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

Size: px
Start display at page:

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

Transcription

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

2 Agenda Review of Neural Nets and Backpropagation Backpropagation: The Math Advantages and Disadvantages of Gradient Descent and other algorithms Enhancements of Gradient Descent Other ways of minimizing error

3 Review Approach that developed from an analysis of the human brain Nodes created as an analog to neurons Mainly used for classification problems (i.e. character recognition, voice recognition, medical applications, etc.)

4 Review Neurons have weighted inputs, threshold values, activation function, and an output Weighted inputs Output Activation function = f( (inputs * weight))

5 Review 4 Input AND Inputs Threshold = 1.5 Outputs Threshold = 1.5 Inputs Threshold = 1.5 All weights = 1 and all outputs = 1 if active 0 otherwise

6 Review Output space for AND gate Input 1 (0,1) (1,1) 1.5 = w1*i1 + w2*i2 (0,0) (1,0) Input 2

7 Review Output space for XOR gate Demonstrates need for hidden layer Input 1 (0,1) (1,1) (0,0) (1,0) Input 2

8 Backpropagation: The Math General multi-layered neural network Output Layer X0,0 X1,0 X9,0 0 1 i W0,0 W1,0 Wi,0 Hidden Layer 0 1 Input Layer

9 Backpropagation: The Math Backpropagation Calculation of hidden layer activation values

10 Backpropagation: The Math Backpropagation Calculation of output layer activation values

11 Backpropagation: The Math Backpropagation Calculation of error δ k = f(d k ) -f(o k )

12 Backpropagation: The Math Backpropagation Gradient Descent objective function Gradient Descent termination condition

13 Backpropagation: The Math Backpropagation Output layer weight recalculation Learning Rate (eg. 0.25) Error at k

14 Backpropagation: The Math Backpropagation Hidden Layer weight recalculation

15 Backpropagation Using Gradient Descent Advantages Relatively simple implementation Standard method and generally works well Disadvantages Slow and inefficient Can get stuck in local minima resulting in suboptimal solutions

16 Local Minima Local Minimum Global Minimum

17 Alternatives To Gradient Descent Simulated Annealing Advantages Can guarantee optimal solution (global minimum) Disadvantages May be slower than gradient descent Much more complicated implementation

18 Alternatives To Gradient Descent Genetic Algorithms/Evolutionary Strategies Advantages Faster than simulated annealing Less likely to get stuck in local minima Disadvantages Slower than gradient descent Memory intensive for large nets

19 Alternatives To Gradient Descent Simplex Algorithm Advantages Similar to gradient descent but faster Easy to implement Disadvantages Does not guarantee a global minimum

20 Enhancements To Gradient Descent Momentum Adds a percentage of the last movement to the current movement

21 Enhancements To Gradient Descent Momentum Useful to get over small bumps in the error function Often finds a minimum in less steps w(t) = -n*d*y + a*w(t-1) w is the change in weight n is the learning rate d is the error y is different depending on which layer we are calculating a is the momentum parameter

22 Enhancements To Gradient Descent Adaptive Backpropagation Algorithm It assigns each weight a learning rate That learning rate is determined by the sign of the gradient of the error function from the last iteration If the signs are equal it is more likely to be a shallow slope so the learning rate is increased The signs are more likely to differ on a steep slope so the learning rate is decreased This will speed up the advancement when on gradual slopes

23 Enhancements To Gradient Descent Adaptive Backpropagation Possible Problems: Since we minimize the error for each weight separately the overall error may increase Solution: Calculate the total output error after each adaptation and if it is greater than the previous error reject that adaptation and calculate new learning rates

24 Enhancements To Gradient Descent SuperSAB(Super Self-Adapting Backpropagation) Combines the momentum and adaptive methods. Uses adaptive method and momentum so long as the sign of the gradient does not change This is an additive effect of both methods resulting in a faster traversal of gradual slopes When the sign of the gradient does change the momentum will cancel the drastic drop in learning rate This allows for the function to roll up the other side of the minimum possibly escaping local minima

25 Enhancements To Gradient Descent SuperSAB Experiments show that the SuperSAB converges faster than gradient descent Overall this algorithm is less sensitive (and so is less likely to get caught in local minima)

26 Other Ways To Minimize Error Varying training data Cycle through input classes Randomly select from input classes Add noise to training data Randomly change value of input node (with low probability) Retrain with expected inputs after initial training E.g. Speech recognition

27 Other Ways To Minimize Error Adding and removing neurons from layers Adding neurons speeds up learning but may cause loss in generalization Removing neurons has the opposite effect

28 Resources Artifical Neural Networks, Backpropagation, J. Henseler Artificial Intelligence: A Modern Approach, S. Russell & P. Norvig 501 notes, J.R. Parker urnal/vl4/cs11/report.html

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

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

Neural Networks II. Chen Gao. Virginia Tech Spring 2019 ECE-5424G / CS-5824 Neural Networks II Chen Gao ECE-5424G / CS-5824 Virginia Tech Spring 2019 Neural Networks Origins: Algorithms that try to mimic the brain. What is this? A single neuron in the brain Input Output Slide

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

Optimization and Search. Jim Tørresen Optimization and Search

Optimization and Search. Jim Tørresen Optimization and Search Optimization and Search INF3490 - Biologically inspired computing Lecture 1: Marsland chapter 9.1, 9.4-9.6 2017 Optimization and Search Jim Tørresen 2 Optimization and Search Methods (selection) Optimization

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

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

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

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

CS 4649/7649 Robot Intelligence: Planning

CS 4649/7649 Robot Intelligence: Planning CS 4649/7649 Robot Intelligence: Planning Differential Kinematics, Probabilistic Roadmaps Sungmoon Joo School of Interactive Computing College of Computing Georgia Institute of Technology S. Joo (sungmoon.joo@cc.gatech.edu)

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

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

SEARCH SEARCH TREE. Node: State in state tree. Root node: Top of state tree

SEARCH SEARCH TREE. Node: State in state tree. Root node: Top of state tree Page 1 Page 1 Page 2 SEARCH TREE SEARCH Node: State in state tree Root node: Top of state tree Children: Nodes that can be reached from a given node in 1 step (1 operator) Expanding: Generating the children

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

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

SEARCH TREE. Generating the children of a node

SEARCH TREE. Generating the children of a node SEARCH TREE Node: State in state tree Root node: Top of state tree Children: Nodes that can be reached from a given node in 1 step (1 operator) Expanding: Generating the children of a node Open: Closed:

More information

Calibration and Validation of the Simulation Model. Xin Zhang

Calibration and Validation of the Simulation Model. Xin Zhang Calibration and Validation of the Simulation Model Xin Zhang Comparison with existing tools Calibration and Validation Comparisons Comparison of vehicle simulation with VISSIM Comparison of simulation

More information

LOCOMOTION CONTROL CYCLES ADAPTED FOR DISABILITIES IN HEXAPOD ROBOTS

LOCOMOTION CONTROL CYCLES ADAPTED FOR DISABILITIES IN HEXAPOD ROBOTS LOCOMOTION CONTROL CYCLES ADAPTED FOR DISABILITIES IN HEXAPOD ROBOTS GARY B. PARKER and INGO CYLIAX Department of Computer Science, Indiana University, Bloomington, IN 47405 gaparker@cs.indiana.edu, cyliax@cs.indiana.edu

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

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

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

A Fault Diagnosis Monitoring System of Reciprocating Pump

A Fault Diagnosis Monitoring System of Reciprocating Pump IOSR Journal of Engineering (IOSRJEN) ISSN (e): 2250-3021, ISSN (p): 2278-8719 Vol. 05, Issue 09 (September. 2015), V1 PP 01-06 www.iosrjen.org A Fault Diagnosis Monitoring System of Reciprocating Pump

More information

Problem Solving as Search - I

Problem Solving as Search - I Problem Solving as Search - I Shobhanjana Kalita Dept. of Computer Science & Engineering Tezpur University Slides prepared from Artificial Intelligence A Modern approach by Russell & Norvig Problem-Solving

More information

The Incremental Evolution of Gaits for Hexapod Robots

The Incremental Evolution of Gaits for Hexapod Robots The Incremental Evolution of Gaits for Hexapod Robots Abstract Gait control programs for hexapod robots are learned by incremental evolution. The first increment is used to learn the activations required

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

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

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

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

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

EE 364B: Wind Farm Layout Optimization via Sequential Convex Programming

EE 364B: Wind Farm Layout Optimization via Sequential Convex Programming EE 364B: Wind Farm Layout Optimization via Sequential Convex Programming Jinkyoo Park 1 Introduction In a wind farm, the wakes formed by upstream wind turbines decrease the power outputs of downstream

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

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

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

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

CENG 466 Artificial Intelligence. Lecture 4 Solving Problems by Searching (II)

CENG 466 Artificial Intelligence. Lecture 4 Solving Problems by Searching (II) CENG 466 Artificial Intelligence Lecture 4 Solving Problems by Searching (II) Topics Search Categories Breadth First Search Uniform Cost Search Depth First Search Depth Limited Search Iterative Deepening

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

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

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and

This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution

More information

ABSTRACT 1 INTRODUCTION

ABSTRACT 1 INTRODUCTION Iterative Product Engineering: Evolutionary Robot Design Dominic. R. Frutiger 1, Josh C. Bongard 2, Fumiya Iida 2 1 Centre of Product Engineering, Swiss Federal Institute of Technology, Zürich, Switzerland

More information

3D Inversion in GM-SYS 3D Modelling

3D Inversion in GM-SYS 3D Modelling 3D Inversion in GM-SYS 3D Modelling GM-SYS 3D provides a wide range of inversion options including inversion for both layer structure and physical properties for gravity and magnetic data. There is an

More information

Evacuation Time Minimization Model using Traffic Simulation and GIS Technology

Evacuation Time Minimization Model using Traffic Simulation and GIS Technology Evacuation Time Minimization Model using Traffic Simulation and GIS Technology Daisik Danny Nam, Presenter Ph.D. Student Department of Civil and Environmental Engineering, University of California, Irvine

More information

Process Control Loops

Process Control Loops In this section, you will learn about how control components and control algorithms are integrated to create a process control system. Because in some processes many variables must be controlled, and each

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

From Passive to Active Dynamic 3D Bipedal Walking - An Evolutionary Approach -

From Passive to Active Dynamic 3D Bipedal Walking - An Evolutionary Approach - From Passive to Active Dynamic 3D Bipedal Walking - An Evolutionary Approach - Steffen Wischmann and Frank Pasemann Fraunhofer Institute for Autonomous Intelligent Systems (AiS) Schloss Birlinghoven, 53754

More information

AIM JOG RUN WALK FAST RUN THINK INCLUSIVE! LiRF Session Card 1

AIM JOG RUN WALK FAST RUN THINK INCLUSIVE! LiRF Session Card 1 LiRF Session Card 1 work at a varying efforts maintaining form. A continuous run with varied pace and effort. The leader determines when and how far or long each effort will be, based on group ability

More information

The Evolution of Transport Planning

The Evolution of Transport Planning The Evolution of Transport Planning On Proportionality and Uniqueness in Equilibrium Assignment Michael Florian Calin D. Morosan Background Several bush-based algorithms for computing equilibrium assignments

More information

COMP9414: Artificial Intelligence Uninformed Search

COMP9414: Artificial Intelligence Uninformed Search COMP9, Monday March, 0 Uninformed Search COMP9: Artificial Intelligence Uninformed Search Overview Breadth-First Search Uniform Cost Search Wayne Wobcke Room J- wobcke@cse.unsw.edu.au Based on slides by

More information

Ocean Fishing Fleet Scheduling Path Optimization Model Research. Based On Improved Ant Colony Algorithm

Ocean Fishing Fleet Scheduling Path Optimization Model Research. Based On Improved Ant Colony Algorithm 4th International Conference on Sensors, Measurement and Intelligent Materials (ICSMIM 205) Ocean Fishing Fleet Scheduling Path Optimization Model Research Based On Improved Ant Colony Algorithm Li Jia-lin2,

More information

A Little Math. Wave speed = wave length/wave period C= L/T. Relationship of Wave Length to Depth of Wave Motion

A Little Math. Wave speed = wave length/wave period C= L/T. Relationship of Wave Length to Depth of Wave Motion Ocean Waves 1 2 1 A Little Math Wave speed = wave length/wave period C= L/T 3 Relationship of Wave Length to Depth of Wave Motion 4 2 Motion of Water as Wave Passes Water in the crest of the wave move

More information

Policy Gradient RL to learn fast walk

Policy Gradient RL to learn fast walk Policy Gradient RL to learn fast walk Goal: Enable an Aibo to walk as fast as possible Policy Gradient RL to learn fast walk Goal: Enable an Aibo to walk as fast as possible Start with a parameterized

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

If you need to reinstall FastBreak Pro you will need to do a complete reinstallation and then install the update.

If you need to reinstall FastBreak Pro you will need to do a complete reinstallation and then install the update. Using this Beta Version of FastBreak Pro First, this new beta version (Version 6.X) will only work with users who have version 5.X of FastBreak Pro. We recommend you read this entire addendum before trying

More information

EVOLVING HEXAPOD GAITS USING A CYCLIC GENETIC ALGORITHM

EVOLVING HEXAPOD GAITS USING A CYCLIC GENETIC ALGORITHM Evolving Hexapod Gaits Using a Cyclic Genetic Algorithm Page 1 of 7 EVOLVING HEXAPOD GAITS USING A CYCLIC GENETIC ALGORITHM GARY B. PARKER, DAVID W. BRAUN, AND INGO CYLIAX Department of Computer Science

More information

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

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

Selection Strategies for Highways. Learning Cooperative Lane

Selection Strategies for Highways. Learning Cooperative Lane From: AAA-98 Proceedings. Copyright 1998, AAA (www.aaai.org). All rights reserved. Learning Cooperative Lane David E. Moriarty nformation Sciences nstitute University of Southern California 4676 Admiralty

More information

Cyrus Soccer 2D Simulation

Cyrus Soccer 2D Simulation Cyrus Soccer 2D Simulation Team Description Paper 2013 Miracle Robotic Group Team Manager : Rouf Khayami Nader Zare, Hossein Zolanvar, Peyman Mahoor Moein Fatehi, Maryam Karimi, Fateme Tekrar, Ehsan Asali

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

Deep-water orbital waves

Deep-water orbital waves What happens when waves approach shore? Deep-water orbital waves Fig. 9.16, p. 211 Wave motion is influenced by water depth and shape of the shoreline wave buildup zone surf zone beach Wave base deepwater

More information

A HYBRID METHOD FOR CALIBRATION OF UNKNOWN PARTIALLY/FULLY CLOSED VALVES IN WATER DISTRIBUTION SYSTEMS ABSTRACT

A HYBRID METHOD FOR CALIBRATION OF UNKNOWN PARTIALLY/FULLY CLOSED VALVES IN WATER DISTRIBUTION SYSTEMS ABSTRACT A HYBRID METHOD FOR CALIBRATION OF UNKNOWN PARTIALLY/FULLY CLOSED VALVES IN WATER DISTRIBUTION SYSTEMS Nhu Cuong Do 1,2, Angus Simpson 3, Jochen Deuerlein 4, Olivier Piller 5 1 University of Saskatchewan,

More information

Transposition Table, History Heuristic, and other Search Enhancements

Transposition Table, History Heuristic, and other Search Enhancements Transposition Table, History Heuristic, and other Search Enhancements Tsan-sheng Hsu tshsu@iis.sinica.edu.tw http://www.iis.sinica.edu.tw/~tshsu 1 Abstract Introduce heuristics for improving the efficiency

More information

Gas-liquid Two-phase Flow Measurement Using Coriolis Flowmeters Incorporating Neural Networks

Gas-liquid Two-phase Flow Measurement Using Coriolis Flowmeters Incorporating Neural Networks Gas-liquid Two-phase Flow Measurement Using Coriolis Flowmeters Incorporating Neural Networks Lijuan Wang a, Jinyu Liu a,yong Yan a, Xue Wang b, Tao Wang c a School of Engineering and Digital Arts University

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

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

Design Linear Quadratic Gaussian for Controlling the Blood Pressure of Patient

Design Linear Quadratic Gaussian for Controlling the Blood Pressure of Patient Design Linear Quadratic Gaussian for Controlling the Blood Pressure of Patient Noor Safaa Abdul-Jaleel Department of Electrical Engineering Assist. Lect. In Al-Mustansyria University Baghdad, Iraq Abstract:

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

SIDT 2017 XXII SEMINARIO SCIENTIFICO DELLA SOCIETÀ ITALIANA DOCENTI DI TRASPORTI

SIDT 2017 XXII SEMINARIO SCIENTIFICO DELLA SOCIETÀ ITALIANA DOCENTI DI TRASPORTI SIDT 2017 XXII SEMINARIO SCIENTIFICO DELLA SOCIETÀ ITALIANA DOCENTI DI TRASPORTI POLITECNICO DI BARI TOWARDS SUSTAINABLE CITIES: INNOVATIVE SOLUTIONS FOR MOBILITY AND LOGISTICS SEPTEMBER 14-15, 2017 SESSION

More information

Problem Solving Agents

Problem Solving Agents Problem Solving Agents A problem solving agent is one which decides what actions and states to consider in completing a goal Examples: Finding the shortest path from one city to another 8-puzzle Problem

More information

Application of Dijkstra s Algorithm in the Evacuation System Utilizing Exit Signs

Application of Dijkstra s Algorithm in the Evacuation System Utilizing Exit Signs Application of Dijkstra s Algorithm in the Evacuation System Utilizing Exit Signs Jehyun Cho a, Ghang Lee a, Jongsung Won a and Eunseo Ryu a a Dept. of Architectural Engineering, University of Yonsei,

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

2007 Gas-Lift Workshop

2007 Gas-Lift Workshop 2007 Gas-Lift Workshop Field Application of Automation and Control Equipment by Cleon Dunham Oilfield Automation Consulting 2/11/2007 2007 Gas-Lift Workshop 1 Gas-Lift Automation & Control Equipment Outline

More information

Optimization of a Wing-Sail shape for a small boat

Optimization of a Wing-Sail shape for a small boat STAR Global Conference 2014 Vienna, March 17-19 Optimization of a Wing-Sail shape for a small boat G. Lombardi, F. Cartoni, M. Maganzi Dept. of Civil and Industrial Engineering of Pisa Aeronautical Section

More information

Genetic Programming of Multi-agent System in the RoboCup Domain

Genetic Programming of Multi-agent System in the RoboCup Domain Genetic Programming of Multi-agent System in the RoboCup Domain by Jonatan Aronsson A thesis presented to the Lund Institute of Technology for the degree of Master of Science in Engineering Physics Lund,

More information

Princess Nora University Faculty of Computer & Information Systems ARTIFICIAL INTELLIGENCE (CS 370D) Computer Science Department

Princess Nora University Faculty of Computer & Information Systems ARTIFICIAL INTELLIGENCE (CS 370D) Computer Science Department Princess Nora University Faculty of Computer & Information Systems 1 ARTIFICIAL INTELLIGENCE (CS 370D) Computer Science Department (CHAPTER-3-PART2) PROBLEM SOLVING AND SEARCH (Course coordinator) Searching

More information

THe rip currents are very fast moving narrow channels,

THe rip currents are very fast moving narrow channels, 1 Rip Current Detection using Optical Flow Shweta Philip sphilip@ucsc.edu Abstract Rip currents are narrow currents of fast moving water that are strongest near the beach. These type of currents are dangerous

More information

Gait Evolution for a Hexapod Robot

Gait Evolution for a Hexapod Robot Gait Evolution for a Hexapod Robot Karen Larochelle, Sarah Dashnaw, and Gary Parker Computer Science Connecticut College 270 Mohegan Avenue New London, CT 06320 @conncoll.edu Abstract

More information

An Investigation into the Effectiveness of an Artificial Neural Network in the Prediction of Results in British Flat Racing

An Investigation into the Effectiveness of an Artificial Neural Network in the Prediction of Results in British Flat Racing An Investigation into the Effectiveness of an Artificial Neural Network in the Prediction of Results in British Flat Racing Donald John Nairn September 2010 Dissertation submitted in partial fulfilment

More information

,WHUDWLYH3URGXFW(QJLQHHULQJ(YROXWLRQDU\5RERW'HVLJQ

,WHUDWLYH3URGXFW(QJLQHHULQJ(YROXWLRQDU\5RERW'HVLJQ ,WHUDWLYH3URGXFW(QJLQHHULQJ(YROXWLRQDU\5RERW'HVLJQ 'RPLQLF5)UXWLJHU -RVK&%RQJDUG )XPL\D,LGD 1 Centre of Product Engineering, Swiss Federal Institute of Technology, Zürich, Switzerland 2 Artificial Intelligence

More information

Project Title: Pneumatic Exercise Machine

Project Title: Pneumatic Exercise Machine EEL 4924 Electrical Engineering Design (Senior Design) Preliminary Design Report 27 January 2011 Project Title: Pneumatic Exercise Machine Team Members: Name: Gino Tozzi Name: Seok Hyun (John) Yun Email:

More information

Genetic Algorithm Optimized Gravity Based RoboCup Soccer Team

Genetic Algorithm Optimized Gravity Based RoboCup Soccer Team Genetic Algorithm Optimized Gravity Based RoboCup Soccer Team Tory Harter Advisor: Dr. Jon Denning Taylor University July 28, 2015 ABSTRACT This report describes how we use genetic algorithms to optimize

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

Tokyo: Simulating Hyperpath-Based Vehicle Navigations and its Impact on Travel Time Reliability

Tokyo: Simulating Hyperpath-Based Vehicle Navigations and its Impact on Travel Time Reliability CHAPTER 92 Tokyo: Simulating Hyperpath-Based Vehicle Navigations and its Impact on Travel Time Reliability Daisuke Fukuda, Jiangshan Ma, Kaoru Yamada and Norihito Shinkai 92.1 Introduction Most standard

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

Better Search Improved Uninformed Search CIS 32

Better Search Improved Uninformed Search CIS 32 Better Search Improved Uninformed Search CIS 32 Functionally PROJECT 1: Lunar Lander Game - Demo + Concept - Open-Ended: No One Solution - Menu of Point Options - Get Started NOW!!! - Demo After Spring

More information

Workshop 1: Bubbly Flow in a Rectangular Bubble Column. Multiphase Flow Modeling In ANSYS CFX Release ANSYS, Inc. WS1-1 Release 14.

Workshop 1: Bubbly Flow in a Rectangular Bubble Column. Multiphase Flow Modeling In ANSYS CFX Release ANSYS, Inc. WS1-1 Release 14. Workshop 1: Bubbly Flow in a Rectangular Bubble Column 14. 5 Release Multiphase Flow Modeling In ANSYS CFX 2013 ANSYS, Inc. WS1-1 Release 14.5 Introduction This workshop models the dispersion of air bubbles

More information

Mechanical Ventilation

Mechanical Ventilation Mechanical Ventilation Understanding Modes Rob Chatburn, RRT-NPS, FAARC Research Manager Respiratory Therapy Cleveland Clinic Associate Professor Case Western Reserve University 1 Overview Characteristics

More information

Soccereus 2D Simulation Team Description Paper

Soccereus 2D Simulation Team Description Paper Soccereus 2D Simulation Team Description Paper Shayan Salehian 1, Ehsan Imani 2 Anahita Hosseini 3, Sahand Mozaffari 4, and Mohammad Ali Baghershemirani 5 1 salehian@ce.sharif.edu, Sharif University of

More information

Atmospheric Waves James Cayer, Wesley Rondinelli, Kayla Schuster. Abstract

Atmospheric Waves James Cayer, Wesley Rondinelli, Kayla Schuster. Abstract Atmospheric Waves James Cayer, Wesley Rondinelli, Kayla Schuster Abstract It is important for meteorologists to have an understanding of the synoptic scale waves that propagate thorough the atmosphere

More information

Resource Allocation for Malaria Prevention

Resource Allocation for Malaria Prevention Resource Allocation for Malaria Prevention Final Presentation April 17, 2008 Michele Cataldi Christina Cho Cesar Gutierrez Jeff Hull Phillip Kim Andrew Park Sponsor Contact: Jason Pickering, PhD. Faculty

More information

Generating Arachnid Robot Gaits with Cyclic Genetic Algorithms

Generating Arachnid Robot Gaits with Cyclic Genetic Algorithms Generating Arachnid Robot Gaits with Cyclic Genetic Algorithms Gary B. Parker Department of Computer Science Indiana University Bloomington, IN gaparker@cs.indiana.edu http://www.cs.indiana.edu/hyplan/gaparker.html

More information

Visual Coding in the H1 Neuron of a Blowfly

Visual Coding in the H1 Neuron of a Blowfly Visual Coding in the H1 Neuron of a Blowfly Justin Chin TA: Jeff Moore UCSD Modern Physics Laboratory: Biological and Quantum Physics Course, Prof. Philibert Tsai Introduction The H1 neuron in flies has

More information

Representation. Representation. Representation. Representation. 8 puzzle.

Representation. Representation. Representation. Representation. 8 puzzle. You have a 3-liter jug and a 4-liter jug, and need to measure out exactly two liters of water. the jugs do not have any measurement lines you don't have any additional containers 8 puzzle. Measuring water.

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

Homework: Turn in Tortoise & the Hare

Homework: Turn in Tortoise & the Hare Your Learning Goal: After students experienced speed in the Runner s Speed Lab, they will be able to describe how different speeds look like on a graph with 100% accuracy. Table of Contents: Notes: Graphs

More information

Chapter 23 Traffic Simulation of Kobe-City

Chapter 23 Traffic Simulation of Kobe-City Chapter 23 Traffic Simulation of Kobe-City Yuta Asano, Nobuyasu Ito, Hajime Inaoka, Tetsuo Imai, and Takeshi Uchitane Abstract A traffic simulation of Kobe-city was carried out. In order to simulate an

More information

An approach for optimising railway traffic flow on high speed lines with differing signalling systems

An approach for optimising railway traffic flow on high speed lines with differing signalling systems Computers in Railways XIII 27 An approach for optimising railway traffic flow on high speed lines with differing signalling systems N. Zhao, C. Roberts & S. Hillmansen Birmingham Centre for Railway Research

More information

MA PM: Memetic algorithms with population management

MA PM: Memetic algorithms with population management MA PM: Memetic algorithms with population management Kenneth Sörensen University of Antwerp kenneth.sorensen@ua.ac.be Marc Sevaux University of Valenciennes marc.sevaux@univ-valenciennes.fr August 2004

More information

WONDERLAB: THE EQUINOR GALLERY. The science and maths behind the exhibits 30 MIN INFORMATION. Topic FORCES. Age

WONDERLAB: THE EQUINOR GALLERY. The science and maths behind the exhibits 30 MIN INFORMATION. Topic FORCES. Age WONDERLAB: THE EQUINOR GALLERY and maths s INFORMATION Age 7 11 11 14 Topic FORCES 30 MIN Location LEVEL 3, SCIENCE MUSEUM, LONDON What s the science? What more will you wonder? and maths s Wonderlab:

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

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

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