CSE/NEURO 528 Lecture 13: Reinforcement Learning & Course Review (Chapter 9)
|
|
- Shanon Scott
- 5 years ago
- Views:
Transcription
1 CSE/NEURO 528 Lecure 13: Reinforceen Learning & Course Review Chaper 9 Aniaion: To Creed, SJU 1 Early Resuls: Pavlov and his Dog F Classical Pavlovian condiioning experiens F Training: Bell Food F Afer: Bell Salivae F Condiioned siulus bell predics fuure reward food Iage: Wikiedia Coons; Aniaion: To Creed, SJU 2
2 Predicing Delayed Rewards F How do we predic rewards delivered soe ie afer a siulus is presened? F Given: Many rials, each of lengh T ie seps F Tie wihin a rial: 0 T wih siulus u and reward r a each ie sep Noe: r can be zero for soe F We would like a neuron whose oupu v predics he expeced oal fuure reward saring fro ie v T 0 r rials 3 Learning o Predic Fuure Rewards F Use a se of synapic weighs w and predic based on all pas siuli u: v w u 0 F Learn weighs w ha iniize error: T 0 Linear filer! r v 2 v w 0 w u u 1 u0 Can we iniize his using gradien descen and dela rule? wt Yes, BUT fuure rewards are no ye available! 4
3 5 Teporal Difference TD Learning F Key Idea: Rewrie error funcion o ge rid of fuure ers: F Teporal Difference TD Learning: v v r v r r v r T T ] 1 [ u v v r w Expeced fuure reward Predicion Miniize his using gradien descen! 6 Predicing Fuure Rewards: TD Learning Siulus a = 100 and reward a = 200 Predicion error for each ie sep over any rials Iage Source: Dayan & Abbo exbook
4 Possible Reward Predicion Error Signal in he Priae Brain Dopainergic cells in Venral Tegenal Area VTA Reward Predicion error δ? [ r v 1 v ] Before Training Afer Training [ 0 v v 1] No error v r v 1 [ r v 1 v ] 0 7 Iage Source: Dayan & Abbo exbook More Evidence for Predicion Error Signals Dopainergic cells in VTA afer Training Negaive error r 0, v 1 0 [ r v 1 v ] v Reward expeced bu no delivered 8 Iage Source: Dayan & Abbo exbook
5 Reinforceen Learning: Acing o Maxiize Rewards Agen Sae u Reward r Acion a Environen 9 The Proble Sae u Reward r Agen Environen Acion a Learn a sae-o-acion apping or policy : u a which axiizes he expeced oal fuure reward: T 0 r rials 10
6 Exaple: Ra in a barn Saes = locaions A, B, or C Acions= L go lef or R go righ If he ra chooses L or R a rando rando policy, wha is he expeced reward or value v for each sae? 11 Iage Source: Dayan & Abbo exbook Policy Evaluaion For rando policy: 1 1 v B v C v A v B v C Le value of sae u vu = weigh wu Can learn value of saes using TD learning: w u w u [ r u v u' v u] Locaion, acion new locaion i.e., u,a u 12
7 TD Learning of Values for Rando Policy Once I know he values, I can pick he acion ha leads o he higher valued sae! For all hree, = Iage Source: Dayan & Abbo exbook Selecing Acions based on Values Values ac as surrogae iediae rewards Locally opial choice leads o globally opial policy for Markov environens Relaed o Dynaic Prograing 14
8 F Puing i all ogeher: Acor-Criic Learning Two separae coponens: Acor selecs acion and ainains policy and Criic ainains value of each sae 1. Criic Learning Policy Evaluaion : Value of sae u = vu = wu w u w u [ r u v u' v u] 2. Acor Learning Policy Iproveen : P a; u For all acions a : Qa' u Qa' u [ r u v u' v u] aa' 3. Repea 1 and 2 exp Qa u exp Q u b b Probabilisically selec an acion a a sae u sae as TD rule P a'; u 15 Acor-Criic Learning in our Barn Exaple Probabiliy of going Lef a each locaion 16 Iage Source: Dayan & Abbo exbook
9 Possible Ipleenaion of he Acor-Criic Model in he Basal Ganglia Corex Sae Esiae STN Sriau GPe DA SNc Hidden Layer Value Acor Criic TD error GPi/SNr Acion Thalaus 17 See Suppleenary Maerials for references Reinforceen learning has been applied o any real-world probles! Exaple: Google s AlphaGo beas huan chapion in Go, Auonoous Helicoper Fligh learned fro huan deonsraions Videos and papers a: hp://heli.sanford.edu/ 18
10 Course Suary Where have we been? Course Highlighs Where do we go fro here? Challenges and Open Probles Furher Reading 19 Wha is he neural code? Wha is he naure of he code? Represening he spiking oupu: single cells vs populaions raes vs spike ies vs inervals Wha feaures of he siulus does he neural syse represen? 20
11 Encoding and decoding neural inforaion Encoding: building funcional odels of neurons/neural syses and predicing he spiking oupu given he siulus Decoding: wha can we say abou he siulus given wha we observe fro he neuron or neural populaion? 21 Inforaion axiizaion as a design principle of he nervous syse 22
12 Biophysical Models of Neurons Volage dependen ransier dependen synapic Ca dependen 23 The neural equivalen circui Oh s law: and Kirchhoff s law - Capaciive curren Ionic currens Exernally applied curren 24
13 Siplified odels: inegrae-and-fire V Inegrae-and- Fire Model dv d V E I If V > V hreshold Spike Then rese: V = V rese L e R 25 Modeling Neworks of Neurons dv v F Wu Mv d Oupu Decay Inpu Feedback 26
14 Unsupervised Learning For linear neuron: Basic Hebb Rule: T v w u u dw w uv d Average effec over any inpus: dw w d uv Qw Q is he inpu correlaion arix: Q uu T T w Hebb rule perfors principal coponen analysis PCA w 27 The Connecion o Saisics Unsupervised learning = learning he hidden causes of inpu daa Generaive odel Causes v Daa u p[ v u; G] poserior Recogniion odel p[ u v; G] daa likelihood Use EM algorih for learning G = v, v Causes of clusered daa Causes of naural iages 28
15 Generaive Models Droning lecure Lack of sleep Maheaical derivaions 29 Supervised Learning Backpropagaion for Mulilayered Neworks v i g j W g ij k w u jk k u k x j Goal: Find W and w ha iniize errors: E W W ij ij, w jk 1 2 E Wij W ij, i d i v i Gradien descen learning rules: Dela rule 2 Desired oupu w jk w jk E w jk w jk E x j x w j jk Chain rule 30
16 Reinforceen Learning Learning o predic rewards: w w r v u Learning o predic delayed rewards TD learning: Acor-Criic Learning: Criic learns value of each sae using TD learning Acor learns bes acions based on value of nex sae using he TD error hp://eployees.csbsju.edu/creed/pb/pdogani.hl w w [ r v 1 v ] u The Fuure: Challenges and Open Probles How do neurons encode inforaion? Topics: Synchrony, Spike-iing based learning, Dynaic synapses Does a neuron s srucure confer copuaional advanages? Topics: Role of channel dynaics, dendries, plasiciy in channels and heir densiy How do neworks ipleen copuaional principles such as efficien coding and Bayesian inference? How do neworks learn opial represenaions of heir environen and engage in purposeful behavior? Topics: Unsupervised/reinforceen/iiaion learning 32
17 Furher Reading for Spring and beyond Spikes: Exploring he Neural Code, F. Rieke e al., MIT Press, 1997 The Biophysics of Copuaion, C. Koch, Oxford Universiy Press, 1999 Large-Scale Neuronal Theories of he Brain, C. Koch and J. L. Davis, MIT Press, 1994 Probabilisic Models of he Brain, R. Rao e al., MIT Press, 2002 Bayesian Brain, K. Doya e al., MIT Press, 2007 Reinforceen Learning: An Inroducion, R. Suon and A. Baro, MIT Press, Nex wo classes: Projec presenaions! Keep your presenaion shor: ~7-8 slides, ins ins/group wih quesions Inroducion, Background, Mehods, Resuls, Conclusion Slides: Bring your slides on a USB sick o use he class lapop Windows achine OR Bring your own lapop esp if you have videos ec. Projecs repors pages oal due March 12 by eail o boh Adrienne, Rich, and Raj before idnigh 34
18 Have a grea weekend! 35
CSE/NB 528 Lecture 14: Reinforcement Learning (Chapter 9)
CSE/NB 528 Lecure 14: Reinforcemen Learning Chaper 9 Image from hp://clasdean.la.asu.edu/news/images/ubep2001/neuron3.jpg Lecure figures are from Dayan & Abbo s book hp://people.brandeis.edu/~abbo/book/index.hml
More informationCSE/NB 528 Lecture 14: From Supervised to Reinforcement Learning (Chapter 9) R. Rao, 528: Lecture 14
CSE/NB 58 Lecure 14: From Supervised o Reinforcemen Learning Chaper 9 1 Recall from las ime: Sigmoid Neworks Oupu v T g w u g wiui w Inpu nodes u = u 1 u u 3 T i Sigmoid oupu funcion: 1 g a 1 a e 1 ga
More informationChapter 21. Reinforcement Learning. The Reinforcement Learning Agent
CSE 47 Chaper Reinforcemen Learning The Reinforcemen Learning Agen Agen Sae u Reward r Acion a Enironmen CSE AI Faculy Why reinforcemen learning Programming an agen o drie a car or fly a helicoper is ery
More informationCSE/NB 528 Final Lecture: All Good Things Must. CSE/NB 528: Final Lecture
CSE/NB 528 Final Lecture: All Good Things Must 1 Course Summary Where have we been? Course Highlights Where do we go from here? Challenges and Open Problems Further Reading 2 What is the neural code? What
More informationCSE/NEUBEH 528 Modeling Synapses and Networks (Chapter 7)
CSE/NEUBEH 528 Modeling Synape and Nework (Chaper 7) Iage fro Wikiedia Coon 1 Lecure figure are fro Dayan & Ao ook Coure Suary (hu far) F Neural Encoding Wha ake a neuron fire? (STA, covariance analyi)
More informationConnectionist Classifier System Based on Accuracy in Autonomous Agent Control
Connecionis Classifier Syse Based on Accuracy in Auonoous Agen Conrol A S Vasilyev Decision Suppor Syses Group Riga Technical Universiy /4 Meza sree Riga LV-48 Lavia E-ail: serven@apollolv Absrac In his
More informationClassical Conditioning IV: TD learning in the brain
Classical Condiioning IV: TD learning in he brain PSY/NEU338: Animal learning and decision making: Psychological, compuaional and neural perspecives recap: Marr s levels of analysis David Marr (1945-1980)
More informationMapping in Dynamic Environments
Mapping in Dynaic Environens Wolfra Burgard Universiy of Freiburg, Gerany Mapping is a Key Technology for Mobile Robos Robos can robusly navigae when hey have a ap. Robos have been shown o being able o
More informationRL Lecture 7: Eligibility Traces. R. S. Sutton and A. G. Barto: Reinforcement Learning: An Introduction 1
RL Lecure 7: Eligibiliy Traces R. S. Suon and A. G. Baro: Reinforcemen Learning: An Inroducion 1 N-sep TD Predicion Idea: Look farher ino he fuure when you do TD backup (1, 2, 3,, n seps) R. S. Suon and
More informationThe field of mathematics has made tremendous impact on the study of
A Populaion Firing Rae Model of Reverberaory Aciviy in Neuronal Neworks Zofia Koscielniak Carnegie Mellon Universiy Menor: Dr. G. Bard Ermenrou Universiy of Pisburgh Inroducion: The field of mahemaics
More informationTIME DELAY BASEDUNKNOWN INPUT OBSERVER DESIGN FOR NETWORK CONTROL SYSTEM
TIME DELAY ASEDUNKNOWN INPUT OSERVER DESIGN FOR NETWORK CONTROL SYSTEM Siddhan Chopra J.S. Laher Elecrical Engineering Deparen NIT Kurukshera (India Elecrical Engineering Deparen NIT Kurukshera (India
More informationLinear Time-invariant systems, Convolution, and Cross-correlation
Linear Time-invarian sysems, Convoluion, and Cross-correlaion (1) Linear Time-invarian (LTI) sysem A sysem akes in an inpu funcion and reurns an oupu funcion. x() T y() Inpu Sysem Oupu y() = T[x()] An
More informationGeorey E. Hinton. University oftoronto. Technical Report CRG-TR February 22, Abstract
Parameer Esimaion for Linear Dynamical Sysems Zoubin Ghahramani Georey E. Hinon Deparmen of Compuer Science Universiy oftorono 6 King's College Road Torono, Canada M5S A4 Email: zoubin@cs.orono.edu Technical
More informationLecture 28: Single Stage Frequency response. Context
Lecure 28: Single Sage Frequency response Prof J. S. Sih Conex In oday s lecure, we will coninue o look a he frequency response of single sage aplifiers, saring wih a ore coplee discussion of he CS aplifier,
More informationReading from Young & Freedman: For this topic, read sections 25.4 & 25.5, the introduction to chapter 26 and sections 26.1 to 26.2 & 26.4.
PHY1 Elecriciy Topic 7 (Lecures 1 & 11) Elecric Circuis n his opic, we will cover: 1) Elecromoive Force (EMF) ) Series and parallel resisor combinaions 3) Kirchhoff s rules for circuis 4) Time dependence
More informationDeep Learning: Theory, Techniques & Applications - Recurrent Neural Networks -
Deep Learning: Theory, Techniques & Applicaions - Recurren Neural Neworks - Prof. Maeo Maeucci maeo.maeucci@polimi.i Deparmen of Elecronics, Informaion and Bioengineering Arificial Inelligence and Roboics
More informationChapter 8 The Complete Response of RL and RC Circuits
Chaper 8 The Complee Response of RL and RC Circuis Seoul Naional Universiy Deparmen of Elecrical and Compuer Engineering Wha is Firs Order Circuis? Circuis ha conain only one inducor or only one capacior
More information1 Widrow-Hoff Algorithm
COS 511: heoreical Machine Learning Lecurer: Rob Schapire Lecure # 18 Scribe: Shaoqing Yang April 10, 014 1 Widrow-Hoff Algorih Firs le s review he Widrow-Hoff algorih ha was covered fro las lecure: Algorih
More informationIntroduction to Numerical Analysis. In this lesson you will be taken through a pair of techniques that will be used to solve the equations of.
Inroducion o Nuerical Analysis oion In his lesson you will be aen hrough a pair of echniques ha will be used o solve he equaions of and v dx d a F d for siuaions in which F is well nown, and he iniial
More information8. Basic RL and RC Circuits
8. Basic L and C Circuis This chaper deals wih he soluions of he responses of L and C circuis The analysis of C and L circuis leads o a linear differenial equaion This chaper covers he following opics
More informationNature Neuroscience: doi: /nn Supplementary Figure 1. Spike-count autocorrelations in time.
Supplemenary Figure 1 Spike-coun auocorrelaions in ime. Normalized auocorrelaion marices are shown for each area in a daase. The marix shows he mean correlaion of he spike coun in each ime bin wih he spike
More informationZürich. ETH Master Course: L Autonomous Mobile Robots Localization II
Roland Siegwar Margaria Chli Paul Furgale Marco Huer Marin Rufli Davide Scaramuzza ETH Maser Course: 151-0854-00L Auonomous Mobile Robos Localizaion II ACT and SEE For all do, (predicion updae / ACT),
More informationReading. Lecture 28: Single Stage Frequency response. Lecture Outline. Context
Reading Lecure 28: Single Sage Frequency response Prof J. S. Sih Reading: We are discussing he frequency response of single sage aplifiers, which isn reaed in he ex unil afer uli-sae aplifiers (beginning
More informationIntroduction to Probability and Statistics Slides 4 Chapter 4
Inroducion o Probabiliy and Saisics Slides 4 Chaper 4 Ammar M. Sarhan, asarhan@mahsa.dal.ca Deparmen of Mahemaics and Saisics, Dalhousie Universiy Fall Semeser 8 Dr. Ammar Sarhan Chaper 4 Coninuous Random
More informationCHAPTER 10 VALIDATION OF TEST WITH ARTIFICAL NEURAL NETWORK
175 CHAPTER 10 VALIDATION OF TEST WITH ARTIFICAL NEURAL NETWORK 10.1 INTRODUCTION Amongs he research work performed, he bes resuls of experimenal work are validaed wih Arificial Neural Nework. From he
More informationDimitri Solomatine. D.P. Solomatine. Data-driven modelling (part 2). 2
Daa-driven modelling. Par. Daa-driven Arificial di Neural modelling. Newors Par Dimiri Solomaine Arificial neural newors D.P. Solomaine. Daa-driven modelling par. 1 Arificial neural newors ANN: main pes
More information6.01: Introduction to EECS I Lecture 8 March 29, 2011
6.01: Inroducion o EES I Lecure 8 March 29, 2011 6.01: Inroducion o EES I Op-Amps Las Time: The ircui Absracion ircuis represen sysems as connecions of elemens hrough which currens (hrough variables) flow
More informationVehicle Arrival Models : Headway
Chaper 12 Vehicle Arrival Models : Headway 12.1 Inroducion Modelling arrival of vehicle a secion of road is an imporan sep in raffic flow modelling. I has imporan applicaion in raffic flow simulaion where
More informationEEEB113 CIRCUIT ANALYSIS I
9/14/29 1 EEEB113 CICUIT ANALYSIS I Chaper 7 Firs-Order Circuis Maerials from Fundamenals of Elecric Circuis 4e, Alexander Sadiku, McGraw-Hill Companies, Inc. 2 Firs-Order Circuis -Chaper 7 7.2 The Source-Free
More informationLecture 18 GMM:IV, Nonlinear Models
Lecure 8 :IV, Nonlinear Models Le Z, be an rx funcion of a kx paraeer vecor, r > k, and a rando vecor Z, such ha he r populaion oen condiions also called esiain equaions EZ, hold for all, where is he rue
More informationCode-specific policy gradient rules for spiking neurons
Code-specific policy gradien rules for spiking neurons Henning Sprekeler Guillaume Hennequin Wulfram Gersner Laboraory for Compuaional Neuroscience École Polyechnique Fédérale de Lausanne 115 Lausanne
More informationHidden Markov Models
Hidden Markov Models Probabilisic reasoning over ime So far, we ve mosly deal wih episodic environmens Excepions: games wih muliple moves, planning In paricular, he Bayesian neworks we ve seen so far describe
More informationRandom Walk with Anti-Correlated Steps
Random Walk wih Ani-Correlaed Seps John Noga Dirk Wagner 2 Absrac We conjecure he expeced value of random walks wih ani-correlaed seps o be exacly. We suppor his conjecure wih 2 plausibiliy argumens and
More informationR.#W.#Erickson# Department#of#Electrical,#Computer,#and#Energy#Engineering# University#of#Colorado,#Boulder#
.#W.#Erickson# Deparmen#of#Elecrical,#Compuer,#and#Energy#Engineering# Universiy#of#Colorado,#Boulder# Chaper 2 Principles of Seady-Sae Converer Analysis 2.1. Inroducion 2.2. Inducor vol-second balance,
More informationBlock Diagram of a DCS in 411
Informaion source Forma A/D From oher sources Pulse modu. Muliplex Bandpass modu. X M h: channel impulse response m i g i s i Digial inpu Digial oupu iming and synchronizaion Digial baseband/ bandpass
More informationRC, RL and RLC circuits
Name Dae Time o Complee h m Parner Course/ Secion / Grade RC, RL and RLC circuis Inroducion In his experimen we will invesigae he behavior of circuis conaining combinaions of resisors, capaciors, and inducors.
More informationArtificial Neural Networks for Nonlinear Dynamic Response Simulation in Mechanical Systems
Downloaded fro orbi.du.d on: Nov 09, 08 Arificial Neural Newors for Nonlinear Dynaic Response Siulaion in Mechanical Syses Chrisiansen, Niels Hørbye; Høgsberg, Jan Becer; Winher, Ole Published in: Proceedings
More informationEnsamble methods: Boosting
Lecure 21 Ensamble mehods: Boosing Milos Hauskrech milos@cs.pi.edu 5329 Senno Square Schedule Final exam: April 18: 1:00-2:15pm, in-class Term projecs April 23 & April 25: a 1:00-2:30pm in CS seminar room
More informationEnsamble methods: Bagging and Boosting
Lecure 21 Ensamble mehods: Bagging and Boosing Milos Hauskrech milos@cs.pi.edu 5329 Senno Square Ensemble mehods Mixure of expers Muliple base models (classifiers, regressors), each covers a differen par
More informationLearning Objectives: Practice designing and simulating digital circuits including flip flops Experience state machine design procedure
Lab 4: Synchronous Sae Machine Design Summary: Design and implemen synchronous sae machine circuis and es hem wih simulaions in Cadence Viruoso. Learning Objecives: Pracice designing and simulaing digial
More informationSpring Ammar Abu-Hudrouss Islamic University Gaza
Chaper 7 Reed-Solomon Code Spring 9 Ammar Abu-Hudrouss Islamic Universiy Gaza ١ Inroducion A Reed Solomon code is a special case of a BCH code in which he lengh of he code is one less han he size of he
More informationThe Operational Semantics of Hybrid Systems
The Operaional Seanics of Hybrid Syses Edward A. Lee Professor, Chair of EE, and Associae Chair of EECS, UC Berkeley Wih conribuions fro: Ada Caaldo, Jie Liu, Xiaojun Liu, Elefherios Masikoudis, and Haiyang
More informationAttention-Gated Reinforcement Learning in Neural Networks A Unified View
Aenion-Gaed Reinforcemen Learning in Neural Neworks A Unified View Tobias Brosch, Friedhelm Schwenker, and Heiko Neumann Insiue of Neural Informaion Processing, Universiy of Ulm, 89069 Ulm, Germany {obias.brosch,friedhelm.schwenker,heiko.neumann}@uni-ulm.de
More information5.2. The Natural Logarithm. Solution
5.2 The Naural Logarihm The number e is an irraional number, similar in naure o π. Is non-erminaing, non-repeaing value is e 2.718 281 828 59. Like π, e also occurs frequenly in naural phenomena. In fac,
More informationChapter 2: Principles of steady-state converter analysis
Chaper 2 Principles of Seady-Sae Converer Analysis 2.1. Inroducion 2.2. Inducor vol-second balance, capacior charge balance, and he small ripple approximaion 2.3. Boos converer example 2.4. Cuk converer
More informationElectrical and current self-induction
Elecrical and curren self-inducion F. F. Mende hp://fmnauka.narod.ru/works.hml mende_fedor@mail.ru Absrac The aricle considers he self-inducance of reacive elemens. Elecrical self-inducion To he laws of
More information( ) ( ) if t = t. It must satisfy the identity. So, bulkiness of the unit impulse (hyper)function is equal to 1. The defining characteristic is
UNIT IMPULSE RESPONSE, UNIT STEP RESPONSE, STABILITY. Uni impulse funcion (Dirac dela funcion, dela funcion) rigorously defined is no sricly a funcion, bu disribuion (or measure), precise reamen requires
More informationChapter 7 Response of First-order RL and RC Circuits
Chaper 7 Response of Firs-order RL and RC Circuis 7.- The Naural Response of RL and RC Circuis 7.3 The Sep Response of RL and RC Circuis 7.4 A General Soluion for Sep and Naural Responses 7.5 Sequenial
More information23.2. Representing Periodic Functions by Fourier Series. Introduction. Prerequisites. Learning Outcomes
Represening Periodic Funcions by Fourier Series 3. Inroducion In his Secion we show how a periodic funcion can be expressed as a series of sines and cosines. We begin by obaining some sandard inegrals
More informationCHAPTER 12 DIRECT CURRENT CIRCUITS
CHAPTER 12 DIRECT CURRENT CIUITS DIRECT CURRENT CIUITS 257 12.1 RESISTORS IN SERIES AND IN PARALLEL When wo resisors are conneced ogeher as shown in Figure 12.1 we said ha hey are conneced in series. As
More information1. Calibration factor
Annex_C_MUBDandP_eng_.doc, p. of pages Annex C: Measureen uncerainy of he oal heigh of profile of a deph-seing sandard ih he sandard deviaion of he groove deph as opography er In his exaple, he uncerainy
More informationSolutions for Assignment 2
Faculy of rs and Science Universiy of Torono CSC 358 - Inroducion o Compuer Neworks, Winer 218 Soluions for ssignmen 2 Quesion 1 (2 Poins): Go-ack n RQ In his quesion, we review how Go-ack n RQ can be
More informationLectures 29 and 30 BIQUADRATICS AND STATE SPACE OP AMP REALIZATIONS. I. Introduction
EE-202/445, 3/18/18 9-1 R. A. DeCarlo Lecures 29 and 30 BIQUADRATICS AND STATE SPACE OP AMP REALIZATIONS I. Inroducion 1. The biquadraic ransfer funcion has boh a 2nd order numeraor and a 2nd order denominaor:
More informationLabQuest 24. Capacitors
Capaciors LabQues 24 The charge q on a capacior s plae is proporional o he poenial difference V across he capacior. We express his wih q V = C where C is a proporionaliy consan known as he capaciance.
More informationTwo Popular Bayesian Estimators: Particle and Kalman Filters. McGill COMP 765 Sept 14 th, 2017
Two Popular Bayesian Esimaors: Paricle and Kalman Filers McGill COMP 765 Sep 14 h, 2017 1 1 1, dx x Bel x u x P x z P Recall: Bayes Filers,,,,,,, 1 1 1 1 u z u x P u z u x z P Bayes z = observaion u =
More informationLab 10: RC, RL, and RLC Circuits
Lab 10: RC, RL, and RLC Circuis In his experimen, we will invesigae he behavior of circuis conaining combinaions of resisors, capaciors, and inducors. We will sudy he way volages and currens change in
More informationDecision Tree Learning. Decision Tree Learning. Decision Trees. Decision Trees: Operation. Blue slides: Mitchell. Orange slides: Alpaydin Humidity
Decision Tree Learning Decision Tree Learning Blue slides: Michell Oulook Orange slides: Alpaydin Huidiy Sunny Overcas Rain ral Srong Learn o approxiae discree-valued arge funcions. Sep-by-sep decision
More informationObject tracking: Using HMMs to estimate the geographical location of fish
Objec racking: Using HMMs o esimae he geographical locaion of fish 02433 - Hidden Markov Models Marin Wæver Pedersen, Henrik Madsen Course week 13 MWP, compiled June 8, 2011 Objecive: Locae fish from agging
More informationMachine Learning 4771
ony Jebara, Columbia Universiy achine Learning 4771 Insrucor: ony Jebara ony Jebara, Columbia Universiy opic 20 Hs wih Evidence H Collec H Evaluae H Disribue H Decode H Parameer Learning via JA & E ony
More informationEECE251. Circuit Analysis I. Set 4: Capacitors, Inductors, and First-Order Linear Circuits
EEE25 ircui Analysis I Se 4: apaciors, Inducors, and Firs-Order inear ircuis Shahriar Mirabbasi Deparmen of Elecrical and ompuer Engineering Universiy of Briish olumbia shahriar@ece.ubc.ca Overview Passive
More informationUnderwater Target Tracking Based on Gaussian Particle Filter in Looking Forward Sonar Images
Journal of Copuaional Inforaion Syses 6:4 (00) 480-4809 Available a hp://www.jofcis.co Underwaer Targe Tracing Based on Gaussian Paricle Filer in Looing Forward Sonar Iages Tiedong ZHANG, Wenjing ZENG,
More informationTom Heskes and Onno Zoeter. Presented by Mark Buller
Tom Heskes and Onno Zoeer Presened by Mark Buller Dynamic Bayesian Neworks Direced graphical models of sochasic processes Represen hidden and observed variables wih differen dependencies Generalize Hidden
More informationEstimation of Poses with Particle Filters
Esimaion of Poses wih Paricle Filers Dr.-Ing. Bernd Ludwig Chair for Arificial Inelligence Deparmen of Compuer Science Friedrich-Alexander-Universiä Erlangen-Nürnberg 12/05/2008 Dr.-Ing. Bernd Ludwig (FAU
More informationACE 562 Fall Lecture 5: The Simple Linear Regression Model: Sampling Properties of the Least Squares Estimators. by Professor Scott H.
ACE 56 Fall 005 Lecure 5: he Simple Linear Regression Model: Sampling Properies of he Leas Squares Esimaors by Professor Sco H. Irwin Required Reading: Griffihs, Hill and Judge. "Inference in he Simple
More informationPhys1112: DC and RC circuits
Name: Group Members: Dae: TA s Name: Phys1112: DC and RC circuis Objecives: 1. To undersand curren and volage characerisics of a DC RC discharging circui. 2. To undersand he effec of he RC ime consan.
More informationWritten HW 9 Sol. CS 188 Fall Introduction to Artificial Intelligence
CS 188 Fall 2018 Inroducion o Arificial Inelligence Wrien HW 9 Sol. Self-assessmen due: Tuesday 11/13/2018 a 11:59pm (submi via Gradescope) For he self assessmen, fill in he self assessmen boxes in your
More informationProblem set 2 for the course on. Markov chains and mixing times
J. Seif T. Hirscher Soluions o Proble se for he course on Markov chains and ixing ies February 7, 04 Exercise 7 (Reversible chains). (i) Assue ha we have a Markov chain wih ransiion arix P, such ha here
More informationEE100 Lab 3 Experiment Guide: RC Circuits
I. Inroducion EE100 Lab 3 Experimen Guide: A. apaciors A capacior is a passive elecronic componen ha sores energy in he form of an elecrosaic field. The uni of capaciance is he farad (coulomb/vol). Pracical
More informationJoint Spectral Distribution Modeling Using Restricted Boltzmann Machines for Voice Conversion
INTERSPEECH 2013 Join Specral Disribuion Modeling Using Resriced Bolzann Machines for Voice Conversion Ling-Hui Chen, Zhen-Hua Ling, Yan Song, Li-Rong Dai Naional Engineering Laboraory of Speech and Language
More informationNotes 04 largely plagiarized by %khc
Noes 04 largely plagiarized by %khc Convoluion Recap Some ricks: x() () =x() x() (, 0 )=x(, 0 ) R ț x() u() = x( )d x() () =ẋ() This hen ells us ha an inegraor has impulse response h() =u(), and ha a differeniaor
More informationAn EM based training algorithm for recurrent neural networks
An EM based raining algorihm for recurren neural neworks Jan Unkelbach, Sun Yi, and Jürgen Schmidhuber IDSIA,Galleria 2, 6928 Manno, Swizerland {jan.unkelbach,yi,juergen}@idsia.ch hp://www.idsia.ch Absrac.
More informationHidden Markov Models. Adapted from. Dr Catherine Sweeney-Reed s slides
Hidden Markov Models Adaped from Dr Caherine Sweeney-Reed s slides Summary Inroducion Descripion Cenral in HMM modelling Exensions Demonsraion Specificaion of an HMM Descripion N - number of saes Q = {q
More informationWhat Ties Return Volatilities to Price Valuations and Fundamentals? On-Line Appendix
Wha Ties Reurn Volailiies o Price Valuaions and Fundamenals? On-Line Appendix Alexander David Haskayne School of Business, Universiy of Calgary Piero Veronesi Universiy of Chicago Booh School of Business,
More informationOrientation. Connections between network coding and stochastic network theory. Outline. Bruce Hajek. Multicast with lost packets
Connecions beween nework coding and sochasic nework heory Bruce Hajek Orienaion On Thursday, Ralf Koeer discussed nework coding: coding wihin he nework Absrac: Randomly generaed coded informaion blocks
More informationObject Tracking. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem
Objec Tracking Compuer Vision Jia-Bin Huang Virginia Tech Man slides from D. Hoiem Adminisraive suffs HW 5 (Scene caegorizaion) Due :59pm on Wed November 6 oll on iazza When should we have he final exam?
More informationA Reinforcement Learning Approach for Collaborative Filtering
A Reinforcemen Learning Approach for Collaboraive Filering Jungkyu Lee, Byonghwa Oh 2, Jihoon Yang 2, and Sungyong Park 2 Cyram Inc, Seoul, Korea jklee@cyram.com 2 Sogang Universiy, Seoul, Korea {mrfive,yangjh,parksy}@sogang.ac.kr
More informationOverview. COMP14112: Artificial Intelligence Fundamentals. Lecture 0 Very Brief Overview. Structure of this course
OMP: Arificial Inelligence Fundamenals Lecure 0 Very Brief Overview Lecurer: Email: Xiao-Jun Zeng x.zeng@mancheser.ac.uk Overview This course will focus mainly on probabilisic mehods in AI We shall presen
More informationNumerical Dispersion
eview of Linear Numerical Sabiliy Numerical Dispersion n he previous lecure, we considered he linear numerical sabiliy of boh advecion and diffusion erms when approimaed wih several spaial and emporal
More informationDesigning Information Devices and Systems I Spring 2019 Lecture Notes Note 17
EES 16A Designing Informaion Devices and Sysems I Spring 019 Lecure Noes Noe 17 17.1 apaciive ouchscreen In he las noe, we saw ha a capacior consiss of wo pieces on conducive maerial separaed by a nonconducive
More informationFinancial Econometrics Jeffrey R. Russell Midterm Winter 2009 SOLUTIONS
Name SOLUTIONS Financial Economerics Jeffrey R. Russell Miderm Winer 009 SOLUTIONS You have 80 minues o complee he exam. Use can use a calculaor and noes. Try o fi all your work in he space provided. If
More informationFourier Series & The Fourier Transform. Joseph Fourier, our hero. Lord Kelvin on Fourier s theorem. What do we want from the Fourier Transform?
ourier Series & The ourier Transfor Wha is he ourier Transfor? Wha do we wan fro he ourier Transfor? We desire a easure of he frequencies presen in a wave. This will lead o a definiion of he er, he specru.
More informationAC Circuits AC Circuit with only R AC circuit with only L AC circuit with only C AC circuit with LRC phasors Resonance Transformers
A ircuis A ircui wih only A circui wih only A circui wih only A circui wih phasors esonance Transformers Phys 435: hap 31, Pg 1 A ircuis New Topic Phys : hap. 6, Pg Physics Moivaion as ime we discovered
More informationδ (τ )dτ denotes the unit step function, and
ECE-202 Homework Problems (Se 1) Spring 18 TO THE STUDENT: ALWAYS CHECK THE ERRATA on he web. ANCIENT ASIAN/AFRICAN/NATIVE AMERICAN/SOUTH AMERICAN ETC. PROVERB: If you give someone a fish, you give hem
More informationThe average rate of change between two points on a function is d t
SM Dae: Secion: Objecive: The average rae of change beween wo poins on a funcion is d. For example, if he funcion ( ) represens he disance in miles ha a car has raveled afer hours, hen finding he slope
More informationPhysics 235 Chapter 2. Chapter 2 Newtonian Mechanics Single Particle
Chaper 2 Newonian Mechanics Single Paricle In his Chaper we will review wha Newon s laws of mechanics ell us abou he moion of a single paricle. Newon s laws are only valid in suiable reference frames,
More informationEE202 Circuit Theory II , Spring. Dr. Yılmaz KALKAN & Dr. Atilla DÖNÜK
EE202 Circui Theory II 2018 2019, Spring Dr. Yılmaz KALKAN & Dr. Ailla DÖNÜK 1. Basic Conceps (Chaper 1 of Nilsson - 3 Hrs.) Inroducion, Curren and Volage, Power and Energy 2. Basic Laws (Chaper 2&3 of
More informationSelf assessment due: Monday 4/29/2019 at 11:59pm (submit via Gradescope)
CS 188 Spring 2019 Inroducion o Arificial Inelligence Wrien HW 10 Due: Monday 4/22/2019 a 11:59pm (submi via Gradescope). Leave self assessmen boxes blank for his due dae. Self assessmen due: Monday 4/29/2019
More informationGround Rules. PC1221 Fundamentals of Physics I. Kinematics. Position. Lectures 3 and 4 Motion in One Dimension. A/Prof Tay Seng Chuan
Ground Rules PC11 Fundamenals of Physics I Lecures 3 and 4 Moion in One Dimension A/Prof Tay Seng Chuan 1 Swich off your handphone and pager Swich off your lapop compuer and keep i No alking while lecure
More informationChapter 9 Sinusoidal Steady State Analysis
Chaper 9 Sinusoidal Seady Sae Analysis 9.-9. The Sinusoidal Source and Response 9.3 The Phasor 9.4 pedances of Passive Eleens 9.5-9.9 Circui Analysis Techniques in he Frequency Doain 9.0-9. The Transforer
More informationPattern Classification and NNet applications with memristive crossbar circuits. Fabien ALIBART D. Strukov s group, ECE-UCSB Now at IEMN-CNRS, France
Paern Classificaion and NNe applicaions wih memrisive crossbar circuis Fabien ALIBART D. Srukov s group, ECE-UCSB Now a IEMN-CNRS, France Ouline Inroducion: Neural Nework wih memrisive devices Engineering
More informationOPTIMAL CAPACITOR PLACEMENT FOR POWER LOSS REDUCTION AND VOLTAGE STABILITY ENHANCEMENT IN DISTRIBUTION SYSTEMS
ISSN 1313-7069 (prin) ISSN 1313-3551 (online) Trakia Journal of Sciences, No 4, pp 45-430, 014 Copyrigh 014 Trakia Universiy Available online a: hp://www.uni-sz.bg doi:10.15547/js.014.04.013 Original Conribuion
More informationA Decision Model for Fuzzy Clustering Ensemble
A Decision Model for Fuzzy Clusering Enseble Yanqiu Fu Yan Yang Yi Liu School of Inforaion Science & echnology, Souhwes Jiaoong Universiy, Chengdu 6003, China Absrac Algorih Recen researches and experiens
More informationPredator - Prey Model Trajectories and the nonlinear conservation law
Predaor - Prey Model Trajecories and he nonlinear conservaion law James K. Peerson Deparmen of Biological Sciences and Deparmen of Mahemaical Sciences Clemson Universiy Ocober 28, 213 Ouline Drawing Trajecories
More informationTemporal probability models
Temporal probabiliy models CS194-10 Fall 2011 Lecure 25 CS194-10 Fall 2011 Lecure 25 1 Ouline Hidden variables Inerence: ilering, predicion, smoohing Hidden Markov models Kalman ilers (a brie menion) Dynamic
More information18 Biological models with discrete time
8 Biological models wih discree ime The mos imporan applicaions, however, may be pedagogical. The elegan body of mahemaical heory peraining o linear sysems (Fourier analysis, orhogonal funcions, and so
More informationThe electromagnetic interference in case of onboard navy ships computers - a new approach
The elecromagneic inerference in case of onboard navy ships compuers - a new approach Prof. dr. ing. Alexandru SOTIR Naval Academy Mircea cel Bărân, Fulgerului Sree, Consanţa, soiralexandru@yahoo.com Absrac.
More informationProblem Set #1. i z. the complex propagation constant. For the characteristic impedance:
Problem Se # Problem : a) Using phasor noaion, calculae he volage and curren waves on a ransmission line by solving he wave equaion Assume ha R, L,, G are all non-zero and independen of frequency From
More informationA Bayesian Approach to Spectral Analysis
Chirped Signals A Bayesian Approach o Specral Analysis Chirped signals are oscillaing signals wih ime variable frequencies, usually wih a linear variaion of frequency wih ime. E.g. f() = A cos(ω + α 2
More informationSynapses with short-term plasticity are optimal estimators of presynaptic membrane potentials: supplementary note
Synapses wih shor-erm plasiciy are opimal esimaors of presynapic membrane poenials: supplemenary noe Jean-Pascal Pfiser, Peer Dayan, Máé Lengyel Supplemenary Noe 1 The local possynapic poenial In he main
More information