convolutional poisson gamma belief network
play

Convolutional Poisson Gamma Belief Network Chaojie Wang Bo Chen - PowerPoint PPT Presentation

Jun 17, 2023 •171 likes •258 views

Convolutional Poisson Gamma Belief Network Chaojie Wang Bo Chen Sucheng Xiao Mingyuan Zhou National Laboratory of Radar Signal Processing, Xidian University, Xi'an, Shaanxi, China McCombs School of Business, The

  1. Convolutional Poisson Gamma Belief Network Chaojie Wang ♖ Bo Chen ♖ Sucheng Xiao ♖ Mingyuan Zhou ♘ ♖ National Laboratory of Radar Signal Processing, Xidian University, Xi'an, Shaanxi, China ♘ McCombs School of Business, The University of Texas at Austin, Austin, TX, USA National Lab of Radar Signal Processing Xidian University & UT-Austin 1 2019-6-11

  2. Motivation Document Representation q Basic Lossless Representation q Simplified Lossy Representation Ø A sequence of one-hot vectors Ø Bag-of-words Simplified ü Preserve all textual information ü Term-document frequency count matrix ※ Extremely large and sparse matrices ※ Lose word order ※ Burdens of calculation and storage Ø Word embeddings ※ Difficult to model directly ü Project words to low-dimensional vectors Document One-hot Sequence ※ Require additional large corpora I love it don't   0   0   0 Challenge       hate 0 0 0       “I love it”       Most basic representation I 1 0 0       0 0 1 it             0 1 0 love       National Lab of Radar Signal Processing Xidian University & UT-Austin 2 2019-6-11

  3. Our Contribution Convolutional Poisson Factor Analysis q Generative model of CPFA ü Preserve word order information ü Directly model sparse matrices ü Take advantages of the sparsity ü Support parallel computation ü Capture pharse-level topics Probabilistic Convolutional Layer National Lab of Radar Signal Processing Xidian University & UT-Austin 3 2019-6-11

  4. Our Contribution Convolutional Poisson Gamma Belief Network q Probabilistic Pooling Layer Equivalent q Generative model of CPGBN ü Transfer the messages from deeper layers ü Jointly Train all the other layers ü Deep extention can boost performance ü Hierachical pharse-level topic National Lab of Radar Signal Processing Xidian University & UT-Austin 4 2019-6-11

  5. Our Contribution Hybrid MCMC/Variational Inference q Convolutional inference network q Weibull Reparameterization Approximate ü Fast in out-of-sample prediction ü Parallel scalable inference ü Easy extension (e.g., modeling document labels) National Lab of Radar Signal Processing Xidian University & UT-Austin 5 2019-6-11

  6. Experiment Phrase-level Topics Visualization National Lab of Radar Signal Processing Xidian University & UT-Austin 6 2019-6-11

  7. Thank you ! Chaojie Wang ♖ Bo Chen ♖ Sucheng Xiao ♖ Mingyuan Zhou ♘ ♖ National Laboratory of Radar Signal Processing, Xidian University, Xi'an, Shaanxi, China ♘ McCombs School of Business, The University of Texas at Austin, Austin, TX, USA National Lab of Radar Signal Processing Xidian University & UT-Austin 7 2019-6-11

Recommend

Clustering and Ranking in Heterogeneous Information Networks via Gamma-Poisson Model Junxiang

Clustering and Ranking in Heterogeneous Information Networks via Gamma-Poisson Model Junxiang

Clustering and Ranking in Heterogeneous Information Networks via Gamma-Poisson Model Junxiang Chen Wei Dai Yizhou Sun Jennifer Dy Northeastern University May 1, 2015 Information Network Information networks are oftentimes used to

621 views • 21 slides
Belief network inference Four main approaches to determine posterior distributions in belief

Belief network inference Four main approaches to determine posterior distributions in belief

Belief network inference Four main approaches to determine posterior distributions in belief networks: Variable Elimination: exploit the structure of the network to eliminate (sum out) the non-observed, non-query variables one at a time.

330 views • 29 slides
Belief Networks Some Belief Network references E. Charniak Bayesian Networks without

Belief Networks Some Belief Network references E. Charniak Bayesian Networks without

Belief Networks Some Belief Network references E. Charniak Bayesian Networks without Tears, AI Magazine Winter 1991, pp 50-63 Chris Williams, School of Informatics University of Edinburgh D. Heckerman, A Tutorial on Learning

486 views • 6 slides
Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN)

Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN)

Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN) A.k.a. CNN or ConvNet Adit Deshpande, A Beginner's Guide To Understanding Convolutional Neural Networks. Digital Images Input array: an images

1.42k views • 72 slides
Math 186: 4.2 Poisson Distribution: Counting Crossovers in Meiosis 4.2 Exponential and 4.6 Gamma

Math 186: 4.2 Poisson Distribution: Counting Crossovers in Meiosis 4.2 Exponential and 4.6 Gamma

Math 186: 4.2 Poisson Distribution: Counting Crossovers in Meiosis 4.2 Exponential and 4.6 Gamma Distributions: Distance Between Crossovers Math 283: Ewens & Grant 1.3.7, 4.1-4.2 Prof. Tesler Math 186 and 283 Fall 2019 Prof. Tesler

875 views • 32 slides
Math 186: 4.2 Poisson Distribution: Counting Crossovers in Meiosis 4.2 Exponential and 4.6 Gamma

Math 186: 4.2 Poisson Distribution: Counting Crossovers in Meiosis 4.2 Exponential and 4.6 Gamma

Math 186: 4.2 Poisson Distribution: Counting Crossovers in Meiosis 4.2 Exponential and 4.6 Gamma Distributions: Distance Between Crossovers Math 283: Ewens & Grant 1.3.7, 4.1-4.2 Prof. Tesler Math 186 and 283 Winter 2019 Prof. Tesler

685 views • 31 slides
Poisson Distribution: Review Poisson Over Time Let B 1 Poisson( ) be the number of bikes

Poisson Distribution: Review Poisson Over Time Let B 1 Poisson( ) be the number of bikes

Poisson Distribution: Review Poisson Over Time Let B 1 Poisson( ) be the number of bikes that Values: are stolen on campus in one hour. (Go bears?) The Poisson Arrival Process Parameter(s) : What is the distribution of B 2 . 5 , the

924 views • 4 slides
ON TEGRA X1 ALAN WANG, NVIDIA Convolutional Neural Network optimization target Result

ON TEGRA X1 ALAN WANG, NVIDIA Convolutional Neural Network optimization target Result

DIRECT CONVOLUTION FOR DEEP NEURAL NETWORK CLASSIFICATION ON TEGRA X1 ALAN WANG, NVIDIA Convolutional Neural Network optimization target Result Convolutional Fully Connected Input layer layer Convolutional Layer An example: A E

621 views • 18 slides
Punt: T , T , T are mutually independent . How about T , the number of

Punt: T , T , T are mutually independent . How about T , the number of

Poisson Distribution: Review Poisson Over Time - neg Let B 1 Poisson( ) be the number of bikes that integers non Values: are stolen on campus in one hour. (Go bears?) The Poisson Arrival Process Parameter(s) : X " rate "

278 views • 4 slides
Inference in Belief Networks CMPUT 366: Intelligent Systems P&M 8.4 Lecture Outline

Inference in Belief Networks CMPUT 366: Intelligent Systems P&M 8.4 Lecture Outline

Inference in Belief Networks CMPUT 366: Intelligent Systems P&M 8.4 Lecture Outline 1. Recap 2. Factors 3. Variable Elimination 4. Efficiency Recap: Belief Networks Definition: A belief network (or Bayesian network )

1.27k views • 23 slides
A DYNAMIC BAYESIAN BELIEF NETWORK APPROACH FOR MODELING THE ATM NETWORK DELAYS Yi it Bekir

A DYNAMIC BAYESIAN BELIEF NETWORK APPROACH FOR MODELING THE ATM NETWORK DELAYS Yi it Bekir

A DYNAMIC BAYESIAN BELIEF NETWORK APPROACH FOR MODELING THE ATM NETWORK DELAYS Yi it Bekir Kaya Data Science Researcher at CAL, Aeronautics Graduate Student Prof. Gkhan nalhan Director of CAL Istanbul Technical University Controls

715 views • 67 slides
NuSpIn Nuclear Spectroscopy Instrumentation Network the network for the gamma-spectroscopy and

NuSpIn Nuclear Spectroscopy Instrumentation Network the network for the gamma-spectroscopy and

NuSpIn Nuclear Spectroscopy Instrumentation Network the network for the gamma-spectroscopy and complementary-instrumentation community Promotion and Coordination of scientific and technological activities for frontline research Exchange of

830 views • 18 slides
Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly

Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly

Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly used for what sort of task? a) Recognizing images b) Transcribing speech c) Translating documents d) Playing games Neural network review

431 views • 13 slides
Outline Convolutional Neural Network Architectures for Matching Natural Language Sentences.

Outline Convolutional Neural Network Architectures for Matching Natural Language Sentences.

Outline Hu, NIPS14 Irsoy, NIPS14 Outline Convolutional Neural Network Architectures for Matching Natural Language Sentences. NIPS14 Convolutional Sentence Model Convolutional Matching Models Experiments Deep Recursive Neural

779 views • 35 slides
Single-parameter models: Poisson data Applied Bayesian Statistics Dr. Earvin Balderama

Single-parameter models: Poisson data Applied Bayesian Statistics Dr. Earvin Balderama

Single-parameter models: Poisson data Applied Bayesian Statistics Dr. Earvin Balderama Department of Mathematics & Statistics Loyola University Chicago September 14, 2017 Poisson-Gamma model 1 Last edited September 8, 2017 by Earvin

321 views • 11 slides
Neural Network Basics Part II Content Image-to-image Why fully convolutional?

Neural Network Basics Part II Content Image-to-image Why fully convolutional?

Neural Network Basics Part II Content Image-to-image Why fully convolutional? Fully Convolutional Networks (FCN) Up-sampling Network architecture Recurrent Neural Networks Sequence data and representation

625 views • 45 slides
Using Python and XMPP to build a decentralized social network J er ome Poisson (Goffi)

Using Python and XMPP to build a decentralized social network J er ome Poisson (Goffi)

Using Python and XMPP to build a decentralized social network J er ome Poisson (Goffi) FOSDEM Saturday 30th January 2016 Some words about the project a lot of features other interfaces about the technologies global architecture

538 views • 32 slides
Learning a Belief Network If you know the structure have observed all of the variables

Learning a Belief Network If you know the structure have observed all of the variables

Learning a Belief Network If you know the structure have observed all of the variables have no missing data you can learn each conditional probability separately. D. Poole and A. Mackworth 2019 c Artificial Intelligence, Lecture

434 views • 40 slides
Learning a Belief Network If you know the structure have observed all of the variables

Learning a Belief Network If you know the structure have observed all of the variables

Learning a Belief Network If you know the structure have observed all of the variables have no missing data you can learn each conditional probability separately. D. Poole and A. Mackworth 2010 c Artificial Intelligence, Lecture

479 views • 17 slides
Convolutional Neural Networks Basics Praveen Krishnan Overview Paradigm Shift Simple

Convolutional Neural Networks Basics Praveen Krishnan Overview Paradigm Shift Simple

Convolutional Neural Networks Basics Praveen Krishnan Overview Paradigm Shift Simple Network Convolutional Network Layers Case Study1: Alex Net Training Generalization Visualizations Transfer Learning Case

1.02k views • 53 slides
Generative vs. discriminative Generative Discriminative Belief network A is more More

Generative vs. discriminative Generative Discriminative Belief network A is more More

Generative vs. discriminative Generative Discriminative Belief network A is more More robust modular Dont need precise model Class-conditional densities are specification, so long as it is likely to be local, characteristic

1.09k views • 15 slides
Randomness in Computing L ECTURE 14 Last time Poisson distribution Poisson approximation

Randomness in Computing L ECTURE 14 Last time Poisson distribution Poisson approximation

Randomness in Computing L ECTURE 14 Last time Poisson distribution Poisson approximation Today Review Poisson distribution Poisson approximation Application: max load Application: Coupon Collector 3/17/2020 Sofya

357 views • 10 slides
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting LSTM

Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting LSTM

Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting LSTM : VALSE 2016/03/23 Content Quick Review of Recurrent Neural Network

738 views • 27 slides
U-Finger Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting

U-Finger Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting

U-Finger Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting Ramakrishna Prabhu, Xiaojing Yu, Zhangyang Wang, Ding Liu, Anxiao (Andrew) Jiang Why Deep Neural Network ? Fingerprint restoration and

321 views • 20 slides

More recommend