Fast R-CNN. Ross Girshick Facebook AI Research (FAIR) Work done at Microsoft Research. Presented by: Nick Joodi Doug Sherman
|
|
- Audra Suzanna Powers
- 5 years ago
- Views:
Transcription
1 Fast R-CNN Ross Girshick Facebook AI Research (FAIR) Work done at Microsoft Research Presented by: Nick Joodi Doug Sherman
2 Fast Region-based ConvNets (R-CNNs) Fast Sorry about the black BG, Girshick s slides were all black. 2
3 The Pascal Visual Object Classes Challenge Overview Classification, Detection, Segmentation For each image: Does it contain the class? classification Where is it? detection via bounding box Evaluation Mean Average Precision (map) Participants submitted results in the form of confidence Produce Precision Recall curves Average precision for each class Take mean to get map 3
4 Object detection renaissance (2013-Present) 4
5 Object detection renaissance (2013-Present) 5
6 Object detection renaissance (2013-Present) 6
7 Agenda 1. Pre-existing Models a. b. 2. Ways to improve a. b. 3. Slow R-CNN SPP-net SGD Mini-Batch New Loss Function Fast R-CNN a. b. Architecture Results & Future Work 7
8 Region-based convnets (R-CNNs) R-CNN (aka slow R-CNN ) [Girshick et al. CVPR14] SPP-net [He et al. ECCV14] 8
9 9
10 10
11 11
12 12
13 13
14 14
15 What s wrong with slow R-CNN? Ad hoc training objectives Fine-tune network with softmax classifier (log loss) Train post-hoc linear SVMs (hinge loss) Train post-hoc bounding-box regressors (L2 loss) 15
16 What s wrong with slow R-CNN? Ad hoc training objectives Fine-tune network with softmax classifier (log loss) Train post-hoc linear SVMs (hinge loss) Train post-hoc bounding-box regressors (L2 loss) Training is slow (84h), takes a lot of disk space 16
17 What s wrong with slow R-CNN? Ad hoc training objectives Fine-tune network with softmax classifier (log loss) Train post-hoc linear SVMs (hinge loss) Train post-hoc bounding-box regressors (L2 loss) Training is slow (84h), takes a lot of disk space Inference (detection) is slow 47s / image with VGG16 [Simonyan & Zisserman. ICLR15] Fixed by SPP-net [He et al. ECCV14] 17
18 Agenda 1. Pre-existing Models a. b. 2. Ways to improve a. b. 3. Slow R-CNN SPP-net SGD Mini-Batch New Loss Function Fast R-CNN a. b. Architecture Results & Future Work 18
19 19
20 20
21 21
22 22
23 23
24 24
25 Pyramid Pooling Layer (w/4 x h/4) (2 x 1) To FC (w/2 x h/2) (4 x 2) (w/1 x h/1) (8 x 2) Region Stride/Window Size Output of Pooling Concatenated 25
26 26
27 What s wrong with SPP-net? Inherits the rest of R-CNN s problems Ad hoc training objective Training is slow (25h), takes a lot of disk space Introduces a new problem: cannot update parameters below SPP layer during training 27
28 28
29 Agenda 1. Pre-existing Models a. b. 2. Ways to improve a. b. 3. Slow R-CNN SPP-net SGD Mini-Batch New Loss Function Fast R-CNN a. b. Architecture Results & Future Work 29
30 SGD Mini-Batch Method for RoIs 30
31 SGD Mini-Batch Method for RoIs 31
32 SGD Mini-Batch Method for RoIs Input size for SPP-net 32
33 SGD Mini-Batch Method for RoIs 33
34 SGD Mini-Batch Method for RoIs 34
35 SGD Mini-Batch Method for RoIs 35
36 SGD Mini-Batch Method for RoIs 36
37 SGD Mini-Batch Method for RoIs 37
38 Agenda 1. Pre-existing Models a. b. 2. Ways to improve a. b. 3. Slow R-CNN SPP-net SGD Mini-Batch New Loss Function Fast R-CNN a. b. c. Architecture Results Future Work 38
39 Revised loss function For the classification For the bounding box p: Predicted RoI Classification u: True RoI Classification tu = (tx,ty,tw,th): Predicted Bounding Box v = (vx,vy,vw,vh): True Bounding Box ƛ : Controls the balance between the two losses 39
40 Revised loss function 40
41 Revised loss function Smooth: Continuously Differentiable 41
42 Agenda 1. Pre-existing Models a. b. 2. Ways to improve a. b. 3. Slow R-CNN SPP-net SGD Mini-Batch New Loss Function Fast R-CNN a. b. Architecture Results & Future Work 42
43 Fast R-CNN Fast test-time, like SPP-net One network, trained in one stage Higher mean average precision than slow R-CNN and SPP-net 43
44 44
45 45
46 46
47 47
48 48
49 49
50 50
51 Agenda 1. Pre-existing Models a. b. 2. Ways to improve a. b. 3. Slow R-CNN SPP-net SGD Mini-Batch New Loss Function Fast R-CNN a. b. Architecture Results & Future Work 51
52 52
53 53
54 54
55 What s still wrong? Out-of-network region proposals Selective search: 2s / img; EdgeBoxes: 0.2s / img Fortunately, this has already been solved S. Ren, K. He, R. Girshick & J. Sun. Faster R'CNN: Towards Real'Time Object Detection with Region Proposal Networks. NIPS (2015). 55
56 Fast R-CNN take-aways End-to-end training of deep ConvNets for object detection Fast training times Open source for easy experimentation A large number of ImageNet detection and COCO detection methods are built on Fast R-CNN 56
$tock Forecasting using Machine Learning
$tock Forecasting using Machine Learning Greg Colvin, Garrett Hemann, and Simon Kalouche Abstract We present an implementation of 3 different machine learning algorithms gradient descent, support vector
More informationScaling SGD Batch Size to 32K for ImageNet Training
Scaling SGD Batch Size to 32K for ImageNet Training Yang You Computer Science Division of UC Berkeley youyang@cs.berkeley.edu Yang You (youyang@cs.berkeley.edu) 32K SGD Batch Size CS Division of UC Berkeley
More informationPredicting stock prices for large-cap technology companies
Predicting stock prices for large-cap technology companies 15 th December 2017 Ang Li (al171@stanford.edu) Abstract The goal of the project is to predict price changes in the future for a given stock.
More informationMachine Learning (CSE 446): Pratical issues: optimization and learning
Machine Learning (CSE 446): Pratical issues: optimization and learning John Thickstun guest lecture c 2018 University of Washington cse446-staff@cs.washington.edu 1 / 10 Review 1 / 10 Our running example
More informationExploring the Potential of Image-based Deep Learning in Insurance. Luisa F. Polanía Cabrera
Exploring the Potential of Image-based Deep Learning in Insurance Luisa F. Polanía Cabrera 1 Madison, Wisconsin based American Family Insurance is the nation's third-largest mutual property/casualty insurance
More informationSupport Vector Machines: Training with Stochastic Gradient Descent
Support Vector Machines: Training with Stochastic Gradient Descent Machine Learning Spring 2018 The slides are mainly from Vivek Srikumar 1 Support vector machines Training by maximizing margin The SVM
More informationTwo kinds of neural networks, a feed forward multi layer Perceptron (MLP)[1,3] and an Elman recurrent network[5], are used to predict a company's
LITERATURE REVIEW 2. LITERATURE REVIEW Detecting trends of stock data is a decision support process. Although the Random Walk Theory claims that price changes are serially independent, traders and certain
More informationUnderstanding Deep Learning Requires Rethinking Generalization
Understanding Deep Learning Requires Rethinking Generalization ChiyuanZhang 1 Samy Bengio 3 Moritz Hardt 3 Benjamin Recht 2 Oriol Vinyals 4 1 Massachusetts Institute of Technology 2 University of California,
More informationNovel Approaches to Sentiment Analysis for Stock Prediction
Novel Approaches to Sentiment Analysis for Stock Prediction Chris Wang, Yilun Xu, Qingyang Wang Stanford University chrwang, ylxu, iriswang @ stanford.edu Abstract Stock market predictions lend themselves
More informationModerator: Ann Weber, JD. Presenters: Dan Adamson Angela Nelson
Session 103 PD - Use of Artificial Intelligence in GI: Industry Opportunities and Regulatory Challenges Moderator: Ann Weber, JD Presenters: Dan Adamson Angela Nelson SOA Antitrust Compliance Guidelines
More informationdistribution of the best bid and ask prices upon the change in either of them. Architecture Each neural network has 4 layers. The standard neural netw
A Survey of Deep Learning Techniques Applied to Trading Published on July 31, 2016 by Greg Harris http://gregharris.info/a-survey-of-deep-learning-techniques-applied-t o-trading/ Deep learning has been
More informationBayesian Deep Learning
Bayesian Deep Learning Dealing with uncertainty and non-stationarity Dr. Thomas Wiecki @twie cki Director of Data Science, Quantopian Disclaimer This presentation is for informational purposes only and
More informationCAES Workshop: Risk Management and Commodity Market Analysis
CAES Workshop: Risk Management and Commodity Market Analysis ARE THE EUROPEAN CARBON MARKETS EFFICIENT? -- UPDATED Speaker: Peter Bell April 12, 2010 UBC Robson Square 1 Brief Thanks, Personal Promotion
More informationLeverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks
Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks Yangtuo Peng A THESIS SUBMITTED TO THE FACULTY OF GRADUATE STUDIES IN PARTIAL FULFILLMENT OF THE
More informationGradient Descent and the Structure of Neural Network Cost Functions. presentation by Ian Goodfellow
Gradient Descent and the Structure of Neural Network Cost Functions presentation by Ian Goodfellow adapted for www.deeplearningbook.org from a presentation to the CIFAR Deep Learning summer school on August
More informationYao s Minimax Principle
Complexity of algorithms The complexity of an algorithm is usually measured with respect to the size of the input, where size may for example refer to the length of a binary word describing the input,
More informationOracle Financial Services FATCA Management User Guide. Release 1.0 January 2013
Oracle Financial Services FATCA Management User Guide Release 1.0 January 2013 Oracle Financial Services FATCA Management User Guide Release 1.0 January 2013 Document Control Number: 9RVE1181001-0001
More informationk-layer neural networks: High capacity scoring functions + tips on how to train them
k-layer neural networks: High capacity scoring functions + tips on how to train them A new class of scoring functions Linear scoring function s = W x + b 2-layer Neural Network s 1 = W 1 x + b 1 h = max(0,
More informationUsing Structured Events to Predict Stock Price Movement: An Empirical Investigation. Yue Zhang
Using Structured Events to Predict Stock Price Movement: An Empirical Investigation Yue Zhang My research areas This talk Reading news from the Internet and predicting the stock market Outline Introduction
More informationDeep Learning - Financial Time Series application
Chen Huang Deep Learning - Financial Time Series application Use Deep learning to learn an existing strategy Warning Don t Try this at home! Investment involves risk. Make sure you understand the risk
More informationLearning Curve Theory
7 Learning Curve Theory LEARNING OBJECTIVES : After studying this unit, you will be able to : l Understand, visualize and explain learning curve phenomenon. l Measure how in some industries and in some
More informationMarkov Decision Process
Markov Decision Process Human-aware Robotics 2018/02/13 Chapter 17.3 in R&N 3rd Ø Announcement: q Slides for this lecture are here: http://www.public.asu.edu/~yzhan442/teaching/cse471/lectures/mdp-ii.pdf
More informationMS&E 448 Final Presentation High Frequency Algorithmic Trading
MS&E 448 Final Presentation High Frequency Algorithmic Trading Francis Choi George Preudhomme Nopphon Siranart Roger Song Daniel Wright Stanford University June 6, 2017 High-Frequency Trading MS&E448 June
More informationBased on BP Neural Network Stock Prediction
Based on BP Neural Network Stock Prediction Xiangwei Liu Foundation Department, PLA University of Foreign Languages Luoyang 471003, China Tel:86-158-2490-9625 E-mail: liuxwletter@163.com Xin Ma Foundation
More informationGenerate Higher Conversions
Generate Higher Conversions AdWords Spend Optimizer TM uses data science to deliver results Data Analytics Spreadsheet Modeling New Yor Boston San Francisco Hyderabad Perceptive-Analytics.com (646) 583
More informationLendingClub Loan Default and Profitability Prediction
LendingClub Loan Default and Profitability Prediction Peiqian Li peiqian@stanford.edu Gao Han gh352@stanford.edu Abstract Credit risk is something all peer-to-peer (P2P) lending investors (and bond investors
More informationMarkov Decision Processes
Markov Decision Processes Robert Platt Northeastern University Some images and slides are used from: 1. CS188 UC Berkeley 2. AIMA 3. Chris Amato Stochastic domains So far, we have studied search Can use
More informationRole of soft computing techniques in predicting stock market direction
REVIEWS Role of soft computing techniques in predicting stock market direction Panchal Amitkumar Mansukhbhai 1, Dr. Jayeshkumar Madhubhai Patel 2 1. Ph.D Research Scholar, Gujarat Technological University,
More informationLarge-Scale SVM Optimization: Taking a Machine Learning Perspective
Large-Scale SVM Optimization: Taking a Machine Learning Perspective Shai Shalev-Shwartz Toyota Technological Institute at Chicago Joint work with Nati Srebro Talk at NEC Labs, Princeton, August, 2008 Shai
More informationMACROECONOMICS II - IS-LM (Part 1)
MACROECONOMICS II - IS-LM (Part 1) Stefania MARCASSA stefania.marcassa@u-cergy.fr http://stefaniamarcassa.webstarts.com/teaching.html 2016-2017 Plan (1) the IS curve and its relation to: the Keynesian
More informationSTOCK PRICE PREDICTION: KOHONEN VERSUS BACKPROPAGATION
STOCK PRICE PREDICTION: KOHONEN VERSUS BACKPROPAGATION Alexey Zorin Technical University of Riga Decision Support Systems Group 1 Kalkyu Street, Riga LV-1658, phone: 371-7089530, LATVIA E-mail: alex@rulv
More informationNPTEL Project. Econometric Modelling. Module 16: Qualitative Response Regression Modelling. Lecture 20: Qualitative Response Regression Modelling
1 P age NPTEL Project Econometric Modelling Vinod Gupta School of Management Module 16: Qualitative Response Regression Modelling Lecture 20: Qualitative Response Regression Modelling Rudra P. Pradhan
More informationPredicting the Success of a Retirement Plan Based on Early Performance of Investments
Predicting the Success of a Retirement Plan Based on Early Performance of Investments CS229 Autumn 2010 Final Project Darrell Cain, AJ Minich Abstract Using historical data on the stock market, it is possible
More informationDeep Learning for Time Series Analysis
CS898 Deep Learning and Application Deep Learning for Time Series Analysis Bo Wang Scientific Computation Lab 1 Department of Computer Science University of Waterloo Outline 1. Background Knowledge 2.
More informationTHE PROBLEM THERE IS AN INFORMATION CRISIS IN CONSUMER FINANCE LATIKA. Emilian. Alternative online lender without enough data
THE PROBLEM THERE IS AN INFORMATION CRISIS IN CONSUMER FINANCE NEEDS A LOAN WANTS TO LEND LATIKA Small business owner in India Emilian Alternative online lender without enough data INTRODUCTION WHAT IS
More informationIndividual Asset Transfer
ADVISOR USE ONLY Individual Asset Transfer ADVISOR GUIDE Life s brighter under the sun INTRODUCTION If you type insurance as an asset class in your favourite internet search engine, you may be surprised
More informationAnswer Key. EC 2273 Problem Set 1. Professor Nyshadham. Spring 2017
EC 2273 Problem Set 1 Professor Nyshadham Spring 2017 Answer Key 1. A visual look at the world In the first class I asked you to write down three characteristics of an under-developed nation. (If you have
More informationfinancial modelling & business analysis in the mining industry Rogers Analytics
financial modelling & business analysis in the mining industry Rogers Analytics & Xeras Software Rogers Analytics financial planning applications are built on the Xeras* financial modelling software platform.
More informationFX Smile Modelling. 9 September September 9, 2008
FX Smile Modelling 9 September 008 September 9, 008 Contents 1 FX Implied Volatility 1 Interpolation.1 Parametrisation............................. Pure Interpolation.......................... Abstract
More informationRecurrent Residual Network
Recurrent Residual Network 2016/09/23 Abstract This work briefly introduces the recurrent residual network which is a combination of the residual network and the long short term memory network(lstm). The
More informationPredictive Model Learning of Stochastic Simulations. John Hegstrom, FSA, MAAA
Predictive Model Learning of Stochastic Simulations John Hegstrom, FSA, MAAA Table of Contents Executive Summary... 3 Choice of Predictive Modeling Techniques... 4 Neural Network Basics... 4 Financial
More informationApplying Image Recognition to Insurance
Applying Image Recognition to Insurance June 2018 2 Applying Image Recognition to Insurance AUTHOR Kailan Shang, FSA, CFA, PRM, SCJP SPONSOR Society of Actuaries Research Expanding Boundaries Pool Caveat
More informationA Short Survey on Pursuit-Evasion Games
A Short Survey on Pursuit-Evasion Games Peng Cheng Dept. of Computer Science University of Illinois at Urbana-Champaign 1 Introduction Pursuit-evasion game is about how to guide one or a group of pursuers
More informationUNDERSTANDING ML/DL MODELS USING INTERACTIVE VISUALIZATION TECHNIQUES
UNDERSTANDING ML/DL MODELS USING INTERACTIVE VISUALIZATION TECHNIQUES Chakri Cherukuri Senior Researcher Quantitative Financial Research Group 1 OUTLINE Introduction Applied machine learning in finance
More informationLecture Notes: Basic Concepts in Option Pricing - The Black and Scholes Model (Continued)
Brunel University Msc., EC5504, Financial Engineering Prof Menelaos Karanasos Lecture Notes: Basic Concepts in Option Pricing - The Black and Scholes Model (Continued) In previous lectures we saw that
More informationUnderstand general-equilibrium relationships, such as the relationship between barriers to trade, and the domestic distribution of income.
Review of Production Theory: Chapter 2 1 Why? Understand the determinants of what goods and services a country produces efficiently and which inefficiently. Understand how the processes of a market economy
More informationForecasting Stock Prices from the Limit Order Book using Convolutional Neural Networks
Forecasting Stock Prices from the Limit Order Book using Convolutional Neural Networks Avraam Tsantekidis, Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj and Alexandros Iosifidis
More informationThe Big Picture. Macro Principles. Lecture 1
What is Macroeconomics? GDP Other Measures The Big Picture Macro Principles Lecture 1 Growth Fluctuations Today s Topics The main ideas in this lecture What do we mean by macroeconomics? What are the major
More informationCS 343: Artificial Intelligence
CS 343: Artificial Intelligence Markov Decision Processes II Prof. Scott Niekum The University of Texas at Austin [These slides based on those of Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC
More informationReal Options. Katharina Lewellen Finance Theory II April 28, 2003
Real Options Katharina Lewellen Finance Theory II April 28, 2003 Real options Managers have many options to adapt and revise decisions in response to unexpected developments. Such flexibility is clearly
More informationAccelerated Option Pricing Multiple Scenarios
Accelerated Option Pricing in Multiple Scenarios 04.07.2008 Stefan Dirnstorfer (stefan@thetaris.com) Andreas J. Grau (grau@thetaris.com) 1 Abstract This paper covers a massive acceleration of Monte-Carlo
More informationArtificial Neural Networks Lecture Notes
Artificial Neural Networks Lecture Notes Part 10 About this file: This is the printer-friendly version of the file "lecture10.htm". In case the page is not properly displayed, use IE 5 or higher. Since
More informationIntro to GLM Day 2: GLM and Maximum Likelihood
Intro to GLM Day 2: GLM and Maximum Likelihood Federico Vegetti Central European University ECPR Summer School in Methods and Techniques 1 / 32 Generalized Linear Modeling 3 steps of GLM 1. Specify the
More informationFull Monte. Looking at your project through rose-colored glasses? Let s get real.
Realistic plans for project success. Looking at your project through rose-colored glasses? Let s get real. Full Monte Cost and schedule risk analysis add-in for Microsoft Project that graphically displays
More informationGame Theory and Economics Prof. Dr. Debarshi Das Department of Humanities and Social Sciences Indian Institute of Technology, Guwahati
Game Theory and Economics Prof. Dr. Debarshi Das Department of Humanities and Social Sciences Indian Institute of Technology, Guwahati Module No. # 03 Illustrations of Nash Equilibrium Lecture No. # 02
More informationCLASS 4: ASSEt pricing. The Intertemporal Model. Theory and Experiment
CLASS 4: ASSEt pricing. The Intertemporal Model. Theory and Experiment Lessons from the 1- period model If markets are complete then the resulting equilibrium is Paretooptimal (no alternative allocation
More informationIn physics and engineering education, Fermi problems
A THOUGHT ON FERMI PROBLEMS FOR ACTUARIES By Runhuan Feng In physics and engineering education, Fermi problems are named after the physicist Enrico Fermi who was known for his ability to make good approximate
More informationMachine Learning in mathematical Finance
Machine Learning in mathematical Finance Josef Teichmann ETH Zürich December 15, 2017 Josef Teichmann (ETH Zürich) Machine Learning in mathematical Finance December 15, 2017 1 / 37 1 Introduction 2 Machine
More informationThe Dynamic Cross-sectional Microsimulation Model MOSART
Third General Conference of the International Microsimulation Association Stockholm, June 8-10, 2011 The Dynamic Cross-sectional Microsimulation Model MOSART Dennis Fredriksen, Pål Knudsen and Nils Martin
More informationAnalyzing the Elements of Real GDP in FRED Using Stacking
Tools for Teaching with Analyzing the Elements of Real GDP in FRED Using Stacking Author Mark Bayles, Senior Economic Education Specialist Introduction This online activity shows how to use FRED, the Federal
More informationSterman, J.D Business dynamics systems thinking and modeling for a complex world. Boston: Irwin McGraw Hill
Sterman,J.D.2000.Businessdynamics systemsthinkingandmodelingfora complexworld.boston:irwinmcgrawhill Chapter7:Dynamicsofstocksandflows(p.231241) 7 Dynamics of Stocks and Flows Nature laughs at the of integration.
More informationStock Trading Following Stock Price Index Movement Classification Using Machine Learning Techniques
Stock Trading Following Stock Price Index Movement Classification Using Machine Learning Techniques 6.1 Introduction Trading in stock market is one of the most popular channels of financial investments.
More informationTop-down particle filtering for Bayesian decision trees
Top-down particle filtering for Bayesian decision trees Balaji Lakshminarayanan 1, Daniel M. Roy 2 and Yee Whye Teh 3 1. Gatsby Unit, UCL, 2. University of Cambridge and 3. University of Oxford Outline
More informationMFE Course Details. Financial Mathematics & Statistics
MFE Course Details Financial Mathematics & Statistics FE8506 Calculus & Linear Algebra This course covers mathematical tools and concepts for solving problems in financial engineering. It will also help
More information* The Unlimited Plan costs $100 per month for as many minutes as you care to use.
Problem: You walk into the new Herizon Wireless store, which just opened in the mall. They offer two different plans for voice (the data and text plans are separate): * The Unlimited Plan costs $100 per
More informationBased on the audacious premise that a lot more can be done with a lot less.
A lot less of IT involvement, minimal processes, greater attention to high-value tasks, enhanced decision-making all resulting in better underwriting. Based on the audacious premise that a lot more can
More informationT2S workshop on Settlement Optimisation Objectives
T2S workshop on Settlement Optimisation Objectives Part 3: PRESENTATION ON SETTLEMENT OPTIMISATION OBJECTIVES Paris Sept 16th 2011 AGENDA part 3 1. Optimisation features of T2S 1. What is optimisation?
More informationSTOCK MARKET PREDICTION AND ANALYSIS USING MACHINE LEARNING
STOCK MARKET PREDICTION AND ANALYSIS USING MACHINE LEARNING Sumedh Kapse 1, Rajan Kelaskar 2, Manojkumar Sahu 3, Rahul Kamble 4 1 Student, PVPPCOE, Computer engineering, PVPPCOE, Maharashtra, India 2 Student,
More informationThe Kalman filter - and other methods
The Kalman filter - and other methods Anders Ringgaard Kristensen Slide 1 Outline Filtering techniques applied to monitoring of daily gain in slaughter pigs: Introduction Basic monitoring Shewart control
More informationThe Kalman filter - and other methods
The Kalman filter - and other methods Anders Ringgaard Kristensen Slide 1 Outline Filtering techniques applied to monitoring of daily gain in slaughter pigs: Introduction Basic monitoring Shewart control
More informationStock Price Prediction using Deep Learning
San Jose State University SJSU ScholarWorks Master's Projects Master's Theses and Graduate Research Spring 2018 Stock Price Prediction using Deep Learning Abhinav Tipirisetty San Jose State University
More informationAccepted Manuscript. Enterprise Credit Risk Evaluation Based on Neural Network Algorithm. Xiaobing Huang, Xiaolian Liu, Yuanqian Ren
Accepted Manuscript Enterprise Credit Risk Evaluation Based on Neural Network Algorithm Xiaobing Huang, Xiaolian Liu, Yuanqian Ren PII: S1389-0417(18)30213-4 DOI: https://doi.org/10.1016/j.cogsys.2018.07.023
More informationDistributed Approaches to Mirror Descent for Stochastic Learning over Rate-Limited Networks
Distributed Approaches to Mirror Descent for Stochastic Learning over Rate-Limited Networks, Detroit MI (joint work with Waheed Bajwa, Rutgers) Motivation: Autonomous Driving Network of autonomous automobiles
More informationSAS Data Mining & Neural Network as powerful and efficient tools for customer oriented pricing and target marketing in deregulated insurance markets
SAS Data Mining & Neural Network as powerful and efficient tools for customer oriented pricing and target marketing in deregulated insurance markets Stefan Lecher, Actuary Personal Lines, Zurich Switzerland
More informationProxy Modelling An in-cycle solution with Least Squares Monte Carlo
Proxy Modelling An in-cycle solution with Least Squares Monte Carlo Shaun Gibbs Nick Jackson Russell Ward 10 November 2017 Contents: Introduction. LSMC Actuarial techniques. LSMC systems and process architecture.
More informationMaking Hard Decision. ENCE 627 Decision Analysis for Engineering. Identify the decision situation and understand objectives. Identify alternatives
CHAPTER Duxbury Thomson Learning Making Hard Decision Third Edition RISK ATTITUDES A. J. Clark School of Engineering Department of Civil and Environmental Engineering 13 FALL 2003 By Dr. Ibrahim. Assakkaf
More informationInventory Models for Special Cases: Multiple Items & Locations
CTL.SC1x -Supply Chain & Logistics Fundamentals Inventory Models for Special Cases: Multiple Items & Locations MIT Center for Transportation & Logistics Agenda Inventory Policies for Multiple Items Grouping
More informationEstimating A Smooth Term Structure of Interest Rates
E STIMATING A SMOOTH LTA 2/98 TERM STRUCTURE P. 159 177 OF INTEREST RATES JARI KÄPPI 1 Estimating A Smooth Term Structure of Interest Rates ABSTRACT This paper extends the literature of the term structure
More informationT H E B O T T O M L I N E
R O I C A S E S T U D Y P R O G R A M : E N T E R P R I S E A P P L I C A T I O N S D O C U M E N T Q 2 0 0 O C T O B E R 2 0 1 6 OUTSYSTEMS RICOH (SINGAPORE) PTE LTD A N A L Y S T Seth Lippincott T H
More informationStrategy and Settings for Tradonator nextgen!
Strategy and Settings for Tradonator nextgen! Introduction Tradonator nextgen! is the successor of the Tradonator Cash Pro Expert Advisor, an automated trading system. On any timeframe two trading pools
More informationLecture 6: Chapter 6
Lecture 6: Chapter 6 C C Moxley UAB Mathematics 3 October 16 6.1 Continuous Probability Distributions Last week, we discussed the binomial probability distribution, which was discrete. 6.1 Continuous Probability
More informationHigh Dimensional Bayesian Optimisation and Bandits via Additive Models
1/20 High Dimensional Bayesian Optimisation and Bandits via Additive Models Kirthevasan Kandasamy, Jeff Schneider, Barnabás Póczos ICML 15 July 8 2015 2/20 Bandits & Optimisation Maximum Likelihood inference
More informationMonitoring - revisited
Monitoring - revisited Anders Ringgaard Kristensen Slide 1 Outline Filtering techniques applied to monitoring of daily gain in slaughter pigs: Introduction Basic monitoring Shewart control charts DLM and
More informationLucas s Investment Tax Credit Example
Lucas s Investment Tax Credit Example The key idea: It is 1975 and you have just been hired by the Council of Economic Adviser s to estimate the effects of an investment tax credit. This policy is being
More informationMoney and Banking. Lecture V: Monetary Policy Transmission Mechanisms. Guoxiong ZHANG, Ph.D. November 7th, Shanghai Jiao Tong University, Antai
Money and Banking Lecture V: Monetary Policy Transmission Mechanisms Guoxiong ZHANG, Ph.D. Shanghai Jiao Tong University, Antai November 7th, 2016 Monetary Policy and Its Effects: a Huge Black Box Source:
More informationIt can be achieved... Built by Predictive Modelers for Predictive Modelers TM
Built by Predictive Modelers for Predictive Modelers TM Attaining growth in a concentrated market Finding and capitalizing on opportunity Creating competitive advantage It can be achieved... FIGHTING FOR
More informationRayleigh Curves A Tutorial
Rayleigh Curves A Tutorial Hear F. Chelson Richard L. Coleman Jessica R. Summerville Steven L. Van Drew SCEA 2004 Manhattan Beach, CA June 2004 Outline Background Description Application The N-R Curve
More informationMLC at Boise State Logarithms Activity 6 Week #8
Logarithms Activity 6 Week #8 In this week s activity, you will continue to look at the relationship between logarithmic functions, exponential functions and rates of return. Today you will use investing
More informationExpected Loss Models: Methodological Approach to IFRS9 Impairment & Validation Framework
Expected Loss Models: Methodological Approach to IFRS9 Impairment & Validation Framework Jad Abou Akl 30 November 2016 2016 Experian Limited. All rights reserved. Experian and the marks used herein are
More informationBinomial Trees. Liuren Wu. Zicklin School of Business, Baruch College. Options Markets
Binomial Trees Liuren Wu Zicklin School of Business, Baruch College Options Markets Binomial tree represents a simple and yet universal method to price options. I am still searching for a numerically efficient,
More informationTHE investment in stock market is a common way of
PROJECT REPORT, MACHINE LEARNING (COMP-652 AND ECSE-608) MCGILL UNIVERSITY, FALL 2018 1 Comparison of Different Algorithmic Trading Strategies on Tesla Stock Price Tawfiq Jawhar, McGill University, Montreal,
More informationMiFID Using Regulatory Change to Create a Competitive Advantage
MiFID Using Regulatory Change to Create a Competitive Advantage Philip Filleul MiFID Program Manager, Sun Microsystems Martin Gibbon Head of Risk, SAS UK 22 nd May 2007 Agenda What is MiFID? What might
More informationDistance-Based High-Frequency Trading
Distance-Based High-Frequency Trading Travis Felker Quantica Trading Kitchener, Canada travis@quanticatrading.com Vadim Mazalov Stephen M. Watt University of Western Ontario London, Canada Stephen.Watt@uwo.ca
More informationPrinciples of Financial Computing
Principles of Financial Computing Prof. Yuh-Dauh Lyuu Dept. Computer Science & Information Engineering and Department of Finance National Taiwan University c 2008 Prof. Yuh-Dauh Lyuu, National Taiwan University
More informationLecture 4 - k-layer Neural Networks
Lecture 4 - k-layer Neural Networks DD2424 May 9, 207 A new class of scoring functions Linear scoring function s = W x + b 2-layer Neural Network s = W x + b h = max(0, s ) s = W 2 h + b 2 xd xd. s3. s,m
More informationCS221 Project Final Report Deep Reinforcement Learning in Portfolio Management
CS221 Project Final Report Deep Reinforcement Learning in Portfolio Management Ruohan Zhan Tianchang He Yunpo Li rhzhan@stanford.edu th7@stanford.edu yunpoli@stanford.edu Abstract Portfolio management
More informationMachine Learning Applications in Insurance
General Public Release Machine Learning Applications in Insurance Nitin Nayak, Ph.D. Digital & Smart Analytics Swiss Re General Public Release Machine learning is.. Giving computers the ability to learn
More informationIntroducing nominal rigidities.
Introducing nominal rigidities. Olivier Blanchard May 22 14.452. Spring 22. Topic 7. 14.452. Spring, 22 2 In the model we just saw, the price level (the price of goods in terms of money) behaved like an
More informationarxiv: v1 [cs.lg] 5 Sep 2018
Deep Reinforcement Learning in High Frequency Trading arxiv:1809.01506v1 [cs.lg] 5 Sep 2018 ABSTRACT Prakhar Ganesh Senior, Dept. of CSE IIT Delhi cs1150245@cse.iitd.ac.in The ability to give precise and
More informationCharacterization of the Optimum
ECO 317 Economics of Uncertainty Fall Term 2009 Notes for lectures 5. Portfolio Allocation with One Riskless, One Risky Asset Characterization of the Optimum Consider a risk-averse, expected-utility-maximizing
More information