Neural Networks II. Chen Gao. Virginia Tech Spring 2019 ECE-5424G / CS-5824

Size: px
Start display at page:

Download "Neural Networks II. Chen Gao. Virginia Tech Spring 2019 ECE-5424G / CS-5824"

Transcription

1 Neural Networks II Chen Gao ECE-5424G / CS-5824 Virginia Tech Spring 2019

2 Neural Networks Origins: Algorithms that try to mimic the brain. What is this?

3 A single neuron in the brain Input Output Slide credit: Andrew Ng

4 An artificial neuron: Logistic unit x 0 x 1 x 2 Bias unit x = Output x 0 x 1 x 2 x 3 θ = h θ x = 1 θ 0 θ 1 θ 2 θ e θ x Weights Parameters x 3 Input Sigmoid (logistic) activation function Slide credit: Andrew Ng

5 Visualization of weights, bias, activation function range determined by g(.) bias b only change the position of the hyperplane Slide credit: Hugo Larochelle

6 Activation - sigmoid Squashes the neuron s preactivation between 0 and 1 Always positive Bounded Strictly increasing g x = e x Slide credit: Hugo Larochelle

7 Activation - hyperbolic tangent (tanh) Squashes the neuron s preactivation between -1 and 1 Can be positive or negative Bounded Strictly increasing g x = tanh x = ex e x e x + e x Slide credit: Hugo Larochelle

8 Activation - rectified linear(relu) Bounded below by 0 always non-negative Not upper bounded Tends to give neurons with sparse activities g x = relu x = max 0, x Slide credit: Hugo Larochelle

9 Activation - softmax For multi-class classification: we need multiple outputs (1 output per class) we would like to estimate the conditional probability p y = c x We use the softmax activation function at the output: g x = softmax x = ex 1 σ c e x c ex c σ c e x c Slide credit: Hugo Larochelle

10 Universal approximation theorem a single hidden layer neural network with a linear output unit can approximate any continuous function arbitrarily well, given enough hidden units Hornik, 1991 Slide credit: Hugo Larochelle

11 Neural network Multilayer x 0 x 1 x 2 a 0 a 1 a 2 Output h Θ x x 3 Layer 1 a 3 Layer 2 (hidden) Layer 3 Slide credit: Andrew Ng

12 Neural network x 0 x 1 x 2 x 3 a 0 a 1 a 2 a 3 h Θ x (1) (1) (1) (1) a 1 = g Θ10 x0 + Θ 11 x1 + Θ 12 x2 + Θ 13 x3 (1) (1) (1) (1) a 2 = g Θ20 x0 + Θ 21 x1 + Θ 22 x2 + Θ 23 x3 (j) a i = activation of unit i in layer j Θ j = matrix of weights controlling function mapping from layer j to layer j + 1 s j unit in layer j s j+1 units in layer j + 1 Size of Θ j? (1) (1) (1) (1) a 3 = g Θ30 x0 + Θ 31 x1 + Θ 32 x2 + Θ 33 x3 (1) (1) (1) h Θ (x) = g Θ 10 a0 + Θ11 a1 + Θ12 a2 + Θ13 a3 s j+1 (s j + 1) Slide credit: Andrew Ng

13 Neural network x 0 x = a 0 x 1 a 1 x 2 a 2 h Θ x x 0 x 1 x 2 x 3 z = Pre-activation z 1 z 2 z 3 x 3 a 3 Why do we need g(.)? (1) (1) (1) (1) a 1 = g Θ10 x0 + Θ 11 x1 + Θ 12 x2 + Θ 13 x3 = g(z 1 ) (1) (1) (1) (1) a 2 = g Θ20 x0 + Θ 21 x1 + Θ 22 x2 + Θ 23 x3 = g(z 2 ) (1) (1) (1) (1) a 3 = g Θ30 x0 + Θ 31 x1 + Θ 32 x2 + Θ 33 x3 = g(z 3 ) h Θ x = g Θ 2 10 a Θ 1 11 a Θ 1 12 a Θ a 3 = g(z (3) ) Slide credit: Andrew Ng

14 Neural network x 0 x = a 0 x 1 a 1 x 2 a 2 h Θ x x 0 x 1 x 2 x 3 z = Pre-activation z 1 z 2 z 3 x 3 a 3 a 1 = g(z1 ) a 2 = g(z2 ) a 3 = g(z3 ) h Θ x = g(z (3) ) z = Θ (1) x = Θ (1) a (1) a = g(z ) Add a 0 = 1 z (3) = Θ a h Θ x = a (3) = g(z (3) ) Slide credit: Andrew Ng

15 Flow graph - Forward propagation X z a (3) h Θ x a z (3) W (1) b (1) W b How do we evaluate our prediction? z = Θ (1) x = Θ (1) a (1) a = g(z ) Add a 0 = 1 z (3) = Θ a h Θ x = a (3) = g(z (3) )

16 Cost function Logistic regression: Neural network: Slide credit: Andrew Ng

17 Gradient computation Need to compute: Slide credit: Andrew Ng

18 Gradient computation Given one training example x, y a (1) = x z = Θ (1) a (1) a = g(z ) (add a 0 ) z (3) = Θ a a (3) = g(z (3) (3) ) (add a 0 ) z (4) = Θ (3) a (3) a (4) = g z 4 = h Θ x Slide credit: Andrew Ng

19 Gradient computation: Backpropagation Intuition: δ j (l) = error of node j in layer l For each output unit (layer L = 4) δ (4) = a (4) y δ (3) = δ (4) δ(4) δ(4) a z (3) = (4) z (4) a (3) δ(4) a (4) z (4) a (3) z (3) = 1 *Θ 3 T δ (4). g z 4. g (z (3) ) z (3) = Θ a a (3) = g(z (3) ) z (4) = Θ (3) a (3) a (4) = g z 4 Slide credit: Andrew Ng

20 Backpropagation algorithm Training set x (1), y (1) x (m), y (m) Set Θ (1) = 0 For i = 1 to m Set a (1) = x Perform forward propagation to compute a (l) for l = 2.. L use y (i) to compute δ (L) = a (L) y (i) Compute δ (L 1), δ (L 2) δ Θ (l) = Θ (l) a (l) δ (l+1) Slide credit: Andrew Ng

21 Activation - sigmoid Partial derivative g x = g x 1 g x g x = e x Slide credit: Hugo Larochelle

22 Activation - hyperbolic tangent (tanh) Partial derivative g x = 1 g x 2 g x = tanh x = ex e x e x + e x Slide credit: Hugo Larochelle

23 Activation - rectified linear(relu) Partial derivative g x = 1 x > 0 g x = relu x = max 0, x Slide credit: Hugo Larochelle

24 Initialization For bias Initialize all to 0 For weights Can t initialize all weights to the same value we can show that all hidden units in a layer will always behave the same need to break symmetry Recipe: U[-b, b] the idea is to sample around 0 but break symmetry Slide credit: Hugo Larochelle

25 Putting it together Pick a network architecture No. of input units: Dimension of features No. output units: Number of classes Reasonable default: 1 hidden layer, or if >1 hidden layer, have same no. of hidden units in every layer (usually the more the better) Grid search Slide credit: Hugo Larochelle

26 Putting it together Early stopping Use a validation set performance to select the best configuration To select the number of epochs, stop training when validation set error increases Slide credit: Hugo Larochelle

27 Other tricks of the trade Normalizing your (real-valued) data Decaying the learning rate as we get closer to the optimum, makes sense to take smaller update steps mini-batch can give a more accurate estimate of the risk gradient Momentum can use an exponential average of previous gradients Slide credit: Hugo Larochelle

28 Dropout Idea: «cripple» neural network by removing hidden units each hidden unit is set to 0 with probability 0.5 hidden units cannot co-adapt to other units hidden units must be more generally useful Slide credit: Hugo Larochelle

Lecture 39: Training Neural Networks (Cont d)

Lecture 39: Training Neural Networks (Cont d) Lecture 39: Training Neural Networks (Cont d) CS 4670/5670 Sean Bell Strawberry Goblet Throne (Side Note for PA5) AlexNet: 1 vs 2 parts Caffe represents caffe like the above image, but computes as if it

More information

Introduction to Machine Learning NPFL 054

Introduction to Machine Learning NPFL 054 Introduction to Machine Learning NPFL 054 http://ufal.mff.cuni.cz/course/npfl054 Barbora Hladká hladka@ufal.mff.cuni.cz Martin Holub holub@ufal.mff.cuni.cz Charles University, Faculty of Mathematics and

More information

Fun Neural Net Demo Site. CS 188: Artificial Intelligence. N-Layer Neural Network. Multi-class Softmax Σ >0? Deep Learning II

Fun Neural Net Demo Site. CS 188: Artificial Intelligence. N-Layer Neural Network. Multi-class Softmax Σ >0? Deep Learning II Fun Neural Net Demo Site CS 188: Artificial Intelligence Demo-site: http://playground.tensorflow.org/ Deep Learning II Instructors: Pieter Abbeel & Anca Dragan --- University of California, Berkeley [These

More information

Neural Nets Using Backpropagation. Chris Marriott Ryan Shirley CJ Baker Thomas Tannahill

Neural Nets Using Backpropagation. Chris Marriott Ryan Shirley CJ Baker Thomas Tannahill Neural Nets Using Backpropagation Chris Marriott Ryan Shirley CJ Baker Thomas Tannahill Agenda Review of Neural Nets and Backpropagation Backpropagation: The Math Advantages and Disadvantages of Gradient

More information

A Brief History of the Development of Artificial Neural Networks

A Brief History of the Development of Artificial Neural Networks A Brief History of the Development of Artificial Neural Networks Prof. Bernard Widrow Department of Electrical Engineering Stanford University Baidu July 18, 2018 Prof. Widrow @ Berkeley A Brief History

More information

CS 1675: Intro to Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh November 1, 2018

CS 1675: Intro to Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh November 1, 2018 CS 1675: Intro to Machine Learning Neural Networks Prof. Adriana Kovashka University of Pittsburgh November 1, 2018 Plan for this lecture Neural network basics Definition and architecture Biological inspiration

More information

Predicting NBA Shots

Predicting NBA Shots Predicting NBA Shots Brett Meehan Stanford University https://github.com/brettmeehan/cs229 Final Project bmeehan2@stanford.edu Abstract This paper examines the application of various machine learning algorithms

More information

Convolutional Neural Networks

Convolutional Neural Networks CS 1674: Intro to Computer Vision Convolutional Neural Networks Prof. Adriana Kovashka University of Pittsburgh March 13, 15, 20, 2018 Plan for the next few lectures Why (convolutional) neural networks?

More information

ARTIFICIAL NEURAL NETWORK BASED DESIGN FOR DUAL LATERAL WELL APPLICATIONS

ARTIFICIAL NEURAL NETWORK BASED DESIGN FOR DUAL LATERAL WELL APPLICATIONS The Pennsylvania State University the Graduate School Department of Energy and Mineral Engineering ARTIFICIAL NEURAL NETWORK BASED DESIGN FOR DUAL LATERAL WELL APPLICATIONS Thesis in Energy and Mineral

More information

Predicting the Total Number of Points Scored in NFL Games

Predicting the Total Number of Points Scored in NFL Games Predicting the Total Number of Points Scored in NFL Games Max Flores (mflores7@stanford.edu), Ajay Sohmshetty (ajay14@stanford.edu) CS 229 Fall 2014 1 Introduction Predicting the outcome of National Football

More information

Practical Approach to Evacuation Planning Via Network Flow and Deep Learning

Practical Approach to Evacuation Planning Via Network Flow and Deep Learning Practical Approach to Evacuation Planning Via Network Flow and Deep Learning Akira Tanaka Nozomi Hata Nariaki Tateiwa Katsuki Fujisawa Graduate School of Mathematics, Kyushu University Institute of Mathematics

More information

Environmental Science: An Indian Journal

Environmental Science: An Indian Journal Environmental Science: An Indian Journal Research Vol 14 Iss 1 Flow Pattern and Liquid Holdup Prediction in Multiphase Flow by Machine Learning Approach Chandrasekaran S *, Kumar S Petroleum Engineering

More information

Universal Style Transfer via Feature Transforms

Universal Style Transfer via Feature Transforms Universal Style Transfer via Feature Transforms Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang UC Merced, Adobe Research, NVIDIA Research Presented: Dong Wang (Refer to slides by

More information

B. AA228/CS238 Component

B. AA228/CS238 Component Abstract Two supervised learning methods, one employing logistic classification and another employing an artificial neural network, are used to predict the outcome of baseball postseason series, given

More information

Machine Learning Methods for Climbing Route Classification

Machine Learning Methods for Climbing Route Classification Machine Learning Methods for Climbing Route Classification Alejandro Dobles Mathematics adobles@stanford.edu Juan Carlos Sarmiento Management Science & Engineering jcs10@stanford.edu Abstract Peter Satterthwaite

More information

Basketball field goal percentage prediction model research and application based on BP neural network

Basketball field goal percentage prediction model research and application based on BP neural network ISSN : 0974-7435 Volume 10 Issue 4 BTAIJ, 10(4), 2014 [819-823] Basketball field goal percentage prediction model research and application based on BP neural network Jijun Guo Department of Physical Education,

More information

1.1 The size of the search space Modeling the problem Change over time Constraints... 21

1.1 The size of the search space Modeling the problem Change over time Constraints... 21 Introduction : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 1 I What Are the Ages of My Three Sons? : : : : : : : : : : : : : : : : : 9 1 Why Are Some Problems Dicult to Solve? : : :

More information

Detection of Proportion of Different Gas Components Present in Manhole Gas Mixture Using Backpropagation Neural Network

Detection of Proportion of Different Gas Components Present in Manhole Gas Mixture Using Backpropagation Neural Network 01 International Conference on Information and Network Technology (ICINT 01) IPCSIT vol. 37 (01) (01) IACSIT Press, Singapore Detection of Proportion of Different Gas Components Present in Manhole Gas

More information

Syntax and Parsing II

Syntax and Parsing II Syntax and Parsing II Dependency Parsing Slav Petrov Google Thanks to: Dan Klein, Ryan McDonald, Alexander Rush, Joakim Nivre, Greg Durrett, David Weiss Lisbon Machine Learning School 2016 Dependency Parsing

More information

NEURAL NETWORKS BASED TYRE IDENTIFICATION FOR A TYRE INFLATOR OPERATIONS

NEURAL NETWORKS BASED TYRE IDENTIFICATION FOR A TYRE INFLATOR OPERATIONS Lfe/sou/n /oh NEURAL NETWORKS BASED TYRE IDENTIFICATION FOR A TYRE INFLATOR OPERATIONS A Thesis submitted to the Department of Electrical Engineering, University of Moratuwa On partial fulfilment of the

More information

Folding Reticulated Shell Structure Wind Pressure Coefficient Prediction Research based on RBF Neural Network

Folding Reticulated Shell Structure Wind Pressure Coefficient Prediction Research based on RBF Neural Network International Conference on Information Sciences, Machinery, Materials and Energy (ICISMME 2015) Folding Reticulated Shell Structure Wind Pressure Coefficient Prediction Research based on RBF Neural Network

More information

Neural Network in Computer Vision for RoboCup Middle Size League

Neural Network in Computer Vision for RoboCup Middle Size League Journal of Software Engineering and Applications, 2016, *,** Neural Network in Computer Vision for RoboCup Middle Size League Paulo Rogério de Almeida Ribeiro 1, Gil Lopes 1, Fernando Ribeiro 1 1 Department

More information

Syntax and Parsing II

Syntax and Parsing II Syntax and Parsing II Dependency Parsing Slav Petrov Google Thanks to: Dan Klein, Ryan McDonald, Alexander Rush, Joakim Nivre, Greg Durrett, David Weiss Lisbon Machine Learning School 2015 Notes for 2016

More information

A Novel Travel Adviser Based on Improved Back-propagation Neural Network

A Novel Travel Adviser Based on Improved Back-propagation Neural Network 216 7th International Conference on Intelligent Systems, Modelling and Simulation A Novel Travel Adviser Based on Improved Back-propagation Neural Network Min Yang Department of Electronic Engineering

More information

Gait Analysis using Neural Networks

Gait Analysis using Neural Networks Gait Analysis using Neural Networks Sai krishna WDS 1 1Student, (B. Tech) Department of Electronics and communication, Vellore Institute of Technology, Chennai, India. -----------------------------------------------------------------------***--------------------------------------------------------------------

More information

Development of PVT Correlation for Iraqi Crude Oils Using Artificial Neural Network

Development of PVT Correlation for Iraqi Crude Oils Using Artificial Neural Network Iraqi Journal of Chemical and Petroleum Engineering Iraqi Journal of Chemical and Petroleum Engineering Vol.13 No.3 (September 2012) 9-16 ISSN: 1997-4884 University of Baghdad College of Engineering Development

More information

Predicting National Gas Consumption in Iran using a Hierarchical Combination of Neural Networks and Genetic Algorithms

Predicting National Gas Consumption in Iran using a Hierarchical Combination of Neural Networks and Genetic Algorithms Predicting National Gas Consumption in Iran using a Hierarchical Combination of Neural Networks and Genetic Algorithms Salehi.M 1, Nikkhah Amirabad.Y 1, Boostani.R 2 1 National Iranian Gas Company, Yasuj,

More information

A Novel Approach to Predicting the Results of NBA Matches

A Novel Approach to Predicting the Results of NBA Matches A Novel Approach to Predicting the Results of NBA Matches Omid Aryan Stanford University aryano@stanford.edu Ali Reza Sharafat Stanford University sharafat@stanford.edu Abstract The current paper presents

More information

Coupling distributed and symbolic execution for natural language queries. Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin

Coupling distributed and symbolic execution for natural language queries. Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin Coupling distributed and symbolic execution for natural language queries Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin doublepower.mou@gmail.com Outline Introduction to neural enquirers Coupled approach of

More information

CS249: ADVANCED DATA MINING

CS249: ADVANCED DATA MINING CS249: ADVANCED DATA MINING Linear Regression, Logistic Regression, and GLMs Instructor: Yizhou Sun yzsun@cs.ucla.edu April 24, 2017 About WWW2017 Conference 2 Turing Award Winner Sir Tim Berners-Lee 3

More information

Performance of Fully Automated 3D Cracking Survey with Pixel Accuracy based on Deep Learning

Performance of Fully Automated 3D Cracking Survey with Pixel Accuracy based on Deep Learning Performance of Fully Automated 3D Cracking Survey with Pixel Accuracy based on Deep Learning Kelvin C.P. Wang Oklahoma State University and WayLink Systems Corp. 2017-10-19, Copenhagen, Denmark European

More information

Development of Prediction Models for Spent Nuclear Fuel Storage Cask Monitoring Hyong Chol Kim, Sam Hee Han, Dong Jae Park

Development of Prediction Models for Spent Nuclear Fuel Storage Cask Monitoring Hyong Chol Kim, Sam Hee Han, Dong Jae Park Transactions of the Korean Nuclear Society Autumn Meeting Yeosu, Korea, October 25-26, 2018 Development of Prediction Models for Spent Nuclear Fuel Storage Cask Monitoring Hyong Chol Kim, Sam Hee Han,

More information

CS 4649/7649 Robot Intelligence: Planning

CS 4649/7649 Robot Intelligence: Planning CS 4649/7649 Robot Intelligence: Planning Partially Observable MDP Sungmoon Joo School of Interactive Computing College of Computing Georgia Institute of Technology S. Joo (sungmoon.joo@cc.gatech.edu)

More information

Research Article Wind Speed Inversion in High Frequency Radar Based on Neural Network

Research Article Wind Speed Inversion in High Frequency Radar Based on Neural Network Antennas and Propagation Volume 1, Article ID 751, pages http://dx.doi.org/.1155/1/751 Research Article Wind Speed Inversion in High Frequency Radar Based on Neural Network Yuming Zeng, 1 Hao Zhou, 1 Hugh

More information

Football Match Statistics Prediction using Artificial Neural Networks

Football Match Statistics Prediction using Artificial Neural Networks Football Match Statistics Prediction using Artificial Neural Networks 1 K. Sujatha, 1 T. Godhavari and 2 Nallamilli P G Bhavani 1 Dept of Electrical and Electronics Engineering/CSE Dept, Center for Electronics

More information

Prediction Model of Tensile Strength Property in Friction Stir Welding Using Artificial Neural Network (ANNs)

Prediction Model of Tensile Strength Property in Friction Stir Welding Using Artificial Neural Network (ANNs) Prediction Model of Tensile Strength Property in Friction Stir Welding Using Artificial Neural Network (ANNs) Ho Hwi Chie, Armansyah, Gatot Suharjanto Industrial Engineering, Faculty of Engineering Bina

More information

In memory of Dr. Kevin P. Granata, my graduate advisor, who was killed protecting others on the morning of April 16, 2007.

In memory of Dr. Kevin P. Granata, my graduate advisor, who was killed protecting others on the morning of April 16, 2007. Acknowledgement In memory of Dr. Kevin P. Granata, my graduate advisor, who was killed protecting others on the morning of April 16, 2007. There are many others without whom I could not have completed

More information

intended velocity ( u k arm movements

intended velocity ( u k arm movements Fig. A Complete Brain-Machine Interface B Human Subjects Closed-Loop Simulator ensemble action potentials (n k ) ensemble action potentials (n k ) primary motor cortex simulated primary motor cortex neuroprosthetic

More information

The Pennsylvania State University. The Graduate School. Department of Energy and Mineral Engineering

The Pennsylvania State University. The Graduate School. Department of Energy and Mineral Engineering The Pennsylvania State University The Graduate School Department of Energy and Mineral Engineering DEVELOPMENT OF AN ARTIFICIAL NEURAL NETWORK MODEL FOR DESIGNING WATER FLOODING PROJECTS IN THREE-PHASE

More information

Autodesk Moldflow Communicator Process settings

Autodesk Moldflow Communicator Process settings Autodesk Moldflow Communicator 212 Process settings Revision 1, 3 March 211. Contents Chapter 1 Process settings....................................... 1 Profiles.................................................

More information

Title: 4-Way-Stop Wait-Time Prediction Group members (1): David Held

Title: 4-Way-Stop Wait-Time Prediction Group members (1): David Held Title: 4-Way-Stop Wait-Time Prediction Group members (1): David Held As part of my research in Sebastian Thrun's autonomous driving team, my goal is to predict the wait-time for a car at a 4-way intersection.

More information

838. Improved aerodynamic optimization for the design of wind turbine blades

838. Improved aerodynamic optimization for the design of wind turbine blades 838. Improved aerodynamic optimization for the design of wind turbine blades Hua-Wei Chi 1, Pey-Shey Wu 2, Kamiru Chen 3, Yue-Hua Jhuo 4, Hung-Yun Wu 5 1, 2, 3, 4 Department of Mechanical and Automation

More information

Detection of Valve Leakage in Reciprocating Compressor Using Artificial Neural Network (ANN)

Detection of Valve Leakage in Reciprocating Compressor Using Artificial Neural Network (ANN) Purdue University Purdue e-pubs International Compressor Engineering Conference School of Mechanical Engineering 28 Detection of Valve Leakage in Reciprocating Compressor Using Artificial Neural Network

More information

Copy of my report. Why am I giving this talk. Overview. State highway network

Copy of my report. Why am I giving this talk. Overview. State highway network Road Surface characteristics and traffic accident rates on New Zealand s state highway network Robert Davies Statistics Research Associates http://www.statsresearch.co.nz Copy of my report There is a copy

More information

EXPERIMENTÁLNÍ ANALÝZA MLP SÍTÍ PRO PREDIKCI POHYBU PLIC PŘI DÝCHÁNÍ Experimental Analysis of MLP for Lung Respiration Prediction

EXPERIMENTÁLNÍ ANALÝZA MLP SÍTÍ PRO PREDIKCI POHYBU PLIC PŘI DÝCHÁNÍ Experimental Analysis of MLP for Lung Respiration Prediction 21 Technická 4, 166 7 Praha 6 EXPERIMENTÁLNÍ ANALÝZA MLP SÍTÍ PRO PREDIKCI POHYBU PLIC PŘI DÝCHÁNÍ Experimental Analysis of MLP for Lung Respiration Prediction Ricardo Rodriguez 1,2 1 Czech Technical University

More information

Heart Rate Prediction Based on Cycling Cadence Using Feedforward Neural Network

Heart Rate Prediction Based on Cycling Cadence Using Feedforward Neural Network Heart Rate Prediction Based on Cycling Cadence Using Feedforward Neural Network Kusprasapta Mutijarsa School of Electrical Engineering and Information Technology Bandung Institute of Technology Bandung,

More information

Predicting Horse Racing Results with Machine Learning

Predicting Horse Racing Results with Machine Learning Predicting Horse Racing Results with Machine Learning LYU 1703 LIU YIDE 1155062194 Supervisor: Professor Michael R. Lyu Outline Recap of last semester Object of this semester Data Preparation Set to sequence

More information

Evaluating and Classifying NBA Free Agents

Evaluating and Classifying NBA Free Agents Evaluating and Classifying NBA Free Agents Shanwei Yan In this project, I applied machine learning techniques to perform multiclass classification on free agents by using game statistics, which is useful

More information

An Artificial Neural Network-based Prediction Model for Underdog Teams in NBA Matches

An Artificial Neural Network-based Prediction Model for Underdog Teams in NBA Matches An Artificial Neural Network-based Prediction Model for Underdog Teams in NBA Matches Paolo Giuliodori University of Camerino, School of Science and Technology, Computer Science Division, Italy paolo.giuliodori@unicam.it

More information

SHOT ON GOAL. Name: Football scoring a goal and trigonometry Ian Edwards Luther College Teachers Teaching with Technology

SHOT ON GOAL. Name: Football scoring a goal and trigonometry Ian Edwards Luther College Teachers Teaching with Technology SHOT ON GOAL Name: Football scoring a goal and trigonometry 2006 Ian Edwards Luther College Teachers Teaching with Technology Shot on Goal Trigonometry page 2 THE TASKS You are an assistant coach with

More information

Research Article Predicting Free Flow Speed and Crash Risk of Bicycle Traffic Flow Using Artificial Neural Network Models

Research Article Predicting Free Flow Speed and Crash Risk of Bicycle Traffic Flow Using Artificial Neural Network Models Mathematical Problems in Engineering Volume, Article ID 20, 11 pages http://dx.doi.org/10.15//20 Research Article Predicting Free Flow Speed and Crash Risk of Bicycle Traffic Flow Using Artificial Neural

More information

Neuro-Fuzzy and Neural Networks Models to Estimate Radon Exhalation Rate in Uranium Ore- Rock Mine

Neuro-Fuzzy and Neural Networks Models to Estimate Radon Exhalation Rate in Uranium Ore- Rock Mine EUROPEAN ACADEMIC RESEARCH Vol. V, Issue 10/ January 201 ISSN 226-422 www.euacademic.org Impact Factor: 3.4546 (UIF) DRJI Value: 5.9 (B+) Neuro-Fuzzy and Neural Networks Models to Estimate Radon Exhalation

More information

A 28nm SoC with a 1.2GHz 568nJ/ Prediction Sparse Deep-Neural-Network Engine with >0.1 Timing Error Rate Tolerance for IoT Applications

A 28nm SoC with a 1.2GHz 568nJ/ Prediction Sparse Deep-Neural-Network Engine with >0.1 Timing Error Rate Tolerance for IoT Applications A 28nm SoC with a 1.2GHz 568nJ/ Prediction Sparse Deep-Neural-Network Engine with >0.1 Timing Error Rate Tolerance for IoT Applications Paul Whatmough, S. K. Lee, H. Lee, S. Rama, D. Brooks, G.-Y. Wei

More information

Effect of Shear Span to Depth Ratio on Shear Strength of Steel Fiber Reinforced High Strength Concrete Deep Beam using ANN

Effect of Shear Span to Depth Ratio on Shear Strength of Steel Fiber Reinforced High Strength Concrete Deep Beam using ANN Effect of Shear Span to Depth Ratio on Shear Strength of Steel Fiber Reinforced High Strength Concrete Deep Beam using ANN U. P. Naik, 1 Research Scholar, Department of Civil Engineering, K.K.Wagh Institute

More information

IMPROVED OIL SLICK IDENTIFICATION USING CMOD5 MODEL FOR WIND SPEED EVALUATION ON SAR IMAGES

IMPROVED OIL SLICK IDENTIFICATION USING CMOD5 MODEL FOR WIND SPEED EVALUATION ON SAR IMAGES IMPROVED OIL SLICK IDENTIFICATION USING CMOD5 MODEL FOR WIND SPEED EVALUATION ON SAR IMAGES H.KHENOUCHI & Y. SMARA University of Sciences and Technology Houari Boumediene (USTHB). Faculty of Electronics

More information

Predicting NFL Game Outcomes. Paul McBride ECE 539 Professor Yu Hen Hu

Predicting NFL Game Outcomes. Paul McBride ECE 539 Professor Yu Hen Hu Predicting NFL Game Outcomes Paul McBride ECE 539 Professor Yu Hen Hu Introduction Football has become an incredibly popular sport in America over the past 20 years or so. Every week, millions and millions

More information

Evolving Gaits for the Lynxmotion Hexapod II Robot

Evolving Gaits for the Lynxmotion Hexapod II Robot Evolving Gaits for the Lynxmotion Hexapod II Robot DAVID TOTH Computer Science, Worcester Polytechnic Institute Worcester, MA 01609-2280, USA toth@cs.wpi.edu, http://www.cs.wpi.edu/~toth and GARY PARKER

More information

Predicting Horse Racing Results with TensorFlow

Predicting Horse Racing Results with TensorFlow Predicting Horse Racing Results with TensorFlow LYU 1703 LIU YIDE WANG ZUOYANG News CUHK Professor, Gu Mingao, wins 50 MILLIONS dividend using his sure-win statistical strategy. News AlphaGO defeats human

More information

PREDICTING the outcomes of sporting events

PREDICTING the outcomes of sporting events CS 229 FINAL PROJECT, AUTUMN 2014 1 Predicting National Basketball Association Winners Jasper Lin, Logan Short, and Vishnu Sundaresan Abstract We used National Basketball Associations box scores from 1991-1998

More information

ASSESMENT of ESTIMATION MODELS for SCOUR AROUND PIPELINES under IRREGULAR WAVES

ASSESMENT of ESTIMATION MODELS for SCOUR AROUND PIPELINES under IRREGULAR WAVES ASSESMENT of ESTIMATION MODELS for SCOUR AROUND PIPELINES under IRREGULAR WAVES Burak Kiziloz 1 Esin Cevik 2 Yalcin Yuksel 3 and Burak Aydogan 4 This study focuses on scour around submarine pipelines exposed

More information

Open Research Online The Open University s repository of research publications and other research outputs

Open Research Online The Open University s repository of research publications and other research outputs Open Research Online The Open University s repository of research publications and other research outputs Developing an intelligent table tennis umpiring system Conference or Workshop Item How to cite:

More information

Ivan Suarez Robles, Joseph Wu 1

Ivan Suarez Robles, Joseph Wu 1 Ivan Suarez Robles, Joseph Wu 1 Section 1: Introduction Mixed Martial Arts (MMA) is the fastest growing competitive sport in the world. Because the fighters engage in distinct martial art disciplines (boxing,

More information

Sensing and Modeling of Terrain Features using Crawling Robots

Sensing and Modeling of Terrain Features using Crawling Robots Czech Technical University in Prague Sensing and Modeling of Terrain Features using Crawling Robots Jakub Mrva 1 Faculty of Electrical Engineering Agent Technology Center Computational Robotics Laboratory

More information

JPEG-Compatibility Steganalysis Using Block-Histogram of Recompression Artifacts

JPEG-Compatibility Steganalysis Using Block-Histogram of Recompression Artifacts JPEG-Compatibility Steganalysis Using Block-Histogram of Recompression Artifacts Jan Kodovský, Jessica Fridrich May 16, 2012 / IH Conference 1 / 19 What is JPEG-compatibility steganalysis? Detects embedding

More information

Visualizing and Understanding Stochastic Depth Networks

Visualizing and Understanding Stochastic Depth Networks Visualizing and Understanding Stochastic Depth Networks Russell Kaplan, Raphael Palefsky-Smith, Liu Jiang Stanford University 450 Serra Mall, Stanford, CA 94305 {rjkaplan, rpalefsk, liujiang}@stanford.edu

More information

CS 7641 A (Machine Learning) Sethuraman K, Parameswaran Raman, Vijay Ramakrishnan

CS 7641 A (Machine Learning) Sethuraman K, Parameswaran Raman, Vijay Ramakrishnan CS 7641 A (Machine Learning) Sethuraman K, Parameswaran Raman, Vijay Ramakrishnan Scenario 1: Team 1 scored 200 runs from their 50 overs, and then Team 2 reaches 146 for the loss of two wickets from their

More information

Ocean Wave Forecasting

Ocean Wave Forecasting Ocean Wave Forecasting Jean-Raymond Bidlot* Marine Prediction Section Predictability Division of the Research Department European Centre for Medium-range Weather Forecasts (E.C.M.W.F.) Reading, UK * With

More information

Prediction Market and Parimutuel Mechanism

Prediction Market and Parimutuel Mechanism Prediction Market and Parimutuel Mechanism Yinyu Ye MS&E and ICME Stanford University Joint work with Agrawal, Peters, So and Wang Math. of Ranking, AIM, 2 Outline World-Cup Betting Example Market for

More information

Sprinkler Protection for Cloud Ceilings. SUPDET 2013 Jason Floyd, Ph.D. 28 February 2013

Sprinkler Protection for Cloud Ceilings. SUPDET 2013 Jason Floyd, Ph.D. 28 February 2013 Sprinkler Protection for Cloud Ceilings SUPDET 2013 Jason Floyd, Ph.D. 28 February 2013 Background Cloud ceilings are a popular architectural feature Lack of clear guidance in the code for sprinkler installation

More information

International Journal of Research in Science and Technology Volume 1, Issue 1: October - December, 2014

International Journal of Research in Science and Technology Volume 1, Issue 1: October - December, 2014 AN APPLICATION OF MULTILAYER PERCEPTRON NEURAL NETWORK TO PREDICT THE PERFORMANCE OF BATSMEN IN INDIAN PREMIER LEAGUE Hemanta Saikia 1 and Dibyojyoti Bhattacharjee 2 Assistant 1 Professor, The Assam Kaziranga

More information

Artificial Neural Network Approach for Fault Detection in Pneumatic Valve in Cooler Water Spray System

Artificial Neural Network Approach for Fault Detection in Pneumatic Valve in Cooler Water Spray System Artificial Neural Network Approach for Fault Detection in Pneumatic Valve in Cooler Water Spray System P. Subbaraj Principal, Theni Kamavar Sangam College of Technology, Theni, Tamilnadu, B. Kannapiran

More information

Flow modelling hills complex terrain and other issues

Flow modelling hills complex terrain and other issues Flow modelling hills, complex terrain and other issues Modelling approaches sorted after complexity Rules of thumbs Codes and standards Linear model, 1 st order turbulence closure LINCOM/Wasp Reynolds-averaged

More information

BASKETBALL PREDICTION ANALYSIS OF MARCH MADNESS GAMES CHRIS TSENG YIBO WANG

BASKETBALL PREDICTION ANALYSIS OF MARCH MADNESS GAMES CHRIS TSENG YIBO WANG BASKETBALL PREDICTION ANALYSIS OF MARCH MADNESS GAMES CHRIS TSENG YIBO WANG GOAL OF PROJECT The goal is to predict the winners between college men s basketball teams competing in the 2018 (NCAA) s March

More information

FORECASTING OF ROLLING MOTION OF SMALL FISHING VESSELS UNDER FISHING OPERATION APPLYING A NON-DETERMINISTIC METHOD

FORECASTING OF ROLLING MOTION OF SMALL FISHING VESSELS UNDER FISHING OPERATION APPLYING A NON-DETERMINISTIC METHOD 8 th International Conference on 633 FORECASTING OF ROLLING MOTION OF SMALL FISHING VESSELS UNDER FISHING OPERATION APPLYING A NON-DETERMINISTIC METHOD Nobuo Kimura, Kiyoshi Amagai Graduate School of Fisheries

More information

A New Approach for Transformer Incipient Fault Diagnosis Based on Dissolved Gas Analysis (DGA)

A New Approach for Transformer Incipient Fault Diagnosis Based on Dissolved Gas Analysis (DGA) Nova Explore Publications Nova Journal of Engineering and Applied Sciences Vol. 3(2), 2014: 1-7 PII: S229279211400008-3 www.novaexplore.com Research Article A New Approach for Transformer Incipient Fault

More information

Smart-Walk: An Intelligent Physiological Monitoring System for Smart Families

Smart-Walk: An Intelligent Physiological Monitoring System for Smart Families Smart-Walk: An Intelligent Physiological Monitoring System for Smart Families P. Sundaravadivel 1, S. P. Mohanty 2, E. Kougianos 3, V. P. Yanambaka 4, and M. K. Ganapathiraju 5 University of North Texas,

More information

Navigate to the golf data folder and make it your working directory. Load the data by typing

Navigate to the golf data folder and make it your working directory. Load the data by typing Golf Analysis 1.1 Introduction In a round, golfers have a number of choices to make. For a particular shot, is it better to use the longest club available to try to reach the green, or would it be better

More information

THE TRANSACTIONS OF THE ROYAL INSTITUTION OF NAVAL ARCHITECTS. Part A International Journal of Maritime Engineering

THE TRANSACTIONS OF THE ROYAL INSTITUTION OF NAVAL ARCHITECTS. Part A International Journal of Maritime Engineering Trans RINA, Vol XXX, Part A1, Intl J Maritime Engineering 2013 Jun-Dec THE TRANSACTIONS OF THE ROYAL INSTITUTION OF NAVAL ARCHITECTS Part A International Journal of Maritime Engineering RESISTANCE PREDICTION

More information

CS145: INTRODUCTION TO DATA MINING

CS145: INTRODUCTION TO DATA MINING CS145: INTRODUCTION TO DATA MINING 3: Vector Data: Logistic Regression Instructor: Yizhou Sun yzsun@cs.ucla.edu October 9, 2017 Methods to Learn Vector Data Set Data Sequence Data Text Data Classification

More information

Lecture 10. Support Vector Machines (cont.)

Lecture 10. Support Vector Machines (cont.) Lecture 10. Support Vector Machines (cont.) COMP90051 Statistical Machine Learning Semester 2, 2017 Lecturer: Andrey Kan Copyright: University of Melbourne This lecture Soft margin SVM Intuition and problem

More information

Development of an Intelligent Gas Recognizer for Analysis of Sewer Gas

Development of an Intelligent Gas Recognizer for Analysis of Sewer Gas Development of an Intelligent Gas Recognizer for Analysis of Sewer Gas Prof. Paramartha Dutta Dept. Computer & System Sciences Visva-Bharati University Santiniketan West Bengal Introduction Objective Composition

More information

Using Spatio-Temporal Data To Create A Shot Probability Model

Using Spatio-Temporal Data To Create A Shot Probability Model Using Spatio-Temporal Data To Create A Shot Probability Model Eli Shayer, Ankit Goyal, Younes Bensouda Mourri June 2, 2016 1 Introduction Basketball is an invasion sport, which means that players move

More information

Using Soft Computing Techniques for Prediction of Winners in Tennis Matches

Using Soft Computing Techniques for Prediction of Winners in Tennis Matches Machine Learning Research 2017; 2(3): 86-98 http://www.sciencepublishinggroup.com/j/mlr doi: 10.11648/j.mlr.20170203.12 Using Soft Computing Techniques for Prediction of Winners in Tennis Matches Mateus

More information

2 When Some or All Labels are Missing: The EM Algorithm

2 When Some or All Labels are Missing: The EM Algorithm CS769 Spring Advanced Natural Language Processing The EM Algorithm Lecturer: Xiaojin Zhu jerryzhu@cs.wisc.edu Given labeled examples (x, y ),..., (x l, y l ), one can build a classifier. If in addition

More information

Adaptability and Fault Tolerance

Adaptability and Fault Tolerance Adaptability and Fault Tolerance Rogério de Lemos University of Kent, UK Context: self-* and dependability; Focus: adaptability and fault tolerance; State of the art; Conclusions; Rogério de Lemos ICSE

More information

Modeling vehicle delays at signalized junctions: Artificial neural networks approach

Modeling vehicle delays at signalized junctions: Artificial neural networks approach Journal of Scientific & Industrial Research Vol. 65, July 2006, pp. 558-564 Modeling vehicle delays at signalized junctions: Artificial neural networks approach Y Sazi Murat* and Özgür Baskan Civil Engineering

More information

Motion Control of a Bipedal Walking Robot

Motion Control of a Bipedal Walking Robot Motion Control of a Bipedal Walking Robot Lai Wei Ying, Tang Howe Hing, Mohamed bin Hussein Faculty of Mechanical Engineering Universiti Teknologi Malaysia, 81310 UTM Skudai, Johor, Malaysia. Wylai2@live.my

More information

Mathematics of Pari-Mutuel Wagering

Mathematics of Pari-Mutuel Wagering Millersville University of Pennsylvania April 17, 2014 Project Objectives Model the horse racing process to predict the outcome of a race. Use the win and exacta betting pools to estimate probabilities

More information

Pedestrian Dynamics: Models of Pedestrian Behaviour

Pedestrian Dynamics: Models of Pedestrian Behaviour Pedestrian Dynamics: Models of Pedestrian Behaviour John Ward 19 th January 2006 Contents Macro-scale sketch plan model Micro-scale agent based model for pedestrian movement Development of JPed Results

More information

CS472 Foundations of Artificial Intelligence. Final Exam December 19, :30pm

CS472 Foundations of Artificial Intelligence. Final Exam December 19, :30pm CS472 Foundations of Artificial Intelligence Final Exam December 19, 2003 12-2:30pm Name: (Q exam takers should write their Number instead!!!) Instructions: You have 2.5 hours to complete this exam. The

More information

Predicting Human Behavior from Public Cameras with Convolutional Neural Networks

Predicting Human Behavior from Public Cameras with Convolutional Neural Networks Comenius University in Bratislava Faculty of Mathematics, Physics and Informatics Predicting Human Behavior from Public Cameras with Convolutional Neural Networks Master thesis 2016 Ondrej Jariabka Comenius

More information

SEPARATING A GAS MIXTURE INTO ITS CONSTITUENT ANALYTES USING FICA

SEPARATING A GAS MIXTURE INTO ITS CONSTITUENT ANALYTES USING FICA SEPARATING A GAS MIXTURE INTO ITS CONSTITUENT ANALYTES USING FICA Aparna Mahadevan Thesis submitted to the faculty of the Virginia Polytechnic Institute and State University in partial fulfillment of the

More information

Projecting Three-Point Percentages for the NBA Draft

Projecting Three-Point Percentages for the NBA Draft Projecting Three-Point Percentages for the NBA Draft Hilary Sun hsun3@stanford.edu Jerold Yu jeroldyu@stanford.edu December 16, 2017 Roland Centeno rcenteno@stanford.edu 1 Introduction As NBA teams have

More information

Attacking and defending neural networks. HU Xiaolin ( 胡晓林 ) Department of Computer Science and Technology Tsinghua University, Beijing, China

Attacking and defending neural networks. HU Xiaolin ( 胡晓林 ) Department of Computer Science and Technology Tsinghua University, Beijing, China Attacking and defending neural networks HU Xiaolin ( 胡晓林 ) Department of Computer Science and Technology Tsinghua University, Beijing, China Outline Background Attacking methods Defending methods 2 AI

More information

Football Play Type Prediction and Tendency Analysis

Football Play Type Prediction and Tendency Analysis Football Play Type Prediction and Tendency Analysis by Karson L. Ota B.S. Computer Science and Engineering Massachusetts Institute of Technology, 2016 SUBMITTED TO THE DEPARTMENT OF ELECTRICAL ENGINEERING

More information

NOVEL TECHNIQUE TO CONTROL THE PREMATURE INFANT INCUBATOR SYSTEM USING ANN

NOVEL TECHNIQUE TO CONTROL THE PREMATURE INFANT INCUBATOR SYSTEM USING ANN Philadelphia University, Jordan From the SelectedWorks of Philadelphia University, Jordan 2005 NOVEL TECHNIQUE TO CONTROL THE PREMATURE INFANT INCUBATOR SYSTEM USING ANN Philadelphia University, Philadelphia

More information

Comparison of Control Methods: Learning Robotics Manipulation with Contact Dynamics

Comparison of Control Methods: Learning Robotics Manipulation with Contact Dynamics Comparison of Control Methods: Learning Robotics Manipulation with Contact Dynamics Keven Wang Computer Science Stanford University Email: kvw@stanford.edu Bruce Li Mashgin Email: yonglisc@gmail.com Abstract

More information

CS 4649/7649 Robot Intelligence: Planning

CS 4649/7649 Robot Intelligence: Planning CS 4649/7649 Robot Intelligence: Planning Roadmap Approaches Sungmoon Joo School of Interactive Computing College of Computing Georgia Institute of Technology S. Joo (sungmoon.joo@cc.gatech.edu) 1 *Slides

More information

Lesson 14: Modeling Relationships with a Line

Lesson 14: Modeling Relationships with a Line Exploratory Activity: Line of Best Fit Revisited 1. Use the link http://illuminations.nctm.org/activity.aspx?id=4186 to explore how the line of best fit changes depending on your data set. A. Enter any

More information

Optimizing Cyclist Parking in a Closed System

Optimizing Cyclist Parking in a Closed System Optimizing Cyclist Parking in a Closed System Letu Qingge, Killian Smith Gianforte School of Computing, Montana State University, Bozeman, MT 59717, USA Abstract. In this paper, we consider the two different

More information