Neural Turing Machines
|
|
- Geraldine Muriel Johnson
- 6 years ago
- Views:
Transcription
1 Neural Turing Machines Can neural nets learn programs? Alex Graves Greg Wayne Ivo Danihelka
2
3
4 Contents 1. IntroducBon 2. FoundaBonal Research 3. Neural Turing Machines 4. Experiments 5. Conclusions
5 IntroducBon First applicabon of Machine Learning to logical flow and external memory
6 IntroducBon First applicabon of Machine Learning to logical flow and external memory Extend the capabilibes of neural networks by coupling them to external memory
7 IntroducBon First applicabon of Machine Learning to logical flow and external memory Extend the capabilibes of neural networks by coupling them to external memory Analogous to TM coupling a finite state machine to infinite tape
8 IntroducBon First applicabon of Machine Learning to logical flow and external memory Extend the capabilibes of neural networks by coupling them to external memory Analogous to TM coupling a finite state machine to infinite tape RNN s have been shown to be Turing- Complete, Siegelmann et al 95
9 IntroducBon First applicabon of Machine Learning to logical flow and external memory Extend the capabilibes of neural networks by coupling them to external memory Analogous to TM coupling a finite state machine to infinite tape RNN s have been shown to be Turing- Complete, Siegelmann et al 95 Unlike TM, NTM is completely differenbable
10 FoundaBonal Research Neuroscience and Psychology Concept of working memory : short- term memory storage and rule based manipulabon Also known as rapidly created variables
11 FoundaBonal Research Neuroscience and Psychology Concept of working memory : short- term memory storage and rule based manipulabon Also known as rapidly created variables ObservaBonal neuroscience results in the pre- frontal cortex and basal ganglia of monkeys
12 FoundaBonal Research Neuroscience and Psychology CogniBve Science and LinguisBcs AI and CogniBve Science were contemporaneous in 1950 s s
13 FoundaBonal Research Neuroscience and Psychology CogniBve Science and LinguisBcs AI and CogniBve Science were contemporaneous in 1950 s s Two fields parted ways when neural nets received cribcism, Fodor et al. 88 Incapable of variable- binding eg Mary spoke to John Incapable of handling variable sized input
14 FoundaBonal Research Neuroscience and Psychology CogniBve Science and LinguisBcs AI and CogniBve Science were contemporaneous in 1950 s s Two fields parted ways when neural nets received cribcism, Fodor et al. 88 MoBvated Recurrent Networks research to handle variable binding and variable length input
15 FoundaBonal Research Neuroscience and Psychology CogniBve Science and LinguisBcs AI and CogniBve Science were contemporaneous in 1950 s s Two fields parted ways when neural nets received cribcism, Fodor et al. 88 MoBvated Recurrent Networks research to handle variable binding and variable length input Recursive processing hot debate topic in role inhuman evolubon (Pinker vs Chomsky)
16 FoundaBonal Research Neuroscience and Psychology CogniBve Science ad LinguisBcs Recurrent Neural networks Broad class of machines with distributed and dynamic state
17 FoundaBonal Research Neuroscience and Psychology CogniBve Science ad LinguisBcs Recurrent Neural networks Broad class of machines with distributed and dynamic state Long Short Term Memory RNN s designed to handle vanishing and exploding gradient
18 FoundaBonal Research Neuroscience and Psychology CogniBve Science ad LinguisBcs Recurrent Neural networks Broad class of machines with distributed and dynamic state Long Short Term Memory RNN s designed to handle vanishing and exploding gradient NaBvely handle variable length structures
19 Neural Turing Machines
20 Neural Turing Machines
21 Neural Turing Machines 1. Reading M t is NxM matrix of memory at Bme t
22 Neural Turing Machines 1. Reading M t is NxM matrix of memory at Bme t w t
23 Neural Turing Machines 1. Reading 2. WriBng involves both erasing and adding
24 Neural Turing Machines 1. Reading 2. WriBng involves both erasing and adding
25 Neural Turing Machines 1. Reading 2. WriBng involves both erasing and adding 3. Addressing
26 Neural Turing Machines 3. Addressing 1. Focusing by Content Each head produces key vector k t of length M Generated a content based weight w t c based on similarity measure, using key strength β t
27 Neural Turing Machines 3. Addressing 2. InterpolaBon Each head emits a scalar interpolabon gate g t
28 Neural Turing Machines 3. Addressing 3. ConvoluBonal shif Each head emits a distribubon over allowable integer shifs s t
29 Neural Turing Machines 3. Addressing 4. Sharpening Each head emits a scalar sharpening parameter γ t
30 Neural Turing Machines 3. Addressing (puhng it all together)
31 Neural Turing Machines 3. Addressing (puhng it all together) This can operate in three complementary modes A weighbng can be chosen by the content system without any modificabon by the locabon system
32 Neural Turing Machines 3. Addressing (puhng it all together) This can operate in three complementary modes A weighbng can be chosen by the content system without any modificabon by the locabon system A weighbng produced by the content addressing system can be chosen and then shifed
33 Neural Turing Machines 3. Addressing (puhng it all together) This can operate in three complementary modes A weighbng can be chosen by the content system without any modificabon by the locabon system A weighbng produced by the content addressing system can be chosen and then shifed A weighbng from the previous Bme step can be rotated without any input from the content- based addressing system
34 Neural Turing Machines Controller Network Architecture Feed Forward vs Recurrent
35 Neural Turing Machines Controller Network Architecture Feed Forward vs Recurrent The LSTM version of RNN has own internal memory complementary to M
36 Neural Turing Machines Controller Network Architecture Feed Forward vs Recurrent The LSTM version of RNN has own internal memory complementary to M Hidden LSTM layers are like registers in processor
37 Neural Turing Machines Controller Network Architecture Feed Forward vs Recurrent The LSTM version of RNN has own internal memory complementary to M Hidden LSTM layers are like registers in processor Allows for mix of informabon across mulbple Bme- steps
38 Neural Turing Machines Controller Network Architecture Feed Forward vs Recurrent The LSTM version of RNN has own internal memory complementary to M Hidden LSTM layers are like registers in processor Allows for mix of informabon across mulbple Bme- steps Feed Forward has bejer transparency
39 Experiments Test NTM s ability to learn simple algorithms like copying and sorbng
40 Experiments Test NTM s ability to learn simple algorithms like copying and sorbng Demonstrate that solubons generalize well beyond the range of training
41 Experiments Test NTM s ability to learn simple algorithms like copying and sorbng Demonstrate that solubons generalize well beyond the range of training Tests three architectures NTM with feed forward controller NTM with LSTM controller Standard LSTM network
42 Experiments 1. Copy Tests whether NTM can store and retrieve data Trained to copy sequences of 8 bit vectors Sequences vary between 1-20 vectors
43 Experiments 1. Copy
44 Experiments 1. Copy NTM
45 Experiments 1. Copy LSTM
46 Experiments 1. Copy
47 Experiments 2. Repeat Copy Tests whether NTM can learn simple nested funcbon Extend copy by repeatedly copying input specified number of Bmes Training is a random- length sequence of 8 bit binary inputs plus a scalar value for # of copies Scalar value is random between 1-10
48 Experiments 2. Repeat Copy
49 Experiments 2. Repeat Copy
50 Experiments 2. Repeat Copy
51 Experiments 3. AssociaBve Recall Tests NTM s ability to associate data references Training input is list of items, followed by a query item Output is subsequent item in list Each item is a three sequence 6- bit binary vector Each episode has between two and six items
52 Experiments 3. AssociaBve Recall
53 Experiments 3. AssociaBve Recall
54 Experiments 3. AssociaBve Recall
55 Experiments 4. Dynamic N- Grams Test whether NTM could rapidly adapt to new predicbve distribubons Trained on 6- gram binary pajern on 200 bit sequences Can NTM learn opbmal esbmator
56 Experiments 4. Dynamic N- Grams
57 Experiments 4. Dynamic N- Grams
58 Experiments 4. Dynamic N- Grams
59 Experiments 5. Priority Sort Tests whether NTM can sort data Input is sequence of 20 random binary vectors, each with a scalar rabng drawn from [- 1, 1] Target sequence is 16- highest priority vectors
60 Experiments 5. Priority Sort
61 Experiments 5. Priority Sort
62 Experiments 5. Priority Sort
63 Experiments 6. Details RMSProp algorithm Momentum 0.9 All LSTM s had three stacked hidden layers
64 Experiments 6. Details
65 Experiments 6. Details
66 Experiments 6. Details
67 Conclusion Introduced an neural net architecture with external memory that is differenbable end- to- end Experiments demonstrate that NTM are capable of leaning simple algorithms and are capable of generalizing beyond training regime
68
Recurrent neural networks Modelling sequential data. MLP Lecture 9 Recurrent Networks 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 Recurrent Networks 1 Recurrent Networks Steve Renals Machine Learning Practical MLP Lecture 9 16 November 2016 MLP Lecture 9 Recurrent
More informationNeural Network Part 4: Recurrent Neural Networks
Neural Network Part 4: Recurrent Neural Networks Yingyu Liang Computer Sciences 760 Fall 2017 http://pages.cs.wisc.edu/~yliang/cs760/ Some of the slides in these lectures have been adapted/borrowed from
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 informationDeep Learning Basics Lecture 9: Recurrent Neural Networks. Princeton University COS 495 Instructor: Yingyu Liang
Deep Learning Basics Lecture 9: Recurrent Neural Networks Princeton University COS 495 Instructor: Yingyu Liang Introduction Recurrent neural networks Dates back to (Rumelhart et al., 1986) A family of
More informationCSCE 315: Programming Studio
CSCE 315: Programming Studio Introduction to Artificial Intelligence Textbook Definitions Thinking like humans What is Intelligence Acting like humans Thinking rationally Acting rationally However, it
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 informationThe Nature of Informatics
The Nature of Informatics Alan Bundy University of Edinburgh 19-Sep-11 1 What is Informatics? The study of the structure, behaviour, and interactions of both natural and artificial computational systems.
More informationUsing Deep Learning for Sentiment Analysis and Opinion Mining
Using Deep Learning for Sentiment Analysis and Opinion Mining Gauging opinions is faster and more accurate. Abstract How does a computer analyze sentiment? How does a computer determine if a comment or
More informationIntroduction (concepts and definitions)
Objectives: Introduction (digital system design concepts and definitions). Advantages and drawbacks of digital techniques compared with analog. Digital Abstraction. Synchronous and Asynchronous Systems.
More informationArtificial Neural Networks. Artificial Intelligence Santa Clara, 2016
Artificial Neural Networks Artificial Intelligence Santa Clara, 2016 Simulate the functioning of the brain Can simulate actual neurons: Computational neuroscience Can introduce simplified neurons: Neural
More informationDeep Neural Network Architectures for Modulation Classification
Deep Neural Network Architectures for Modulation Classification Xiaoyu Liu, Diyu Yang, and Aly El Gamal School of Electrical and Computer Engineering Purdue University Email: {liu1962, yang1467, elgamala}@purdue.edu
More informationAN IMPROVED NEURAL NETWORK-BASED DECODER SCHEME FOR SYSTEMATIC CONVOLUTIONAL CODE. A Thesis by. Andrew J. Zerngast
AN IMPROVED NEURAL NETWORK-BASED DECODER SCHEME FOR SYSTEMATIC CONVOLUTIONAL CODE A Thesis by Andrew J. Zerngast Bachelor of Science, Wichita State University, 2008 Submitted to the Department of Electrical
More informationMINE 432 Industrial Automation and Robotics
MINE 432 Industrial Automation and Robotics Part 3, Lecture 5 Overview of Artificial Neural Networks A. Farzanegan (Visiting Associate Professor) Fall 2014 Norman B. Keevil Institute of Mining Engineering
More informationCITS2211 Discrete Structures Turing Machines
CITS2211 Discrete Structures Turing Machines October 23, 2017 Highlights We have seen that FSMs and PDAs are surprisingly powerful But there are some languages they can not recognise We will study a new
More information1 Introduction. w k x k (1.1)
Neural Smithing 1 Introduction Artificial neural networks are nonlinear mapping systems whose structure is loosely based on principles observed in the nervous systems of humans and animals. The major
More informationAudio Effects Emulation with Neural Networks
DEGREE PROJECT IN TECHNOLOGY, FIRST CYCLE, 15 CREDITS STOCKHOLM, SWEDEN 2017 Audio Effects Emulation with Neural Networks OMAR DEL TEJO CATALÁ LUIS MASÍA FUSTER KTH ROYAL INSTITUTE OF TECHNOLOGY SCHOOL
More informationTiling Problems. This document supersedes the earlier notes posted about the tiling problem. 1 An Undecidable Problem about Tilings of the Plane
Tiling Problems This document supersedes the earlier notes posted about the tiling problem. 1 An Undecidable Problem about Tilings of the Plane The undecidable problems we saw at the start of our unit
More informationRecurrent neural networks Modelling sequential data. MLP Lecture 9 / 13 November 2018 Recurrent Neural Networks 1: Modelling sequential data 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 / 13 November 2018 Recurrent Neural Networks 1: Modelling sequential data 1 Recurrent Neural Networks 1: Modelling sequential data Steve
More informationCHAPTER 6 BACK PROPAGATED ARTIFICIAL NEURAL NETWORK TRAINED ARHF
95 CHAPTER 6 BACK PROPAGATED ARTIFICIAL NEURAL NETWORK TRAINED ARHF 6.1 INTRODUCTION An artificial neural network (ANN) is an information processing model that is inspired by biological nervous systems
More informationRecurrent neural networks Modelling sequential data. MLP Lecture 9 Recurrent Neural Networks 1: Modelling sequential data 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 Recurrent Neural Networks 1: Modelling sequential data 1 Recurrent Neural Networks 1: Modelling sequential data Steve Renals Machine Learning
More informationAudio Effects Emulation with Neural Networks
Escola Tècnica Superior d Enginyeria Informàtica Universitat Politècnica de València Audio Effects Emulation with Neural Networks Trabajo Fin de Grado Grado en Ingeniería Informática Autor: Omar del Tejo
More informationarxiv: v1 [cs.ne] 5 Feb 2014
LONG SHORT-TERM MEMORY BASED RECURRENT NEURAL NETWORK ARCHITECTURES FOR LARGE VOCABULARY SPEECH RECOGNITION Haşim Sak, Andrew Senior, Françoise Beaufays Google {hasim,andrewsenior,fsb@google.com} arxiv:12.1128v1
More informationGenerating an appropriate sound for a video using WaveNet.
Australian National University College of Engineering and Computer Science Master of Computing Generating an appropriate sound for a video using WaveNet. COMP 8715 Individual Computing Project Taku Ueki
More informationThe Munich 2011 CHiME Challenge Contribution: BLSTM-NMF Speech Enhancement and Recognition for Reverberated Multisource Environments
The Munich 2011 CHiME Challenge Contribution: BLSTM-NMF Speech Enhancement and Recognition for Reverberated Multisource Environments Felix Weninger, Jürgen Geiger, Martin Wöllmer, Björn Schuller, Gerhard
More informationAnalysis and Op,miza,on of Mixed- Cri,cality Applica,ons on Par,,oned Distributed Architectures
Analysis and Op,miza,on of Mixed- Cri,cality Applica,ons on Par,,oned Distributed Architectures Domițian Tămaș- Selicean, Sorin Ovidiu Marinescu and Paul Pop Technical University of Denmark Outline MoBvaBon
More informationVISUAL ANALOGIES BETWEEN ATARI GAMES FOR STUDYING TRANSFER LEARNING IN RL
VISUAL ANALOGIES BETWEEN ATARI GAMES FOR STUDYING TRANSFER LEARNING IN RL Doron Sobol 1, Lior Wolf 1,2 & Yaniv Taigman 2 1 School of Computer Science, Tel-Aviv University 2 Facebook AI Research ABSTRACT
More informationVisual Thinking for Design. Han- Wei Shen Department of Computer Science and Engineering The Ohio State University
Visual Thinking for Design Han- Wei Shen Department of Computer Science and Engineering The Ohio State University MoBvaBon How am I going to aeract people s aeenbon to my Web page Product brochure MarkeBng
More informationCSE101: Algorithm Design and Analysis. Ragesh Jaiswal, CSE, UCSD
Longest increasing subsequence Problem Longest increasing subsequence: You are given a sequence of integers A[1], A[2],..., A[n] and you are asked to find a longest increasing subsequence of integers.
More informationMusic Recommendation using Recurrent Neural Networks
Music Recommendation using Recurrent Neural Networks Ashustosh Choudhary * ashutoshchou@cs.umass.edu Mayank Agarwal * mayankagarwa@cs.umass.edu Abstract A large amount of information is contained in the
More informationReinforcement Learning and the Frame Problem
Reinforcement Learning and the Frame Problem Roberto Santiago 1, George G. Lendaris 2 NW Computational Intelligence Laboratory, Portland State University, Portland, OR 97201 1 Systems Science, robes@pdx.edu
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 informationArtificial Intelligence: An overview
Artificial Intelligence: An overview Thomas Trappenberg January 4, 2009 Based on the slides provided by Russell and Norvig, Chapter 1 & 2 What is AI? Systems that think like humans Systems that act like
More informationA Hybrid Architecture using Cross Correlation and Recurrent Neural Networks for Acoustic Tracking in Robots
A Hybrid Architecture using Cross Correlation and Recurrent Neural Networks for Acoustic Tracking in Robots John C. Murray, Harry Erwin and Stefan Wermter Hybrid Intelligent Systems School for Computing
More informationREAL TIME EMULATION OF PARAMETRIC GUITAR TUBE AMPLIFIER WITH LONG SHORT TERM MEMORY NEURAL NETWORK
REAL TIME EMULATION OF PARAMETRIC GUITAR TUBE AMPLIFIER WITH LONG SHORT TERM MEMORY NEURAL NETWORK Thomas Schmitz and Jean-Jacques Embrechts 1 1 Department of Electrical Engineering and Computer Science,
More information7/22/14. Lecture Notes. Chapter 1 Welcome Aboard. Introduction to Computing Systems: From Bits and Gates to C and Beyond 2 nd Edition
Computer Science 210 Computer Systems 1 Lecture Notes Lecture 2 Introduction Credits: Slides adapted from Gregory T. Byrd, North Carolina State University Introduction to Computing Systems: From Bits and
More informationSno Projects List IEEE. High - Throughput Finite Field Multipliers Using Redundant Basis For FPGA And ASIC Implementations
Sno Projects List IEEE 1 High - Throughput Finite Field Multipliers Using Redundant Basis For FPGA And ASIC Implementations 2 A Generalized Algorithm And Reconfigurable Architecture For Efficient And Scalable
More informationComputability. What can be computed?
Computability What can be computed? Computability What can be computed? read/write tape 0 1 1 0 control Computability What can be computed? read/write tape 0 1 1 0 control Computability What can be computed?
More informationDigital Integrated CircuitDesign
Digital Integrated CircuitDesign Lecture 13 Building Blocks (Multipliers) Register Adder Shift Register Adib Abrishamifar EE Department IUST Acknowledgement This lecture note has been summarized and categorized
More informationEur Ing Dr. Lei Zhang Faculty of Engineering and Applied Science University of Regina Canada
Eur Ing Dr. Lei Zhang Faculty of Engineering and Applied Science University of Regina Canada The Second International Conference on Neuroscience and Cognitive Brain Information BRAININFO 2017, July 22,
More information(Theory-Practice-Lab) Credit BBM 1511 Introduction to Computer Engineering - 1 (2-0-0) 2
ARAS Brief Course Descriptions (Theory-Practice-Lab) Credit BBM 1511 Introduction to Computer Engineering - 1 (2-0-0) 2 Basic Concepts in Computer Science / Computer Systems and Peripherals / Introduction
More informationDeep Neural Networks (2) Tanh & ReLU layers; Generalisation and Regularisation
Deep Neural Networks (2) Tanh & ReLU layers; Generalisation and Regularisation Steve Renals Machine Learning Practical MLP Lecture 4 9 October 2018 MLP Lecture 4 / 9 October 2018 Deep Neural Networks (2)
More informationAutomata and Formal Languages - CM0081 Turing Machines
Automata and Formal Languages - CM0081 Turing Machines Andrés Sicard-Ramírez Universidad EAFIT Semester 2018-1 Turing Machines Alan Mathison Turing (1912 1954) Automata and Formal Languages - CM0081. Turing
More informationCSC321 Lecture 11: Convolutional Networks
CSC321 Lecture 11: Convolutional Networks Roger Grosse Roger Grosse CSC321 Lecture 11: Convolutional Networks 1 / 35 Overview What makes vision hard? Vison needs to be robust to a lot of transformations
More informationAn Efficient Implementation of Tower of Hanoi using Gray Codes
GRD Journals Global Research and Development Journal for Engineering National Conference on Computational Intelligence Systems (NCCIS 17) March 2017 e-issn: 2455-5703 An Efficient Implementation of Tower
More informationDeep learning architectures for music audio classification: a personal (re)view
Deep learning architectures for music audio classification: a personal (re)view Jordi Pons jordipons.me @jordiponsdotme Music Technology Group Universitat Pompeu Fabra, Barcelona Acronyms MLP: multi layer
More informationAnalog Computation for Next Generation AI
Analog Computation for Next Generation AI Dr. Hava Siegelmann DARPA/MTO DISTRIBUTION A. Approved for public release: distribution unlimited. Introduction: Hardware via Gordon Moore History: Moore's Law
More informationAre there alternatives to Sigmoid Hidden Units? MLP Lecture 6 Hidden Units / Initialisation 1
Are there alternatives to Sigmoid Hidden Units? MLP Lecture 6 Hidden Units / Initialisation 1 Hidden Unit Transfer Functions Initialising Deep Networks Steve Renals Machine Learning Practical MLP Lecture
More informationIntroduction to Artificial Intelligence
Introduction to Artificial Intelligence Christian Jacob jacob@cpsc.ucalgary.ca Department of Computer Science University of Calgary 1. What is Artificial Intelligence? How does the human brain work? What
More information2 TD-MoM ANALYSIS OF SYMMETRIC WIRE DIPOLE
Design of Microwave Antennas: Neural Network Approach to Time Domain Modeling of V-Dipole Z. Lukes Z. Raida Dept. of Radio Electronics, Brno University of Technology, Purkynova 118, 612 00 Brno, Czech
More informationChapter # 1: Introduction
Chapter # : Randy H. Katz University of California, erkeley May 993 ฉ R.H. Katz Transparency No. - The Elements of Modern Design Representations, Circuit Technologies, Rapid Prototyping ehaviors locks
More informationSequential program, state machine, Concurrent process models
INSIGHT Sequential program, state machine, Concurrent process models Finite State Machines, or automata, originated in computational theory and mathematical models in support of various fields of bioscience.
More informationMembrane Computing as Multi Turing Machines
Volume 4 No.8, December 2012 www.ijais.org Membrane Computing as Multi Turing Machines Mahmoud Abdelaziz Amr Badr Ibrahim Farag ABSTRACT A Turing machine (TM) can be adapted to simulate the logic of any
More informationIntroduction to Computer Engineering. CS/ECE 252, Spring 2013 Prof. Mark D. Hill Computer Sciences Department University of Wisconsin Madison
Introduction to Computer Engineering CS/ECE 252, Spring 2013 Prof. Mark D. Hill Computer Sciences Department University of Wisconsin Madison Chapter 1 Welcome Aboard Slides based on set prepared by Gregory
More information"Shape Grammars and the Generative Specification of Painting and Sculpture" by George Stiny and James Gips.
"Shape Grammars and the Generative Specification of Painting and Sculpture" by George Stiny and James Gips. Presented at IFIP Congress 71 in Ljubljana, Yugoslavia. Selected as the Best Submitted Paper.
More informationCSCI 2570 Introduction to Nanocomputing
CSCI 2570 Introduction to Nanocomputing DNA Tiling John E Savage Computing with DNA Prepare oligonucleotides ( program them ) Prepare solution with multiple strings. Only complementary substrings q and
More informationPose Invariant Face Recognition
Pose Invariant Face Recognition Fu Jie Huang Zhihua Zhou Hong-Jiang Zhang Tsuhan Chen Electrical and Computer Engineering Department Carnegie Mellon University jhuangfu@cmu.edu State Key Lab for Novel
More informationImplementing Logic with the Embedded Array
Implementing Logic with the Embedded Array in FLEX 10K Devices May 2001, ver. 2.1 Product Information Bulletin 21 Introduction Altera s FLEX 10K devices are the first programmable logic devices (PLDs)
More informationOutline. Introduction to AI. Artificial Intelligence. What is an AI? What is an AI? Agents Environments
Outline Introduction to AI ECE457 Applied Artificial Intelligence Fall 2007 Lecture #1 What is an AI? Russell & Norvig, chapter 1 Agents s Russell & Norvig, chapter 2 ECE457 Applied Artificial Intelligence
More informationOn the Use of Convolutional Neural Networks for Specific Emitter Identification
On the Use of Convolutional Neural Networks for Specific Emitter Identification Lauren Joy Wong Thesis submitted to the Faculty of the Virginia Polytechnic Institute and State University in partial fulfillment
More informationWhat this paper is about:
The Impact of Pipelining on Energy per Operation in Field-Programmable Gate Arrays Steve Wilton Department of Electrical and Computer Engineering University of British Columbia Vancouver, Canada Su-Shin
More informationWest Windsor-Plainsboro Regional School District Advanced Topics in Computer Science Grades 9-12
West Windsor-Plainsboro Regional School District Advanced Topics in Computer Science Grades 9-12 Unit 1: Recursion Content Area: Technology Course & Grade Level: Advanced Topics in Computer Science, 9
More informationCS344: Introduction to Artificial Intelligence (associated lab: CS386)
CS344: Introduction to Artificial Intelligence (associated lab: CS386) Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture 1: Introduction 3 rd Jan, 2011 Basic Facts Faculty instructor: Dr. Pushpak Bhattacharyya
More informationHeads-up Limit Texas Hold em Poker Agent
Heads-up Limit Texas Hold em Poker Agent Nattapoom Asavareongchai and Pin Pin Tea-mangkornpan CS221 Final Project Report Abstract Our project aims to create an agent that is able to play heads-up limit
More informationDeep Learning for Autonomous Driving
Deep Learning for Autonomous Driving Shai Shalev-Shwartz Mobileye IMVC dimension, March, 2016 S. Shalev-Shwartz is also affiliated with The Hebrew University Shai Shalev-Shwartz (MobilEye) DL for Autonomous
More informationThe REAL Problem With Artificial Intelligence:
The REAL Problem With Artificial Intelligence: A Lack of Understanding Dr. Frank Jones January 2016 Outline of This Talk Beginning (YOU ARE HERE) Middle End Definition: Artificial Intelligence: The branch
More informationECS 20 (Spring 2013) Phillip Rogaway Lecture 1
ECS 20 (Spring 2013) Phillip Rogaway Lecture 1 Today: Introductory comments Some example problems Announcements course information sheet online (from my personal homepage: Rogaway ) first HW due Wednesday
More informationEnergy Consumption Prediction for Optimum Storage Utilization
Energy Consumption Prediction for Optimum Storage Utilization Eric Boucher, Robin Schucker, Jose Ignacio del Villar December 12, 2015 Introduction Continuous access to energy for commercial and industrial
More informationSection 8.1. Sequences and Series
Section 8.1 Sequences and Series Sequences Definition A sequence is a list of numbers. Definition A sequence is a list of numbers. A sequence could be finite, such as: 1, 2, 3, 4 Definition A sequence
More informationAdaptive Kalman Filter based Channel Equalizer
Adaptive Kalman Filter based Bharti Kaushal, Agya Mishra Department of Electronics & Communication Jabalpur Engineering College, Jabalpur (M.P.), India Abstract- Equalization is a necessity of the communication
More informationEE 280 Introduction to Digital Logic Design
EE 280 Introduction to Digital Logic Design Lecture 1. Introduction EE280 Lecture 1 1-1 Instructors: EE 280 Introduction to Digital Logic Design Dr. Lukasz Kurgan (section A1) office: ECERF 6 th floor,
More informationTechnical framework of Operating System using Turing Machines
Reviewed Paper Technical framework of Operating System using Turing Machines Paper ID IJIFR/ V2/ E2/ 028 Page No 465-470 Subject Area Computer Science Key Words Turing, Undesirability, Complexity, Snapshot
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 informationCSE 355: Human-aware Robo.cs Introduction to Theoretical Computer Science
CSE 355: Introduction to Theoretical Computer Science Instructor: Dr. Yu ( Tony ) Zhang Lecture: WGHL101, Tue/Thu, 3:00 4:15 PM Office Hours: BYENG 594, Tue/Thu, 5:00 6:00PM 1 Subject of interest? 2 Robo.cs
More informationCPS331 Lecture: Agents and Robots last revised April 27, 2012
CPS331 Lecture: Agents and Robots last revised April 27, 2012 Objectives: 1. To introduce the basic notion of an agent 2. To discuss various types of agents 3. To introduce the subsumption architecture
More informationCopyright The McGraw-Hill Companies, Inc. Permission required for reproduction or display. Computing Layers
Chapter 3 Digital Logic Structures Original slides from Gregory Byrd, North Carolina State University Modified by Chris Wilcox, Sanjay Rajopadhye Colorado State University Computing Layers Problems Algorithms
More informationDiversity and Freedom: A Fundamental Tradeoff in Multiple Antenna Channels
Diversity and Freedom: A Fundamental Tradeoff in Multiple Antenna Channels Lizhong Zheng and David Tse Department of EECS, U.C. Berkeley Feb 26, 2002 MSRI Information Theory Workshop Wireless Fading Channels
More informationIntro to Artificial Intelligence Lecture 1. Ahmed Sallam { }
Intro to Artificial Intelligence Lecture 1 Ahmed Sallam { http://sallam.cf } Purpose of this course Understand AI Basics Excite you about this field Definitions of AI Thinking Rationally Acting Humanly
More informationunderstand the hardware and software components that make up computer systems, and how they communicate with one another and with other systems
Subject Knowledge Audit & Tracker Computer Science 2017-18 Purpose of the Audit Your indications of specialist subject knowledge strengths and areas for development are used as a basis for discussion during
More informationKey-Words: - NARX Neural Network; Nonlinear Loads; Shunt Active Power Filter; Instantaneous Reactive Power Algorithm
Parameter control scheme for active power filter based on NARX neural network A. Y. HATATA, M. ELADAWY, K. SHEBL Department of Electric Engineering Mansoura University Mansoura, EGYPT a_hatata@yahoo.com
More informationDr. Vincent Lau
Dr. Vincent Lau vincentmklau@astri.org 2015-6-25 Hong Kong Applied Science and Technology Research Institute (ASTRI) Largest HK R&D centre created by HK Government 500+ staffs with 30% Ph.D., 50% Master
More informationNEURAL NETWORK BASED MAXIMUM POWER POINT TRACKING
NEURAL NETWORK BASED MAXIMUM POWER POINT TRACKING 3.1 Introduction This chapter introduces concept of neural networks, it also deals with a novel approach to track the maximum power continuously from PV
More informationDHANALAKSHMI COLLEGE OF ENGINEERING, CHENNAI
DHANALAKSHMI COLLEGE OF ENGINEERING, CHENNAI Department of Computer Science and Engineering CS6503 THEORY OF COMPUTATION 2 Mark Questions & Answers Year / Semester: III / V Regulation: 2013 Academic year:
More informationCitation for published version (APA): Nutma, T. A. (2010). Kac-Moody Symmetries and Gauged Supergravity Groningen: s.n.
University of Groningen Kac-Moody Symmetries and Gauged Supergravity Nutma, Teake IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please
More informationMaximum Contiguous Subarray Sum Problems
Project Report, by Lirong TAN Maximum Contiguous Subarray Sum Problems Contents 1 Abstract 2 2 Part 1: Maximum Subsequence Sum Problem 2 2.1 Problem Formulation....................................... 2
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 informationCS10: The Beauty and Joy of Computing Lecture #6: Algorithms
CS10: The Beauty and Joy of Computing Lecture #6: Algorithms In the news: A recently security study suggests that a computer worm that ran rampant several years ago is still running on many machines, including
More informationTransistors, Gates and Busses 3/21/01 Lecture #
Transistors, Gates and Busses 3/2/ Lecture #8 6.7 The goal for today is to understand a bit about how a computer actually works: how it stores, adds, and communicates internally! How transistors make gates!
More informationHigher Order Rotation Spreading Matrix for Block Spread OFDM
University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 27 Higher Order Rotation Spreading Matrix for Block Spread OFDM Ibrahim
More informationEmergence of Purposive and Grounded Communication through Reinforcement Learning
Emergence of Purposive and Grounded Communication through Reinforcement Learning Katsunari Shibata and Kazuki Sasahara Dept. of Electrical & Electronic Engineering, Oita University, 7 Dannoharu, Oita 87-1192,
More informationCHAPTER 8: EXTENDED TETRACHORD CLASSIFICATION
CHAPTER 8: EXTENDED TETRACHORD CLASSIFICATION Chapter 7 introduced the notion of strange circles: using various circles of musical intervals as equivalence classes to which input pitch-classes are assigned.
More information124 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 45, NO. 1, JANUARY 1997
124 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 45, NO. 1, JANUARY 1997 Blind Adaptive Interference Suppression for the Near-Far Resistant Acquisition and Demodulation of Direct-Sequence CDMA Signals
More informationCSE101: Design and Analysis of Algorithms. Ragesh Jaiswal, CSE, UCSD
Course Overview Graph Algorithms Algorithm Design Techniques: Greedy Algorithms Divide and Conquer Dynamic Programming Network Flows Computational Intractability Main Ideas Main idea: Break the given
More informationLesson 08. Convolutional Neural Network. Ing. Marek Hrúz, Ph.D. Katedra Kybernetiky Fakulta aplikovaných věd Západočeská univerzita v Plzni.
Lesson 08 Convolutional Neural Network Ing. Marek Hrúz, Ph.D. Katedra Kybernetiky Fakulta aplikovaných věd Západočeská univerzita v Plzni Lesson 08 Convolution we will consider 2D convolution the result
More informationImage Manipulation Detection using Convolutional Neural Network
Image Manipulation Detection using Convolutional Neural Network Dong-Hyun Kim 1 and Hae-Yeoun Lee 2,* 1 Graduate Student, 2 PhD, Professor 1,2 Department of Computer Software Engineering, Kumoh National
More informationBrain-inspired information processing: Beyond the Turing machine
Brain-inspired information processing: Beyond the Turing machine Herbert Jaeger Jacobs University Bremen Part 1: That is Computing! Turing computability Image sources are given on last slide Deep historical
More informationMultiple input gates. The AND gate
Multiple input gates Inverters and buffers exhaust the possibilities for single-input gate circuits. What more can be done with a single logic signal but to buffer it or invert it? To explore more logic
More informationChapter 3 Digital Logic Structures
Chapter 3 Digital Logic Structures Transistor: Building Block of Computers Microprocessors contain millions of transistors Intel Pentium 4 (2000): 48 million IBM PowerPC 750FX (2002): 38 million IBM/Apple
More informationAn Efficient Approach to Face Recognition Using a Modified Center-Symmetric Local Binary Pattern (MCS-LBP)
, pp.13-22 http://dx.doi.org/10.14257/ijmue.2015.10.8.02 An Efficient Approach to Face Recognition Using a Modified Center-Symmetric Local Binary Pattern (MCS-LBP) Anusha Alapati 1 and Dae-Seong Kang 1
More informationSCUBA-2. Low Pass Filtering
Physics and Astronomy Dept. MA UBC 07/07/2008 11:06:00 SCUBA-2 Project SC2-ELE-S582-211 Version 1.3 SCUBA-2 Low Pass Filtering Revision History: Rev. 1.0 MA July 28, 2006 Initial Release Rev. 1.1 MA Sept.
More informationCPS331 Lecture: Agents and Robots last revised November 18, 2016
CPS331 Lecture: Agents and Robots last revised November 18, 2016 Objectives: 1. To introduce the basic notion of an agent 2. To discuss various types of agents 3. To introduce the subsumption architecture
More information