Training deep Autoencoders for collaborative filtering Oleksii Kuchaiev & Boris Ginsburg
|
|
- Jessie Shepherd
- 5 years ago
- Views:
Transcription
1 Training deep Autoencoders for collaborative filtering Oleksii Kuchaiev & Boris Ginsburg
2 Motivation Personalized recommendations 2
3 Key points (spoiler alert) 1. Deep autoencoder for collaborative filtering 1. Improves generalization 2. Right activation function (SELU, ELU, LeakyRELU) enables deep architectures 1. No layer-wise pre-training, or skip connections 3. Heavy use of dropout 4. Dense re-feeding for faster and better training 5. Beats other models on time-split Netflix data (RMSE of vs ) 6. (PyTorch-based) Oleksii Kuchaiev and Boris Ginsburg "Training Deep AutoEncoders for Collaborative Filtering, arxiv preprint arxiv: (2017). 3
4 Autoencoders & collaborative filtering Effects of the activation types Overfitting the data Going deeper Dropout Dense re-feeding Conclusions Oleksii Kuchaiev and Boris Ginsburg "Training Deep AutoEncoders for Collaborative Filtering, arxiv preprint arxiv: (2017). 4
5 Collaborative filtering Rating prediction R(i,j) = k iff user i gave item j rating k j Some of the most popular approaches Alternative Least Squares (ALS) 3 X Items r 4 m users R=Rating matrix Users i n items r hidden factors 5
6 Autoencoder Deep learning tool of choice for dimensionality reduction E n c o d e r y x z = e 2 e 2 = f(w e 2 e 1 + b 2 ) e 1 = f(w e 1 x + b 1 ) d 2 = W d 1 d 1 + b 4 d 1 = f(w d 2 z + b 3 ) D e c o d e r z = encoder(x), encoding y = decoder(z), reconstruction of x y = decoder(encoder(x)) Autoencoder can be thought of as generalization of PCA Constrained if decoder weights are transpose of encoder De-noising if noise is a added to x. Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786),
7 AutoEncoders for recommendations User (item) based Masked Mean Squared Error z (very) sparse r dense y Sedhain, Suvash, et al. "Autorec: Autoencoders meet collaborative filtering." Proceedings of the 24th International Conference on World Wide Web. ACM,
8 Dataset Netflix prize training data set Time split to predict future ratings Wu, Chao-Yuan, et al. "Recurrent recommender networks." Proceedings of the Tenth ACM International Conference on Web Search and Data Mining. ACM,
9 Benchmark Netflix prize training data set RMSE = σ r i 0 r i y i 2 σ ri 0 1 PMF: Mnih, Andriy, and Ruslan R. Salakhutdinov. "Probabilistic matrix factorization." Advances in neural information processing systems I-AR, U-AR: Sedhain, Suvash, et al. "Autorec: Autoencoders meet collaborative filtering." Proceedings of the 24th International Conference on World Wide Web. ACM, RRN: Wu, Chao-Yuan, et al. "Recurrent recommender networks." Proceedings of the Tenth ACM International Conference on Web Search and Data Mining. ACM,
10 Autoencoders & collaborative filtering Effects of the activation types Overfitting the data Going deeper Dropout Dense re-feeding Conclusions Oleksii Kuchaiev and Boris Ginsburg "Training Deep AutoEncoders for Collaborative Filtering, arxiv preprint arxiv: (2017). 10
11 RMSE Activation function matters - We found that on this task ELU, SELU and LRELU perform much better than SIGMOID, RELU, RELU6, TANH and SWISH Apparently important: a) non-zero negative part b) Unbounded positive part Training RMSE per mini-batch. All lines correspond to 4-layers autoencoder (2 layer encoder and 2 layer decoder) with hidden unit dimensions of 128. Different line colors correspond to different activation functions. Iteration 11
12 Autoencoders & collaborative filtering Effects of the activation types Overfitting the data Going deeper Dropout Dense re-feeding Conclusions Oleksii Kuchaiev and Boris Ginsburg "Training Deep AutoEncoders for Collaborative Filtering, arxiv preprint arxiv: (2017). 12
13 Overfit your data Wide layers generalize poorly RMSE RMSE d size 128 d size 256 d size 512 d size 1024 y d 2 = W 1 d d 1 + b 4 d e 1 = f(w 1 e x + b 1 ) x Evaluation RMSE > 1.1 on Netflix full d size 128 d size 256 d size 512 d size Epoch 13
14 Autoencoders & collaborative filtering Effects of the activation types Overfitting the data Going deeper Dropout Dense re-feeding Conclusions Oleksii Kuchaiev and Boris Ginsburg "Training Deep AutoEncoders for Collaborative Filtering, arxiv preprint arxiv: (2017). 14
15 Deeper models Generalize better y No layer-wise pre-training necessary! x 15
16 Autoencoders & collaborative filtering Effects of the activation types Overfitting the data Going deeper Dropout Dense re-feeding Conclusions Oleksii Kuchaiev and Boris Ginsburg "Training Deep AutoEncoders for Collaborative Filtering, arxiv preprint arxiv: (2017). 16
17 RMSE y Dropout Helps wider models generalize dropout Evaluation RMSE Drop Prob 0.0 Drop Prob 0.5 Drop Prob 0.65 Drop Prob x Epoch 17
18 Autoencoders & collaborative filtering Effects of the activation types Overfitting the data Going deeper Dropout Dense re-feeding Conclusions Oleksii Kuchaiev and Boris Ginsburg "Training Deep AutoEncoders for Collaborative Filtering, arxiv preprint arxiv: (2017). 18
19 Dense re-feeding Note that x is sparse but f(x) is dense For x, most of the loss is masked Intuition: idealized scenario Imagine perfect f x i 0: f x i = x i If user later rates new item k with rating r, then: f x k = r f(x)= By induction: f f x = f x Thus, f(x) should be a fixed point of f for every valid x 19
20 Dense re-feeding Attempt to enforce fixed point constraint (very) sparse x Dense f(x) Dense f(x) Dense f(f(x)) Update with real data x Update with synthetic data f(x) 20
21 RMSE Dense re-feeding Together with bigger LR improves generalization Baseline Baseline LR Baseline RF Baseline LF RF Epoch 21
22 Results Netflix time split data I-AR, U-AR: Sedhain, Suvash, et al. "Autorec: Autoencoders meet collaborative filtering." Proceedings of the 24th International Conference on World Wide Web. ACM, RRN: Wu, Chao-Yuan, et al. "Recurrent recommender networks." Proceedings of the Tenth ACM International Conference on Web Search and Data Mining. ACM, DeepRec is our 6 layer model 22
23 Conclusions 1. Autoencoders can replace ALS and be competitive with other methods 2. Deeper models generalize better 1. No layer-wise pre-training is necessary 3. Right activation function enables deep architectures 1. Negative parts are important 2. Unbounded positive part 4. Heavy use of dropout is needed for wider models 5. Dense re-feeding further improves generalization 23
24 Oleksii Kuchaiev and Boris Ginsburg "Training Deep Autoencoders for Collaborative Filtering, arxiv preprint arxiv: (2017). Code, docs and tutorial:
JOINT TRAINING OF RATINGS AND REVIEWS WITH RECURRENT RECOMMENDER NETWORKS
JOINT TRAINING OF RATINGS AND REVIEWS WITH RECURRENT RECOMMENDER NETWORKS Chao-Yuan Wu University of Texas at Austin Austin, TX, USA cywu@cs.utexas.edu Amr Ahmed & Alex Beutel Google Mountain View, CA,
More informationCSE 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 informationA 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 informationMulti-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 informationCOMP9444 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 informationConvolutional Neural Networks for Estimating Left Ventricular Volume
Convolutional Neural Networks for Estimating Left Ventricular Volume Ryan Silva Stanford University rdsilva@stanford.edu Maksim Korolev Stanford University mkorolev@stanford.edu Abstract End-systolic and
More informationarxiv: v2 [cs.lg] 1 Jun 2018
Shagun Sodhani 1 * Vardaan Pahuja 1 * arxiv:1805.11016v2 [cs.lg] 1 Jun 2018 Abstract Self-play (Sukhbaatar et al., 2017) is an unsupervised training procedure which enables the reinforcement learning agents
More informationOn Training of Deep Neural Network. Lornechen
On Training of Deep Neural Network Lornechen 2016.04.20 1 Outline Introduction Layer-wise Pre-training & Fine-tuning Activation Function Initialization Method Advanced Layers and Nets 2 Neural Network
More informationAutomatic Prostate Cancer Classification using Deep Learning. Ida Arvidsson Centre for Mathematical Sciences, Lund University, Sweden
Automatic Prostate Cancer Classification using Deep Learning Ida Arvidsson Centre for Mathematical Sciences, Lund University, Sweden Outline Autoencoders, theory Motivation, background and goal for prostate
More informationarxiv: v1 [cs.ai] 28 Nov 2017
: a better way of the parameters of a Deep Neural Network arxiv:1711.10177v1 [cs.ai] 28 Nov 2017 Guglielmo Montone Laboratoire Psychologie de la Perception Université Paris Descartes, Paris montone.guglielmo@gmail.com
More informationarxiv: v2 [cs.lg] 30 Oct 2013
Prediction of breast cancer recurrence using Classification Restricted Boltzmann Machine with Dropping arxiv:1308.6324v2 [cs.lg] 30 Oct 2013 Jakub M. Tomczak Wrocław University of Technology Wrocław, Poland
More informationUNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014
UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 Exam policy: This exam allows two one-page, two-sided cheat sheets (i.e. 4 sides); No other materials. Time: 2 hours. Be sure to write
More informationReduction 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 informationDeep Learning-based Detection of Periodic Abnormal Waves in ECG Data
, March 1-16, 2018, Hong Kong Deep Learning-based Detection of Periodic Abnormal Waves in ECG Data Kaiji Sugimoto, Saerom Lee, and Yoshifumi Okada Abstract Automatic detection of abnormal electrocardiogram
More informationEfficient Deep Model Selection
Efficient Deep Model Selection Jose Alvarez Researcher Data61, CSIRO, Australia GTC, May 9 th 2017 www.josemalvarez.net conv1 conv2 conv3 conv4 conv5 conv6 conv7 conv8 softmax prediction???????? Num Classes
More informationRetinopathy Net. Alberto Benavides Robert Dadashi Neel Vadoothker
Retinopathy Net Alberto Benavides Robert Dadashi Neel Vadoothker Motivation We were interested in applying deep learning techniques to the field of medical imaging Field holds a lot of promise and can
More informationA CONVOLUTION NEURAL NETWORK ALGORITHM FOR BRAIN TUMOR IMAGE SEGMENTATION
A CONVOLUTION NEURAL NETWORK ALGORITHM FOR BRAIN TUMOR IMAGE SEGMENTATION 1 Priya K, 2 Dr.O. Saraniya 1 PG Scholar, 2 Assistant Professor Department Of ECE Government College of Technology, Coimbatore,
More informationDEEP NEURAL NETWORKS VERSUS SUPPORT VECTOR MACHINES FOR ECG ARRHYTHMIA CLASSIFICATION. Sean shensheng Xu, Man-Wai Mak and Chi-Chung Cheung
DEEP NEURAL NETWORKS VERSUS SUPPORT VECTOR MACHINES FOR ECG ARRHYTHMIA CLASSIFICATION Sean shensheng Xu, Man-Wai Mak and Chi-Chung Cheung Department of Electronic and Information Engineering The Hong Kong
More informationElad Hoffer*, Itay Hubara*, Daniel Soudry
Train longer, generalize better: closing the generalization gap in large batch training of neural networks Elad Hoffer*, Itay Hubara*, Daniel Soudry *Equal contribution Better models - parallelization
More informationConvolutional 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 informationarxiv: 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 informationSmaller, faster, deeper: University of Edinburgh MT submittion to WMT 2017
Smaller, faster, deeper: University of Edinburgh MT submittion to WMT 2017 Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip
More informationDeep CNNs for Diabetic Retinopathy Detection
Deep CNNs for Diabetic Retinopathy Detection Alex Tamkin Stanford University atamkin@stanford.edu Iain Usiri Stanford University iusiri@stanford.edu Chala Fufa Stanford University cfufa@stanford.edu 1
More informationSign Language Recognition using Convolutional Neural Networks
Sign Language Recognition using Convolutional Neural Networks Lionel Pigou, Sander Dieleman, Pieter-Jan Kindermans, Benjamin Schrauwen Ghent University, ELIS, Belgium Abstract. There is an undeniable communication
More informationMachine learning for neural decoding
Machine learning for neural decoding Joshua I. Glaser 1,2,6,7*, Raeed H. Chowdhury 3,4, Matthew G. Perich 3,4, Lee E. Miller 2-4, and Konrad P. Kording 2-7 1. Interdepartmental Neuroscience Program, Northwestern
More informationarxiv: v3 [stat.ml] 28 Oct 2017
Interpretable Deep Learning applied to Plant Stress Phenotyping arxiv:1710.08619v3 [stat.ml] 28 Oct 2017 Sambuddha Ghosal sghosal@iastate.edu Asheesh K. Singh singhak@iastate.edu Arti Singh arti@iastate.edu
More informationPatient Subtyping via Time-Aware LSTM Networks
Patient Subtyping via Time-Aware LSTM Networks Inci M. Baytas Computer Science and Engineering Michigan State University 428 S Shaw Ln. East Lansing, MI 48824 baytasin@msu.edu Fei Wang Healthcare Policy
More informationECG Signal Classification with Deep Learning Techniques
ECG Signal Classification with Deep Learning Techniques Chien You Huang, B04901147 Ruey Lin Jahn, B02901043 Sung-wei Huang, B04901093 Department of Electrical Engineering, National Taiwan University, Taipei,
More informationExploiting Implicit Item Relationships for Recommender Systems
Exploiting Implicit Item Relationships for Recommender Systems Zhu Sun, Guibing Guo, and Jie Zhang School of Computer Engineering, Nanyang Technological University, Singapore School of Information Systems,
More informationSynthesis of Gadolinium-enhanced MRI for Multiple Sclerosis patients using Generative Adversarial Network
Medical Application of GAN Synthesis of Gadolinium-enhanced MRI for Multiple Sclerosis patients using Generative Adversarial Network Sumana Basu School of Computer Science McGill University 260727568 sumana.basu@mail.mcgill.ca
More informationError Detection based on neural signals
Error Detection based on neural signals Nir Even- Chen and Igor Berman, Electrical Engineering, Stanford Introduction Brain computer interface (BCI) is a direct communication pathway between the brain
More informationDeep Learning of Brain Lesion Patterns for Predicting Future Disease Activity in Patients with Early Symptoms of Multiple Sclerosis
Deep Learning of Brain Lesion Patterns for Predicting Future Disease Activity in Patients with Early Symptoms of Multiple Sclerosis Youngjin Yoo 1,2,5(B),LisaW.Tang 2,3,5, Tom Brosch 1,2,5,DavidK.B.Li
More informationBottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering SUPPLEMENTARY MATERIALS 1. Implementation Details 1.1. Bottom-Up Attention Model Our bottom-up attention Faster R-CNN
More informationAn 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 informationY-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images
Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images Sachin Mehta 1, Ezgi Mercan 1, Jamen Bartlett 2, Donald Weaver 2, Joann G. Elmore 1, and Linda Shapiro 1 1 University
More informationLearning in neural networks
http://ccnl.psy.unipd.it Learning in neural networks Marco Zorzi University of Padova M. Zorzi - European Diploma in Cognitive and Brain Sciences, Cognitive modeling", HWK 19-24/3/2006 1 Connectionist
More informationSummary and discussion of: Why Does Unsupervised Pre-training Help Deep Learning?
Summary and discussion of: Why Does Unsupervised Pre-training Help Deep Learning? Statistics Journal Club, 36-825 Avinava Dubey and Mrinmaya Sachan and Jerzy Wieczorek December 3, 2014 1 Summary 1.1 Deep
More informationCan Generic Neural Networks Estimate Numerosity Like Humans?
Can Generic Neural Networks Estimate Numerosity Like Humans? Sharon Y. Chen (syc2138@columbia.edu) 1, Zhenglong Zhou (zzhou34@jhu.edu) 2, Mengting Fang (mtfang@mail.bnu.edu.cn) 3, and James L. McClelland
More informationA 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 informationarxiv: v1 [cs.ne] 5 Dec 2018
Neuromodulated Learning in Deep Neural Networks Dennis G Wilson University of Toulouse, IRIT - CNRS - UMR5505, Toulouse, France dennis.wilson@irit.fr arxiv:1812.03365v1 [cs.ne] 5 Dec 2018 Sylvain Cussat-Blanc
More informationSleep Staging with Deep Learning: A convolutional model
Sleep Staging with Deep Learning: A convolutional model Isaac Ferna ndez-varela1, Dimitrios Athanasakis2, Samuel Parsons3 Elena Herna ndez-pereira1, and Vicente Moret-Bonillo1 1- Universidade da Corun
More informationPersonalized Disease Prediction Using a CNN-Based Similarity Learning Method
2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) Personalized Disease Prediction Using a CNN-Based Similarity Learning Method Qiuling Suo, Fenglong Ma, Ye Yuan, Mengdi Huai,
More informationarxiv: 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 informationUnderstanding 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 informationLearning 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 informationAutomatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks
Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks Joseph Antony 1, Kevin McGuinness 1, Kieran Moran 1,2 and Noel E O Connor 1 Insight
More informationSimultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation
Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation Charles Hamesse 1, Paul Ackermann 2, Hedvig Kjellström 1, and Cheng Zhang 3 1 KTH Royal Institute of
More informationarxiv: v1 [cs.cv] 26 Oct 2017
Lip2AudSpec: Speech reconstruction from silent lip movements video arxiv:1710.09798v1 [cs.cv] 26 Oct 17 Hassan Akbari Department of Electrical Engineering Columbia University, New York, NY, USA ha2436@columbia.edu
More informationMagnetic Resonance Contrast Prediction Using Deep Learning
Magnetic Resonance Contrast Prediction Using Deep Learning Cagan Alkan Department of Electrical Engineering Stanford University calkan@stanford.edu Andrew Weitz Department of Bioengineering Stanford University
More informationReview: Logistic regression, Gaussian naïve Bayes, linear regression, and their connections
Review: Logistic regression, Gaussian naïve Bayes, linear regression, and their connections New: Bias-variance decomposition, biasvariance tradeoff, overfitting, regularization, and feature selection Yi
More informationWHEN AND WHERE DO FEED-FORWARD NEURAL NET-
WHEN AND WHERE DO FEED-FORWARD NEURAL NET- WORKS LEARN LOCALIST REPRESENTATIONS? Anonymous authors Paper under double-blind review ABSTRACT According to parallel distributed processing (PDP) theory in
More informationConvolutional 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 informationPersonalized Colorectal Cancer Survivability Prediction with Machine Learning Methods*
Personalized Colorectal Cancer Survivability Prediction with Machine Learning Methods* 1 st Samuel Li Princeton University Princeton, NJ seli@princeton.edu 2 nd Talayeh Razzaghi New Mexico State University
More informationarxiv: v1 [cs.lg] 22 Mar 2017
Independently Controllable Features Emmanuel Bengio ebengi@cs.mcgill.ca Valentin Thomas École Polytechnique Fédérale de Lausanne valentin.thomas@epfl.ch arxiv:1703.07718v1 [cs.lg] 22 Mar 2017 Joelle Pineau
More informationDeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation
DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation Biyi Fang Michigan State University ACM SenSys 17 Nov 6 th, 2017 Biyi Fang (MSU) Jillian Co (MSU) Mi Zhang
More informationCS 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 informationHHS 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 informationAutomated 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 informationDeep Multimodal Fusion of Health Records and Notes for Multitask Clinical Event Prediction
Deep Multimodal Fusion of Health Records and Notes for Multitask Clinical Event Prediction Chirag Nagpal Auton Lab Carnegie Mellon Pittsburgh, PA 15213 chiragn@cs.cmu.edu Abstract The advent of Electronic
More informationFigure 1: MRI Scanning [2]
A Deep Belief Network Based Brain Tumor Detection in MRI Images Thahseen P 1, Anish Kumar B 2 1 MEA Engineering College, State Highway 39, Nellikunnu-Vengoor, Perinthalmanna, Malappuram, Kerala 2 Assistant
More informationRating prediction on Amazon Fine Foods Reviews
Rating prediction on Amazon Fine Foods Reviews Chen Zheng University of California,San Diego chz022@ucsd.edu Ye Zhang University of California,San Diego yez033@ucsd.edu Yikun Huang University of California,San
More informationRecurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation
Recurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation Rudra P K Poudel, Pablo Lamata and Giovanni Montana Department of Biomedical Engineering, King s College London, SE1
More informationFully Convolutional Network-based Multi-Task Learning for Rectum and Rectal Cancer Segmentation
Fully Convolutional Network-based Multi-Task Learning for Rectum and Rectal Cancer Segmentation Joohyung Lee 1, Ji Eun Oh 1, Min Ju Kim 2, Bo Yun Hur 2, Sun Ah Cho 1 1, 2*, and Dae Kyung Sohn 1 Innovative
More informationMedical Knowledge Attention Enhanced Neural Model. for Named Entity Recognition in Chinese EMR
Medical Knowledge Attention Enhanced Neural Model for Named Entity Recognition in Chinese EMR Zhichang Zhang, Yu Zhang, Tong Zhou College of Computer Science and Engineering, Northwest Normal University,
More informationA general error-based spike-timing dependent learning rule for the Neural Engineering Framework
A general error-based spike-timing dependent learning rule for the Neural Engineering Framework Trevor Bekolay Monday, May 17, 2010 Abstract Previous attempts at integrating spike-timing dependent plasticity
More informationDeep 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 informationarxiv: v1 [stat.ml] 23 Mar 2017
The Dependence of Machine Learning on Electronic Medical Record Quality Long V. Ho, David Ledbetter, Melissa Aczon, Ph.D., Randall Wetzel, M.D. The Laura P. and Leland K. Whittier Virtual Pediatric Intensive
More informationGradient Masking Is a Type of Overfitting
Gradient Masking Is a Type of Overfitting Yusuke Yanagita and Masayuki Yamamura Abstract Neural networks have recently been attracting attention again as classifiers with high accuracy, so called deep
More informationComputational 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 informationComparison of Two Approaches for Direct Food Calorie Estimation
Comparison of Two Approaches for Direct Food Calorie Estimation Takumi Ege and Keiji Yanai Department of Informatics, The University of Electro-Communications, Tokyo 1-5-1 Chofugaoka, Chofu-shi, Tokyo
More informationBeyond Parity: Fairness Objectives for Collaborative Filtering
Beyond Parity: Fairness Objectives for Collaborative Filtering Sirui Yao Department of Computer Science Virginia Tech Blacksburg, VA 24061 ysirui@vt.edu Bert Huang Department of Computer Science Virginia
More informationDifferentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network
Original Article Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network Aida Allahverdi 1, Siavash Akbarzadeh 1, Alireza Khorrami Moghaddam 2, Armin Allahverdy
More informationMotivation: 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 informationMMSE Interference in Gaussian Channels 1
MMSE Interference in Gaussian Channels Shlomo Shamai Department of Electrical Engineering Technion - Israel Institute of Technology 202 Information Theory and Applications Workshop 5-0 February, San Diego
More informationarxiv: v1 [cs.cv] 9 Oct 2018
Automatic Segmentation of Thoracic Aorta Segments in Low-Dose Chest CT Julia M. H. Noothout a, Bob D. de Vos a, Jelmer M. Wolterink a, Ivana Išgum a a Image Sciences Institute, University Medical Center
More informationImage-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 informationConvolutional 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 informationRolls,E.T. (2016) Cerebral Cortex: Principles of Operation. Oxford University Press.
Digital Signal Processing and the Brain Is the brain a digital signal processor? Digital vs continuous signals Digital signals involve streams of binary encoded numbers The brain uses digital, all or none,
More informationDeep Learning based Information Extraction Framework on Chinese Electronic Health Records
Deep Learning based Information Extraction Framework on Chinese Electronic Health Records Bing Tian Yong Zhang Kaixin Liu Chunxiao Xing RIIT, Beijing National Research Center for Information Science and
More informationIntroduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018
Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this
More informationFactoid Question Answering
Factoid Question Answering CS 898 Project June 12, 2017 Salman Mohammed David R. Cheriton School of Computer Science University of Waterloo Motivation Source: https://www.apple.com/newsroom/2017/01/hey-siri-whos-going-to-win-the-super-bowl/
More informationRisk Prediction with Electronic Health Records: A Deep Learning Approach
Risk Prediction with Electronic Health Records: A Deep Learning Approach Abstract Yu Cheng Fei Wang Ping Zhang Jianying Hu The recent years have witnessed a surge of interests in data analytics with patient
More informationCS-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 informationPredicting Breast Cancer Survivability Rates
Predicting Breast Cancer Survivability Rates For data collected from Saudi Arabia Registries Ghofran Othoum 1 and Wadee Al-Halabi 2 1 Computer Science, Effat University, Jeddah, Saudi Arabia 2 Computer
More informationApplying Neural Networks Approach to Achieve the Parameter Optimization for Censored Data
Proceedings of the 2007 WSEAS International Conference on Computer Engineering and Applications, Gold Coast, Australia, January 17-19, 2007 516 Applying Neural Networks Approach to Achieve the Parameter
More informationDeep 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 informationCoronary Heart Disease Diagnosis using Deep Neural Networks
Coronary Heart Disease Diagnosis using Deep Neural Networks *Kathleen H. Miao a, b, *Julia H. Miao a a Cornell University, Ithaca, NY 14853, USA b New York University School of Medicine, New York, NY 10016,
More informationArrhythmia Detection from 2-lead ECG using Convolutional Denoising Autoencoders
Arrhythmia Detection from 2-lead ECG using Convolutional Denoising Autoencoders Keiichi Ochiai NTT DOCOMO, INC. ochiaike@nttdocomo.com Shu Takahashi SAS Institute Japan Ltd. shu.takahashi@sas.com Yusuke
More informationModel reconnaissance: discretization, naive Bayes and maximum-entropy. Sanne de Roever/ spdrnl
Model reconnaissance: discretization, naive Bayes and maximum-entropy Sanne de Roever/ spdrnl December, 2013 Description of the dataset There are two datasets: a training and a test dataset of respectively
More informationFormulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification
Formulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification Reza Lotfian and Carlos Busso Multimodal Signal Processing (MSP) lab The University of Texas
More informationPositive and Unlabeled Relational Classification through Label Frequency Estimation
Positive and Unlabeled Relational Classification through Label Frequency Estimation Jessa Bekker and Jesse Davis Computer Science Department, KU Leuven, Belgium firstname.lastname@cs.kuleuven.be Abstract.
More informationBayesRandomForest: An R
BayesRandomForest: An R implementation of Bayesian Random Forest for Regression Analysis of High-dimensional Data Oyebayo Ridwan Olaniran (rid4stat@yahoo.com) Universiti Tun Hussein Onn Malaysia Mohd Asrul
More informationarxiv: v1 [cs.cv] 24 Jul 2018
Multi-Class Lesion Diagnosis with Pixel-wise Classification Network Manu Goyal 1, Jiahua Ng 2, and Moi Hoon Yap 1 1 Visual Computing Lab, Manchester Metropolitan University, M1 5GD, UK 2 University of
More informationDeep Diabetologist: Learning to Prescribe Hypoglycemia Medications with Hierarchical Recurrent Neural Networks
Deep Diabetologist: Learning to Prescribe Hypoglycemia Medications with Hierarchical Recurrent Neural Networks Jing Mei a, Shiwan Zhao a, Feng Jin a, Eryu Xia a, Haifeng Liu a, Xiang Li a a IBM Research
More informationPositive and Unlabeled Relational Classification through Label Frequency Estimation
Positive and Unlabeled Relational Classification through Label Frequency Estimation Jessa Bekker and Jesse Davis Computer Science Department, KU Leuven, Belgium firstname.lastname@cs.kuleuven.be Abstract.
More informationOn the Combination of Collaborative and Item-based Filtering
On the Combination of Collaborative and Item-based Filtering Manolis Vozalis 1 and Konstantinos G. Margaritis 1 University of Macedonia, Dept. of Applied Informatics Parallel Distributed Processing Laboratory
More informationImage Captioning using Reinforcement Learning. Presentation by: Samarth Gupta
Image Captioning using Reinforcement Learning Presentation by: Samarth Gupta 1 Introduction Summary Supervised Models Image captioning as RL problem Actor Critic Architecture Policy Gradient architecture
More informationA Novel Method using Convolutional Neural Network for Segmenting Brain Tumor in MRI Images
A Novel Method using Convolutional Neural Network for Segmenting Brain Tumor in MRI Images K. Meena*, S. Pavitra**, N. Nishanthi*** & M. Nivetha**** *UG Student, Department of Electronics and Communication
More informationArecent paper [31] claims to (learn to) classify EEG
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 Training on the test set? An analysis of Spampinato et al. [31] Ren Li, Jared S. Johansen, Hamad Ahmed, Thomas V. Ilyevsky, Ronnie B Wilbur,
More information