Visual semantics: image elements. Symbols Objects People Poses

Size: px
Start display at page:

Download "Visual semantics: image elements. Symbols Objects People Poses"

Transcription

1 Visible Partisanship Polmeth XXXIII, Rice University, July 22, 2016 Convolutional Neural Networks for the Analysis of Political Images L. Jason Anastasopoulos (University of Georgia, Public Admin + Policy, Political Science, Georgia Informatics Institute) Dhruvil Badani (UC Berkeley, EECS) Crystal Lee (UC Berkeley, EECS) Shiry Ginosar (UC Berkeley, EECS)

2 Outline Background Image experiment - the people you pose with how race and gender of people politicians pose with affect perceptions. Race classifier for images using convolutional neural networks. Analysis of race in US House of Representative Facebook profile photos.

3 Visual semantics: image elements Symbols Objects People Poses

4 Images convey political meaning: symbols

5 Images convey political meaning: objects Source - usa4palin.com: Still from Sarah Palin s Amazing America

6 Images convey political meaning: people Source - haaretz.com: Netanyahu (left), Obama (middle), Abbas (right)

7 Images convey political meaning: poses Source - google.com: Image search for John Boehner

8 Political functions of images For politicians Signaling Partisanship/ideology. Policy positions. Homestyle (Fenno 1978) Qualification competence. Identification I am one of you. Empathy I care about your needs.

9 Political functions of images For politicians Signaling Partisanship/ideology. Policy positions. Homestyle (Fenno 1978) Qualification competence. Identification I am one of you. Empathy I care about your needs.

10 Political functions of images For news media Issue framing. Persuasion.

11 Hardware and software limitations Hardware Even small images are big data. One 200 x 200 image = 3 200x200 matrices or 1 vector of length 120,000.

12 Hardware and software limitations Software High dimensional statistical theory developed more recently. n + Asymptotics deals with properties of estimators as parameters, p. arge (possibly In modern machine learning applications, (n, p) + with a fixed number of

13 Image analysis renaissance in social science Hardware: Powerful CPUs and now GPUs in desktop computers (thanks gamers!)

14 Image analysis renaissance in social science Software Statistical theory for computing in high dimensions. Advances in numerical computing. Deep-learning frameworks: Torch, Tensorflow, Theano, Caffe.

15 Signaling and image features Symbols Objects People Poses

16 Signaling and image features Symbols Objects People Poses

17 Questions How do the group characteristics (gender, race, age, etc.) of people that Members of Congress pose with affect how they are perceived? Social media homestyle Is there evidence that Members of Congress use social media images to signal identification and empathy with constituents using group characteristics?

18 Questions How do the group characteristics (gender, race, age, etc.) of people that Members of Congress pose with affect how they are perceived? Social media homestyle Is there evidence that Members of Congress use social media images to signal identification and empathy with constituents using group characteristics?

19 The people you pose with experiment: Lou Barletta Lou Barletta (R-PA, 11) chosen for initial experiment because of relative obscurity and similar pictures with different groups of people. MTurk respondents randomly assigned one of 7 images with Barletta Alone Barletta by himself. Woman Barletta with a woman. Man Barletta with a white man. Black Barletta with African-American men. Asked a series of questions based only on the image.

20 Image treatments Alone Man Woman Af. American

21 What is your best guess of the political party that this politician belongs to? Beliefs about Barletta s party ID vary significantly by image shown. Alone: 39% guessed Democrat 61% guessed Republican Black: 58% guessed Democrat 42% guessed Republican Man: 42% guessed Democrat 58% guessed Republican Woman: 43% guessed Democrat 57% guessed Republican

22 What is your best guess of this politician s ideological orientation? Average by treatment groups Alone: Moderate. Black: Liberal. Man: Moderate. Woman: Moderate.

23 Does this politician seem honest and trustworthy? Perceived to be more trustworthy when pictured next to a woman.

24 Does the politician seem like a strong and decisive leader? Perceived to be a stronger leader when pictured next to a woman.

25 Does the politician seem knowledgeable about the issues? Perceived to be less knowledgeable when pictured next to an older white man.

26 Does the politician seem like someone who shares my values? (non-white respondents) Perceived by non-white respondents to share their values when pictured next to African-American men.

27 Barletta experiment conclusions Opinion of Barletta affected by group identity of individuals included in images. Race affected beliefs about partisanship/ideology and implied shared values. Gender affected beliefs in trustworthiness, honesty and decisiveness. Survey experiment expanding goal is to test which aspects of photos most strongly tied to perceptions of candidate ideology and party.

28 Questions How do the group characteristics (gender, race, age, etc.) of people that Members of Congress pose with affect how they are perceived? Social media homestyle Is there evidence that Members of Congress use social media images to signal identification and empathy with constituents using group characteristics?

29 Questions How do the group characteristics (gender, race, age, etc.) of people that Members of Congress pose with affect how they are perceived? Social media homestyle Is there evidence that Members of Congress use social media images to signal identification and empathy with constituents using group characteristics?

30 Data 300,000+ Facebook images with text posts for accounts of: 300 US House members. 56 US Senate members.

31 Goals and Methods Identify race of individuals pictured in Facebook profiles of House Members. Viola-Jones Algorithm Train a convolutional neural network race classifier. Explore how distribution of racial groups in photos compare to congressional district demographics, partisanship and ideology. Compare Facebook profile demographics with district demographics, party id and DW-Nominate scores.

32 Results Democrats and Republicans in the US House of Representatives have very different social media styles. Evidence that Democrats use Facebook images to elicit racial identification and empathy among constituents.

33 How you see an image Image as data. Eg 620x412 pixel image. You see: {Donald Trump, blue tie, black suit, blue background, anger}

34 How a computer sees an image x412 pixel image. 3 Channels: Red, Green, Blue 3 640x412 matrices of pixel intensity values. -or- 3x640x412 = 791,040 x 1 vector

35 Human image classification is robust

36 Machine image classification is error prone... Image Credit: Andrej Karpathy

37 Theoretical means of image feature extraction limited mostly to faces... Viola-Jones Object Detection Framework

38 Data driven approach/supervised machine learning approach train models utilizing pixel intensity data... Collect labeled images. Train a machine learning classifier. Test classifier accuracy. CIFAR-10 library of 32x32 labels images benchmark performance.

39 One layer neural network Inputs multiplied by weights and added create hidden layer. Hidden layer passed through activation function multiplied by another set of weights to generate class probabilities/scores. X 1 X 2 X 3 Simplest model discussed by psychologist Rosenblatt (1958)

40 Neural network activation functions Most common activation functions are sigmoid and tangent. Optimizing predictions requires Choice of activation functions and; Choice of weights.

41 Backpropagation Rumelhart, Hinton and Williams (1986) Selection of weights involves: Forward pass - Calculation of loss function. Backward pass Use of chain rule and stochastic gradient descent to iteratively calculate new weights.

42 Convolutional neural networks for image feature classification Multi-layer neural network involving series of activation functions on chunks of pixel data.

43 Convolutional neural networks for image feature classification Equivalent of passing pixel data through a number of filters. Discover which filter is activated by which labeled image category. Output is highest probability category given filter responses Image credit: Andrej Karpathy

44 Convolutional neural network: building a race classifier Labeled image data 60,000 high school yearbook images, ,000 images sampled from Congressional Facebook dataset we collected. Categories: White, African-American, East Asian, Hispanic. 16-layer CNN model for large-scale image recognition from CNN Model Zoo by Simonyan and Zisserman (2015): and

45 Convolutional neural network: building a race classifier Step 1: Identify faces using Viola- Jones algorithm. Image on the right is a Facebook photo from Representative Tammy Duckworth s (D-IL) profile.

46 Convolutional neural network: building a race classifier Step 2: Label race of faces.

47 Convolutional neural network: building a race classifier Step 3: Train CNN on labeled data.

48 Convolutional neural network: building a race classifier Step 4: Test classifier accuracy Avg. cross-validated accuracy rates of 90% for whites, 85% for African- American, 75% for Asian, 65% for HIspanic.

49 Convolutional neural network: building a race classifier Step 5: Estimate race of individuals in Congressional Facebook image set using trained model.

50 Race and partisanship in House Facebook image posts (white House members) White Democrats post Facebook photos of African-Americans at 4x the rate of white Republicans Hispanics at 1.2x the rate of white Republicans. Asians at 2x the rate of white Republicans.

51 Race and partisanship in House Facebook image posts (white House members) Even conditional on relevant district demographics, state and region fixed effects, evidence of conscious efforts by partisans to include/exclude racial groups in Facebook image posts. Democrats (white): +6% more African-Americans in posts. Republicans (white): +6% more whites in posts.

52 Identification and empathy: district demographics and Facebook image posts Do MCs strategically post photos of racial groups to engender identification and empathy from constituents? Overall strong evidence that they do. Strong relationship between % of racial group in district and % of racial group posted in Facebook profiles.

53 Identification and empathy: district demographics and Facebook image posts by party Strategic use of race in image posts much more evident among Democrats than Republicans

54 Identification and empathy: district demographics and Facebook image posts by party Y = % white in Facebook profile photos White Democrats more race conscious when posting FB photos. After conditioning on state and region fixed effects and district demographics, Democrats Facebook photos more likely to reflect racial/ethnic mix of district.

55 Identification and empathy: district demographics and Facebook image posts by party Representation = % White in Facebook profile photos % White in Congressional District Whites over-represented in Facebook photos of white Democrats and Republicans

56 Identification and empathy: district demographics and Facebook image posts by party Representation = % Black in Facebook profile photos % Black in Congressional District African-Americans under-represented in Facebook photos of Republican MCs by an average of about 3.8%

57 Identification and empathy: district demographics and Facebook image posts by party Representation = % Hispanic in Facebook profile photos % Hispanic in Congressional District Hispanics under-represented In Facebook photos of both parties, more so among Democrats

58 Identification and empathy: district demographics and Facebook image posts by party Representation = % Asian in Facebook profile photos % Asian in Congressional District Asians under-represented in Facebook photos of white Democrats.

59 Discussion Modern computational methods allow for the large scale analysis of images. Here we build a race classifier for images using convolutional neural networks.

60 Discussion Characteristics of people that politicians pose with shape perceptions. Democrats and Republicans in the US House of Representatives have very different social media styles. Evidence that Democrats use Facebook images to elicit racial identification and empathy among constituents.

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil CSE 5194.01 - Introduction to High-Perfomance Deep Learning ImageNet & VGG Jihyung Kil ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,

More information

Automatic Classification of Perceived Gender from Facial Images

Automatic Classification of Perceived Gender from Facial Images Automatic Classification of Perceived Gender from Facial Images Joseph Lemley, Sami Abdul-Wahid, Dipayan Banik Advisor: Dr. Razvan Andonie SOURCE 2016 Outline 1 Introduction 2 Faces - Background 3 Faces

More information

Convolutional and LSTM Neural Networks

Convolutional and LSTM Neural Networks Convolutional and LSTM Neural Networks Vanessa Jurtz January 11, 2017 Contents Neural networks and GPUs Lasagne Peptide binding to MHC class II molecules Convolutional Neural Networks (CNN) Recurrent and

More information

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations

More information

Convolutional and LSTM Neural Networks

Convolutional and LSTM Neural Networks Convolutional and LSTM Neural Networks Vanessa Jurtz January 12, 2016 Contents Neural networks and GPUs Lasagne Peptide binding to MHC class II molecules Convolutional Neural Networks (CNN) Recurrent and

More information

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns 1. Introduction Vasily Morzhakov, Alexey Redozubov morzhakovva@gmail.com, galdrd@gmail.com Abstract Cortical

More information

A convolutional neural network to classify American Sign Language fingerspelling from depth and colour images

A convolutional neural network to classify American Sign Language fingerspelling from depth and colour images A convolutional neural network to classify American Sign Language fingerspelling from depth and colour images Ameen, SA and Vadera, S http://dx.doi.org/10.1111/exsy.12197 Title Authors Type URL A convolutional

More information

Flexible, High Performance Convolutional Neural Networks for Image Classification

Flexible, High Performance Convolutional Neural Networks for Image Classification Flexible, High Performance Convolutional Neural Networks for Image Classification Dan C. Cireşan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber IDSIA, USI and SUPSI Manno-Lugano,

More information

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence To understand the network paradigm also requires examining the history

More information

A HMM-based Pre-training Approach for Sequential Data

A HMM-based Pre-training Approach for Sequential Data A HMM-based Pre-training Approach for Sequential Data Luca Pasa 1, Alberto Testolin 2, Alessandro Sperduti 1 1- Department of Mathematics 2- Department of Developmental Psychology and Socialisation University

More information

arxiv: v1 [stat.ml] 23 Jan 2017

arxiv: v1 [stat.ml] 23 Jan 2017 Learning what to look in chest X-rays with a recurrent visual attention model arxiv:1701.06452v1 [stat.ml] 23 Jan 2017 Petros-Pavlos Ypsilantis Department of Biomedical Engineering King s College London

More information

arxiv: v2 [cs.cv] 19 Dec 2017

arxiv: v2 [cs.cv] 19 Dec 2017 An Ensemble of Deep Convolutional Neural Networks for Alzheimer s Disease Detection and Classification arxiv:1712.01675v2 [cs.cv] 19 Dec 2017 Jyoti Islam Department of Computer Science Georgia State University

More information

The Impact of Visual Saliency Prediction in Image Classification

The Impact of Visual Saliency Prediction in Image Classification Dublin City University Insight Centre for Data Analytics Universitat Politecnica de Catalunya Escola Tècnica Superior d Enginyeria de Telecomunicacions de Barcelona Eric Arazo Sánchez The Impact of Visual

More information

Understanding Convolutional Neural

Understanding Convolutional Neural Understanding Convolutional Neural Networks Understanding Convolutional Neural Networks David Stutz July 24th, 2014 David Stutz July 24th, 2014 0/53 1/53 Table of Contents - Table of Contents 1 Motivation

More information

Omnibus Poll April 11-12, 2013

Omnibus Poll April 11-12, 2013 1. Feminist or anti-feminist Do you consider yourself a feminist, an anti-feminist, or neither? Gender Age Party ID Voter Registration Total Male Female 18-29 30-44 45-64 65+ Democrat Independent Republican

More information

Computational Cognitive Neuroscience

Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience *Computer vision, *Pattern recognition, *Classification, *Picking the relevant information

More information

Image Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning

Image Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning Image Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning Charles Killam, LP.D. Certified Instructor, NVIDIA Deep Learning Institute NVIDIA Corporation

More information

Appendix D: Statistical Modeling

Appendix D: Statistical Modeling Appendix D: Statistical Modeling Cluster analysis Cluster analysis is a method of grouping people based on specific sets of characteristics. Often used in marketing and communication, its goal is to identify

More information

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Stefan Glüge, Ronald Böck and Andreas Wendemuth Faculty of Electrical Engineering and Information Technology Cognitive Systems Group,

More information

Object Detectors Emerge in Deep Scene CNNs

Object Detectors Emerge in Deep Scene CNNs Object Detectors Emerge in Deep Scene CNNs Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Presented By: Collin McCarthy Goal: Understand how objects are represented in CNNs Are

More information

CPSC81 Final Paper: Facial Expression Recognition Using CNNs

CPSC81 Final Paper: Facial Expression Recognition Using CNNs CPSC81 Final Paper: Facial Expression Recognition Using CNNs Luis Ceballos Swarthmore College, 500 College Ave., Swarthmore, PA 19081 USA Sarah Wallace Swarthmore College, 500 College Ave., Swarthmore,

More information

Chapter 1. Introduction

Chapter 1. Introduction Chapter 1 Introduction Artificial neural networks are mathematical inventions inspired by observations made in the study of biological systems, though loosely based on the actual biology. An artificial

More information

Shu Kong. Department of Computer Science, UC Irvine

Shu Kong. Department of Computer Science, UC Irvine Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge 4. Fine-grained classification with holistic representation

More information

Running head: AFFECTIVE FORECASTING AND OBJECTIFICATION 1

Running head: AFFECTIVE FORECASTING AND OBJECTIFICATION 1 Running head: AFFECTIVE FORECASTING AND OBJECTIFICATION 1 The Effect of Demographics, Body Shame, Ambivalent Sexism, and Enjoyment of Sexualization on Anticipated Emotion in Response to Sexual Objectification

More information

CAS Seminar - Spiking Neurons Network (SNN) Jakob Kemi ( )

CAS Seminar - Spiking Neurons Network (SNN) Jakob Kemi ( ) CAS Seminar - Spiking Neurons Network (SNN) Jakob Kemi (820622-0033) kemiolof@student.chalmers.se November 20, 2006 Introduction Biological background To be written, lots of good sources. Background First

More information

Learning Convolutional Neural Networks for Graphs

Learning Convolutional Neural Networks for Graphs GA-65449 Learning Convolutional Neural Networks for Graphs Mathias Niepert Mohamed Ahmed Konstantin Kutzkov NEC Laboratories Europe Representation Learning for Graphs Telecom Safety Transportation Industry

More information

Immuno-Oncology Therapies and Precision Medicine: Personal Tumor-Specific Neoantigen Prediction by Machine Learning

Immuno-Oncology Therapies and Precision Medicine: Personal Tumor-Specific Neoantigen Prediction by Machine Learning Immuno-Oncology Therapies and Precision Medicine: Personal Tumor-Specific Neoantigen Prediction by Machine Learning Yi-Hsiang Hsu, MD, SCD Sep 16, 2017 yihsianghsu@hsl.harvard.edu Director & Associate

More information

Immuno-Oncology Therapies and Precision Medicine: Personal Tumor-Specific Neoantigen Prediction by Machine Learning

Immuno-Oncology Therapies and Precision Medicine: Personal Tumor-Specific Neoantigen Prediction by Machine Learning Immuno-Oncology Therapies and Precision Medicine: Personal Tumor-Specific Neoantigen Prediction by Machine Learning Yi-Hsiang Hsu, MD, SCD Sep 16, 2017 yihsianghsu@hsl.harvard.edu HSL GeneticEpi Center,

More information

POC Brain Tumor Segmentation. vlife Use Case

POC Brain Tumor Segmentation. vlife Use Case Brain Tumor Segmentation vlife Use Case 1 Automatic Brain Tumor Segmentation using CNN Background Brain tumor segmentation seeks to separate healthy tissue from tumorous regions such as the advancing tumor,

More information

CS-E Deep Learning Session 4: Convolutional Networks

CS-E Deep Learning Session 4: Convolutional Networks CS-E4050 - Deep Learning Session 4: Convolutional Networks Jyri Kivinen Aalto University 23 September 2015 Credits: Thanks to Tapani Raiko for slides material. CS-E4050 - Deep Learning Session 4: Convolutional

More information

Deep learning and non-negative matrix factorization in recognition of mammograms

Deep learning and non-negative matrix factorization in recognition of mammograms Deep learning and non-negative matrix factorization in recognition of mammograms Bartosz Swiderski Faculty of Applied Informatics and Mathematics Warsaw University of Life Sciences, Warsaw, Poland bartosz_swiderski@sggw.pl

More information

Deep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations

Deep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations Deep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations Andy Nguyen, M.D., M.S. Medical Director, Hematopathology, Hematology and Coagulation Laboratory,

More information

B657: Final Project Report Holistically-Nested Edge Detection

B657: Final Project Report Holistically-Nested Edge Detection B657: Final roject Report Holistically-Nested Edge Detection Mingze Xu & Hanfei Mei May 4, 2016 Abstract Holistically-Nested Edge Detection (HED), which is a novel edge detection method based on fully

More information

North Carolina Survey Results

North Carolina Survey Results North Carolina Survey Results Q1 Q2 Q3 Q4 Q5 Generally speaking, do you think the use of marijuana should be, or not? Marijuana should be...40% Marijuana should be...47%...13% Do you think doctors should

More information

arxiv: v1 [cs.lg] 4 Feb 2019

arxiv: v1 [cs.lg] 4 Feb 2019 Machine Learning for Seizure Type Classification: Setting the benchmark Subhrajit Roy [000 0002 6072 5500], Umar Asif [0000 0001 5209 7084], Jianbin Tang [0000 0001 5440 0796], and Stefan Harrer [0000

More information

Shu Kong. Department of Computer Science, UC Irvine

Shu Kong. Department of Computer Science, UC Irvine Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with

More information

Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network

Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network Akm Ashiquzzaman *, Abdul Kawsar Tushar *, Md. Rashedul Islam *, 1, and Jong-Myon Kim **, 2 * Department of CSE, University

More information

Convolutional Neural Networks (CNN)

Convolutional Neural Networks (CNN) Convolutional Neural Networks (CNN) Algorithm and Some Applications in Computer Vision Luo Hengliang Institute of Automation June 10, 2014 Luo Hengliang (Institute of Automation) Convolutional Neural Networks

More information

Audiovisual to Sign Language Translator

Audiovisual to Sign Language Translator Technical Disclosure Commons Defensive Publications Series July 17, 2018 Audiovisual to Sign Language Translator Manikandan Gopalakrishnan Follow this and additional works at: https://www.tdcommons.org/dpubs_series

More information

Multi-attention Guided Activation Propagation in CNNs

Multi-attention Guided Activation Propagation in CNNs Multi-attention Guided Activation Propagation in CNNs Xiangteng He and Yuxin Peng (B) Institute of Computer Science and Technology, Peking University, Beijing, China pengyuxin@pku.edu.cn Abstract. CNNs

More information

Detecting and Disrupting Criminal Networks. A Data Driven Approach. P.A.C. Duijn

Detecting and Disrupting Criminal Networks. A Data Driven Approach. P.A.C. Duijn Detecting and Disrupting Criminal Networks. A Data Driven Approach. P.A.C. Duijn Summary Detecting and Disrupting Criminal Networks A data-driven approach It is estimated that transnational organized crime

More information

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience. Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing

More information

The Hunger Games. An Examination of How Hunger Affects Judgments of Political Figures

The Hunger Games. An Examination of How Hunger Affects Judgments of Political Figures The Hunger Games An Examination of How Hunger Affects Judgments of Political Figures Government 1372 Prof. Ryan Enos TF: Camille Morvan Section: Th 7pm Past Research People judge others based on thin slices,

More information

Skin cancer reorganization and classification with deep neural network

Skin cancer reorganization and classification with deep neural network Skin cancer reorganization and classification with deep neural network Hao Chang 1 1. Department of Genetics, Yale University School of Medicine 2. Email: changhao86@gmail.com Abstract As one kind of skin

More information

Automatic Context-Aware Image Captioning

Automatic Context-Aware Image Captioning Technical Disclosure Commons Defensive Publications Series May 23, 2017 Automatic Context-Aware Image Captioning Sandro Feuz Sebastian Millius Follow this and additional works at: http://www.tdcommons.org/dpubs_series

More information

[POLS 4150] R, Randomization and Sampling

[POLS 4150] R, Randomization and Sampling Professor Jason Anastasopoulos ljanastas@uga.edu January 12, 2017 Variables and their measurement When we talk about political phenomena and their relationships we are talking about variables. Variables

More information

arxiv: v2 [cs.cv] 8 Mar 2018

arxiv: v2 [cs.cv] 8 Mar 2018 Automated soft tissue lesion detection and segmentation in digital mammography using a u-net deep learning network Timothy de Moor a, Alejandro Rodriguez-Ruiz a, Albert Gubern Mérida a, Ritse Mann a, and

More information

Convolutional Neural Networks for Text Classification

Convolutional Neural Networks for Text Classification Convolutional Neural Networks for Text Classification Sebastian Sierra MindLab Research Group July 1, 2016 ebastian Sierra (MindLab Research Group) NLP Summer Class July 1, 2016 1 / 32 Outline 1 What is

More information

Multilayer Perceptron Neural Network Classification of Malignant Breast. Mass

Multilayer Perceptron Neural Network Classification of Malignant Breast. Mass Multilayer Perceptron Neural Network Classification of Malignant Breast Mass Joshua Henry 12/15/2017 henry7@wisc.edu Introduction Breast cancer is a very widespread problem; as such, it is likely that

More information

A Fuzzy Improved Neural based Soft Computing Approach for Pest Disease Prediction

A Fuzzy Improved Neural based Soft Computing Approach for Pest Disease Prediction International Journal of Information & Computation Technology. ISSN 0974-2239 Volume 4, Number 13 (2014), pp. 1335-1341 International Research Publications House http://www. irphouse.com A Fuzzy Improved

More information

Networks and Hierarchical Processing: Object Recognition in Human and Computer Vision

Networks and Hierarchical Processing: Object Recognition in Human and Computer Vision Networks and Hierarchical Processing: Object Recognition in Human and Computer Vision Guest&Lecture:&Marius&Cătălin&Iordan&& CS&131&8&Computer&Vision:&Foundations&and&Applications& 01&December&2014 1.

More information

HHS Public Access Author manuscript Med Image Comput Comput Assist Interv. Author manuscript; available in PMC 2018 January 04.

HHS Public Access Author manuscript Med Image Comput Comput Assist Interv. Author manuscript; available in PMC 2018 January 04. Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules Xinyang Feng 1, Jie Yang 1, Andrew F. Laine 1, and Elsa D. Angelini 1,2 1 Department of Biomedical Engineering,

More information

BACKPROPOGATION NEURAL NETWORK FOR PREDICTION OF HEART DISEASE

BACKPROPOGATION NEURAL NETWORK FOR PREDICTION OF HEART DISEASE BACKPROPOGATION NEURAL NETWORK FOR PREDICTION OF HEART DISEASE NABEEL AL-MILLI Financial and Business Administration and Computer Science Department Zarqa University College Al-Balqa' Applied University

More information

Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing

Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing ANNUAL REVIEWS Further Click here to view this article's online features: Download figures as PPT slides Navigate linked references Download citations Explore related articles Search keywords Annu. Rev.

More information

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Longhao Yuan and Jianting Cao ( ) Graduate School of Engineering, Saitama Institute of Technology, Fusaiji 1690, Fukaya-shi,

More information

Assessing Undergraduate Campus Climate Trends at UC Berkeley

Assessing Undergraduate Campus Climate Trends at UC Berkeley Assessing Undergraduate Campus Climate Trends at UC Berkeley Andrew Eppig, Ph.D. Equity & Inclusion Sereeta Alexander, Ph.D. Office of Planning & Analysis November 8, 2012 CAIR 2012 - Alexander and Eppig

More information

Why did the network make this prediction?

Why did the network make this prediction? Why did the network make this prediction? Ankur Taly (Google Inc.) Joint work with Mukund Sundararajan and Qiqi Yan Some Deep Learning Successes Source: https://www.cbsinsights.com Deep Neural Networks

More information

Action Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem

Action Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem Action Recognition Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem This section: advanced topics Convolutional neural networks in vision Action recognition Vision and Language 3D

More information

ZIKA VIRUS AND THE ELECTION SEASON

ZIKA VIRUS AND THE ELECTION SEASON ZIKA VIRUS AND THE ELECTION SEASON August 2016 0 INTRODUCTION The current Zika virus outbreak is occurring in a presidential and congressional election year. Given the important role that infectious disease

More information

Using stigmergy to incorporate the time into artificial neural networks

Using stigmergy to incorporate the time into artificial neural networks Using stigmergy to incorporate the time into artificial neural networks Federico A. Galatolo, Mario G.C.A. Cimino, and Gigliola Vaglini Department of Information Engineering, University of Pisa, 56122

More information

arxiv: v2 [cs.cv] 22 Mar 2018

arxiv: v2 [cs.cv] 22 Mar 2018 Deep saliency: What is learnt by a deep network about saliency? Sen He 1 Nicolas Pugeault 1 arxiv:1801.04261v2 [cs.cv] 22 Mar 2018 Abstract Deep convolutional neural networks have achieved impressive performance

More information

The New Food Fights: U.S. Public Divides Over Food Science

The New Food Fights: U.S. Public Divides Over Food Science NUMBERS, FACTS AND TRENDS SHAPING YOUR WORLD ABOUT FOLLOW US Search Internet, Science & Tech M ENU RESEARCH AREAS DECEMBER 1, 2016 The New Food Fights: U.S. Public Divides Over Food Science Differing view

More information

RECOMMENDED CITATION: Pew Research Center, October 2014, Public Divided over Whether Secret Service Lapses Signal Broader Problems

RECOMMENDED CITATION: Pew Research Center, October 2014, Public Divided over Whether Secret Service Lapses Signal Broader Problems NUMBERS, FACTS AND TRENDS SHAPING THE WORLD FOR RELEASE OCTOBER 6, 2014 FOR FURTHER INFORMATION ON THIS REPORT: Carroll Doherty, Director of Political Research Seth Motel, Research Analyst Rachel Weisel,

More information

Question 1 Multiple Choice (8 marks)

Question 1 Multiple Choice (8 marks) Philadelphia University Student Name: Faculty of Engineering Student Number: Dept. of Computer Engineering First Exam, First Semester: 2015/2016 Course Title: Neural Networks and Fuzzy Logic Date: 19/11/2015

More information

Neuromorphic convolutional recurrent neural network for road safety or safety near the road

Neuromorphic convolutional recurrent neural network for road safety or safety near the road Neuromorphic convolutional recurrent neural network for road safety or safety near the road WOO-SUP HAN 1, IL SONG HAN 2 1 ODIGA, London, U.K. 2 Korea Advanced Institute of Science and Technology, Daejeon,

More information

SECTION 1. CHAPTER 1 Environmental and Behavioral Issues. CHAPTER 2 Acoustical Principles. CHAPTER 3 Accessible Design Basics

SECTION 1. CHAPTER 1 Environmental and Behavioral Issues. CHAPTER 2 Acoustical Principles. CHAPTER 3 Accessible Design Basics SECTION 1 DESIGN PRINCIPLES AND PROCESS 3 13 18 24 29 CHAPTER 1 Environmental and Behavioral Issues CHAPTER 2 Acoustical Principles CHAPTER 3 Accessible Design Basics CHAPTER 4 Sustainable Design Basics

More information

arxiv: v1 [cs.cv] 17 Aug 2017

arxiv: v1 [cs.cv] 17 Aug 2017 Deep Learning for Medical Image Analysis Mina Rezaei, Haojin Yang, Christoph Meinel Hasso Plattner Institute, Prof.Dr.Helmert-Strae 2-3, 14482 Potsdam, Germany {mina.rezaei,haojin.yang,christoph.meinel}@hpi.de

More information

University of Cambridge Engineering Part IB Information Engineering Elective

University of Cambridge Engineering Part IB Information Engineering Elective University of Cambridge Engineering Part IB Information Engineering Elective Paper 8: Image Searching and Modelling Using Machine Learning Handout 1: Introduction to Artificial Neural Networks Roberto

More information

Hierarchical Convolutional Features for Visual Tracking

Hierarchical Convolutional Features for Visual Tracking Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Husan Yang SJTU UIUC SJTU UC Merced ICCV 2015 Background Given the initial state (position and scale), estimate

More information

CS 453X: Class 18. Jacob Whitehill

CS 453X: Class 18. Jacob Whitehill CS 453X: Class 18 Jacob Whitehill More on k-means Exercise: Empty clusters (1) Assume that a set of distinct data points { x (i) } are initially assigned so that none of the k clusters is empty. How can

More information

Proposal for the ANES 2016 Pilot Study: Supplementing Skin tone Measurement from the 2012 ANES

Proposal for the ANES 2016 Pilot Study: Supplementing Skin tone Measurement from the 2012 ANES Proposal for the ANES 2016 Pilot Study: Supplementing Skin tone Measurement from the 2012 ANES Keywords: Skin tone; measurement; discrimination; colorism A variety of social science and public health research

More information

Direct memory access using two cues: Finding the intersection of sets in a connectionist model

Direct memory access using two cues: Finding the intersection of sets in a connectionist model Direct memory access using two cues: Finding the intersection of sets in a connectionist model Janet Wiles, Michael S. Humphreys, John D. Bain and Simon Dennis Departments of Psychology and Computer Science

More information

A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition

A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition LászlóTóth and Tamás Grósz MTA-SZTE Research Group on Artificial Intelligence Hungarian Academy of Sciences

More information

1 PEW RESEARCH CENTER

1 PEW RESEARCH CENTER 1 About the Survey The analysis in this report is based on telephone interviews conducted May 15-18, 2014 among a national sample of 1,000 adults, 18 years of age or older living in the continental United

More information

Analyzing Causal Mechanisms in Survey Experiments *

Analyzing Causal Mechanisms in Survey Experiments * Analyzing Causal Mechanisms in Survey Experiments * Avidit Acharya, Matthew Blackwell, and Maya Sen July 5, 2016 Abstract We present an approach to investigating causal mechanisms in experiments that include

More information

Machine Gaydar : Using Facebook Profiles to Predict Sexual Orientation

Machine Gaydar : Using Facebook Profiles to Predict Sexual Orientation Machine Gaydar : Using Facebook Profiles to Predict Sexual Orientation Nikhil Bhattasali 1, Esha Maiti 2 Mentored by Sam Corbett-Davies Stanford University, Stanford, California 94305, USA ABSTRACT The

More information

Pre-analysis plan: Voter evaluations of candidate socioeconomic characteristics

Pre-analysis plan: Voter evaluations of candidate socioeconomic characteristics Pre-analysis plan: Voter evaluations of candidate socioeconomic characteristics Sophie Hill August 31, 2018 1 Introduction In most democracies, elected officials are overwhelming drawn from higher income,

More information

Personal Talent Skills Inventory

Personal Talent Skills Inventory Personal Talent Skills Inventory Sales Version Inside Sales Sample Co. 5-30-2013 Introduction Research suggests that the most effective people are those who understand themselves, both their strengths

More information

2008 Ohio State University. Campus Climate Study. Prepared by. Student Life Research and Assessment

2008 Ohio State University. Campus Climate Study. Prepared by. Student Life Research and Assessment 2008 Ohio State University Campus Climate Study Prepared by Student Life Research and Assessment January 22, 2009 Executive Summary The purpose of this report is to describe the experiences and perceptions

More information

reward based power have ability to give you what you want. coercive have power to punish

reward based power have ability to give you what you want. coercive have power to punish Chapter 7 Finding and Using Negotiation Power Why Power Important to Negotiators? Seeking power in negotiations from 1 of 2 perceptions: 1. Negotiator believes he has less power than other party 2. Negotiator

More information

Deep Learning based FACS Action Unit Occurrence and Intensity Estimation

Deep Learning based FACS Action Unit Occurrence and Intensity Estimation Deep Learning based FACS Action Unit Occurrence and Intensity Estimation Amogh Gudi, H. Emrah Tasli, Tim M. den Uyl, Andreas Maroulis Vicarious Perception Technologies, Amsterdam, The Netherlands Abstract

More information

Contents. Just Classifier? Rules. Rules: example. Classification Rule Generation for Bioinformatics. Rule Extraction from a trained network

Contents. Just Classifier? Rules. Rules: example. Classification Rule Generation for Bioinformatics. Rule Extraction from a trained network Contents Classification Rule Generation for Bioinformatics Hyeoncheol Kim Rule Extraction from Neural Networks Algorithm Ex] Promoter Domain Hybrid Model of Knowledge and Learning Knowledge refinement

More information

Prediction of Average and Perceived Polarity in Online Journalism

Prediction of Average and Perceived Polarity in Online Journalism Prediction of Average and Perceived Polarity in Online Journalism Albert Chu, Kensen Shi, Catherine Wong Abstract We predicted the average and perceived journalistic objectivity in online news articles

More information

Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images

Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images Tae Joon Jun, Dohyeun Kim, and Daeyoung Kim School of Computing, KAIST,

More information

A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals

A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals Luis Guarda Bräuning (1) Nicolas Astorga (1) Enrique López Droguett (1) Marcio Moura (2) Marcelo

More information

BLADDERSCAN PRIME PLUS TM DEEP LEARNING

BLADDERSCAN PRIME PLUS TM DEEP LEARNING BLADDERSCAN PRIME PLUS TM DEEP LEARNING BladderScan Prime Plus from Verathon Takes Accuracy and Ease of Use to a New Level Powered by ImageSense TM deep learning technology, an advanced implementation

More information

Supporting Online Material for

Supporting Online Material for www.sciencemag.org/cgi/content/full/315/5812/619/dc1 Supporting Online Material for Dimensions of Mind Perception Heather M. Gray,* Kurt Gray, Daniel M. Wegner *To whom correspondence should be addressed.

More information

Facial Expression Classification Using Convolutional Neural Network and Support Vector Machine

Facial Expression Classification Using Convolutional Neural Network and Support Vector Machine Facial Expression Classification Using Convolutional Neural Network and Support Vector Machine Valfredo Pilla Jr, André Zanellato, Cristian Bortolini, Humberto R. Gamba and Gustavo Benvenutti Borba Graduate

More information

LOOK, LISTEN, AND DECODE: MULTIMODAL SPEECH RECOGNITION WITH IMAGES. Felix Sun, David Harwath, and James Glass

LOOK, LISTEN, AND DECODE: MULTIMODAL SPEECH RECOGNITION WITH IMAGES. Felix Sun, David Harwath, and James Glass LOOK, LISTEN, AND DECODE: MULTIMODAL SPEECH RECOGNITION WITH IMAGES Felix Sun, David Harwath, and James Glass MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA {felixsun,

More information

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 1

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 1 IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING Joint Classification and Regression via Deep Multi-Task Multi-Channel Learning for Alzheimer s Disease Diagnosis Mingxia Liu, Jun Zhang, Ehsan Adeli, Dinggang

More information

Artificial Neural Networks

Artificial Neural Networks Artificial Neural Networks Torsten Reil torsten.reil@zoo.ox.ac.uk Outline What are Neural Networks? Biological Neural Networks ANN The basics Feed forward net Training Example Voice recognition Applications

More information

Computational modeling of visual attention and saliency in the Smart Playroom

Computational modeling of visual attention and saliency in the Smart Playroom Computational modeling of visual attention and saliency in the Smart Playroom Andrew Jones Department of Computer Science, Brown University Abstract The two canonical modes of human visual attention bottomup

More information

TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING

TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING 134 TWO HANDED SIGN LANGUAGE RECOGNITION SYSTEM USING IMAGE PROCESSING H.F.S.M.Fonseka 1, J.T.Jonathan 2, P.Sabeshan 3 and M.B.Dissanayaka 4 1 Department of Electrical And Electronic Engineering, Faculty

More information

Case study critical analysis: Leadership style in the Deaf community: An exploratory case study. of a university president.

Case study critical analysis: Leadership style in the Deaf community: An exploratory case study. of a university president. Running Head: LEADERSHIP IN DEAF COMMUNITY Case study critical analysis: Leadership style in the Deaf community: An exploratory case study of a university president Elizabeth Harris Georgia Southern University

More information

Sparse Coding in Sparse Winner Networks

Sparse Coding in Sparse Winner Networks Sparse Coding in Sparse Winner Networks Janusz A. Starzyk 1, Yinyin Liu 1, David Vogel 2 1 School of Electrical Engineering & Computer Science Ohio University, Athens, OH 45701 {starzyk, yliu}@bobcat.ent.ohiou.edu

More information

Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation

Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation Takumi Ege, Yoshikazu Ando, Ryosuke Tanno, Wataru Shimoda and Keiji Yanai Department of Informatics, The University of Electro-Communications,

More information

Artificial Intelligence to Enhance Radiology Image Interpretation

Artificial Intelligence to Enhance Radiology Image Interpretation Artificial Intelligence to Enhance Radiology Image Interpretation Curtis P. Langlotz, MD, PhD Professor of Radiology and Biomedical Informatics Associate Chair, Information Systems, Department of Radiology

More information

Towards disentangling underlying explanatory factors Yoshua Bengio. July 13th, 2018 ICML 2018 Workshop on Learning with Limited Labels

Towards disentangling underlying explanatory factors Yoshua Bengio. July 13th, 2018 ICML 2018 Workshop on Learning with Limited Labels Towards disentangling underlying explanatory factors Yoshua Bengio July 13th, 2018 ICML 2018 Workshop on Learning with Limited Labels Generalizing Beyond i.i.d. Data Current ML theory is strongly dependent

More information

Final Report: Automated Semantic Segmentation of Volumetric Cardiovascular Features and Disease Assessment

Final Report: Automated Semantic Segmentation of Volumetric Cardiovascular Features and Disease Assessment Final Report: Automated Semantic Segmentation of Volumetric Cardiovascular Features and Disease Assessment Tony Lindsey 1,3, Xiao Lu 1 and Mojtaba Tefagh 2 1 Department of Biomedical Informatics, Stanford

More information

ENVIRONMENTAL VALUES EXECUTIVE SUMMARY

ENVIRONMENTAL VALUES EXECUTIVE SUMMARY CHARLTON RESEARCH COMPANY 44 Montgomery Street, Suite 1710 San Francisco, California 94104 415/981-2343 Fax 415/981-4850 ENVIRONMENTAL VALUES EXECUTIVE SUMMARY A Public Opinion Study Commissioned by the

More information