for Maritime Container Terminals
Knowledge-based Short-Term Load Forecasting for Maritime Container Terminals Evaluation of two approaches based on operation plans @International Data Science Conference Norman Ihle R&D-Division Energy
More informationGoya Inference Platform & Performance Benchmarks. Rev January 2019
Goya Inference Platform & Performance Benchmarks Rev. 1.6.1 January 2019 Habana Goya Inference Platform Table of Contents 1. Introduction 2. Deep Learning Workflows Training and Inference 3. Goya Deep
More informationChallenges and Future Directions of Laser Fuse Processing in Memory Repair
Challenges and Future Directions of Laser Fuse Processing in Memory Repair Bo Gu, * T. Coughlin, B. Maxwell, J. Griffiths, J. Lee, J. Cordingley, S. Johnson, E. Karagiannis, J. Ehrmann GSI Lumonics, Inc.
More informationStep-response of an RC Wire as a Function of Time and Space (Fig. 4-15, p. 157)
Step-response of an RC Wire as a Function of Time and Space (Fig. 4-15, p. 157) 2.5 2 x= L/10 voltage (V) 1.5 1 x = L/4 x = L/2 x= L 0.5 0 0 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 time (nsec) time EEC 116, Fall
More informationCHAPTER 5 IMPROVING ON TIME, IN FULL DELIVERY
70 CHAPTER 5 IMPROVING ON TIME, IN FULL DELIVERY 5.1 INTRODUCTION The orders which are not yet shipped or invoiced to customer are called backlog orders. The various reasons for accumulation of stock,
More information