The document discusses machine learning techniques for clustering and segmentation. It introduces Dirichlet process mixtures and the Chinese restaurant process as nonparametric Bayesian models that allow for an infinite number of clusters. It describes how these models can be used for problems like image segmentation, object recognition, population clustering from genetic data, and evolutionary document clustering over time. Approximate inference methods like Markov chain Monte Carlo sampling are used to analyze these models.
Medical pathology images are visually evaluated by experts for disease diagnosis, but the connectionbetween image features and the state of the cells in an image is typically unknown. To understand thisrelationship, we describe a multimodal modeling and inference framework that estimates shared latentstructure of joint gene expression levels and medical image features. The method is built aroundprobabilistic canonical correlation analysis (PCCA), which is jointly fit to image embeddings that are learnedusing convolutional neural networks and linear embeddings of paired gene expression data. We finallydiscuss a set of theoretical and empirical challenges in domain adaptation settings arising from genomics data.(based on work in collab with Gregory Gundersen and Barbara E. Engelhardt)
Since the advent of the horseshoe priors for regularization, global-local shrinkage methods have proved to be a fertile ground for the development of Bayesian theory and methodology in machine learning. They have achieved remarkable success in computation, and enjoy strong theoretical support. Much of the existing literature has focused on the linear Gaussian case. The purpose of the current talk is to demonstrate that the horseshoe priors are useful more broadly, by reviewing both methodological and computational developments in complex models that are more relevant to machine learning applications. Specifically, we focus on methodological challenges in horseshoe regularization in nonlinear and non-Gaussian models; multivariate models; and deep neural networks. We also outline the recent computational developments in horseshoe shrinkage for complex models along with a list of available software implementations that allows one to venture out beyond the comfort zone of the canonical linear regression problems.
Asynchronous Stochastic Optimization, New Analysis and AlgorithmsFabian Pedregosa
As datasets continue to increase in size and multi-core computer architectures are developed, asynchronous parallel optimization algorithms become more and more essential to the field of Machine Learning. In this talk I will describe two of our recent contributions to this topic. First, we highlight an important technical issue present in a large fraction of the recent convergence proofs for asynchronous parallel optimization algorithms and propose a new framework that resolves it [1]. Second, we propose a novel asynchronous variant of SAGA, a stochastic method that combines the low cost per iteration of SGD with the fast convergence rates of gradient descent [2]
[1] Leblond, R., Pedregosa, F., & Lacoste-Julien, S. (2018). Improved asynchronous parallel optimization analysis for stochastic incremental methods. arXiv:1801.03749, https://arxiv.org/pdf/1801.03749.pdf
[2] Pedregosa, F., Leblond, R., & Lacoste-Julien, S. (2017). Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization. In Advances in Neural Information Processing Systems, http://papers.nips.cc/paper/6611-breaking-the-nonsmooth-barrier-a-scalable-parallel-method-for-composite-optimization.pdf
Learning to discover monte carlo algorithm on spin ice manifoldKai-Wen Zhao
The global update Monte Carlo sampler can be discovered naturally by trained machine using policy gradient method on topologically constrained environment.
Medical pathology images are visually evaluated by experts for disease diagnosis, but the connectionbetween image features and the state of the cells in an image is typically unknown. To understand thisrelationship, we describe a multimodal modeling and inference framework that estimates shared latentstructure of joint gene expression levels and medical image features. The method is built aroundprobabilistic canonical correlation analysis (PCCA), which is jointly fit to image embeddings that are learnedusing convolutional neural networks and linear embeddings of paired gene expression data. We finallydiscuss a set of theoretical and empirical challenges in domain adaptation settings arising from genomics data.(based on work in collab with Gregory Gundersen and Barbara E. Engelhardt)
Since the advent of the horseshoe priors for regularization, global-local shrinkage methods have proved to be a fertile ground for the development of Bayesian theory and methodology in machine learning. They have achieved remarkable success in computation, and enjoy strong theoretical support. Much of the existing literature has focused on the linear Gaussian case. The purpose of the current talk is to demonstrate that the horseshoe priors are useful more broadly, by reviewing both methodological and computational developments in complex models that are more relevant to machine learning applications. Specifically, we focus on methodological challenges in horseshoe regularization in nonlinear and non-Gaussian models; multivariate models; and deep neural networks. We also outline the recent computational developments in horseshoe shrinkage for complex models along with a list of available software implementations that allows one to venture out beyond the comfort zone of the canonical linear regression problems.
Asynchronous Stochastic Optimization, New Analysis and AlgorithmsFabian Pedregosa
As datasets continue to increase in size and multi-core computer architectures are developed, asynchronous parallel optimization algorithms become more and more essential to the field of Machine Learning. In this talk I will describe two of our recent contributions to this topic. First, we highlight an important technical issue present in a large fraction of the recent convergence proofs for asynchronous parallel optimization algorithms and propose a new framework that resolves it [1]. Second, we propose a novel asynchronous variant of SAGA, a stochastic method that combines the low cost per iteration of SGD with the fast convergence rates of gradient descent [2]
[1] Leblond, R., Pedregosa, F., & Lacoste-Julien, S. (2018). Improved asynchronous parallel optimization analysis for stochastic incremental methods. arXiv:1801.03749, https://arxiv.org/pdf/1801.03749.pdf
[2] Pedregosa, F., Leblond, R., & Lacoste-Julien, S. (2017). Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization. In Advances in Neural Information Processing Systems, http://papers.nips.cc/paper/6611-breaking-the-nonsmooth-barrier-a-scalable-parallel-method-for-composite-optimization.pdf
Learning to discover monte carlo algorithm on spin ice manifoldKai-Wen Zhao
The global update Monte Carlo sampler can be discovered naturally by trained machine using policy gradient method on topologically constrained environment.
Kernel methods and variable selection for exploratory analysis and multi-omic...tuxette
Nathalie Vialaneix
4th course on Computational Systems Biology of Cancer: Multi-omics and Machine Learning Approaches
International course, Curie training
https://training.institut-curie.org/courses/sysbiocancer2021
(remote)
September 29th, 2021
Enhancing Partition Crossover with Articulation Points Analysisjfrchicanog
This is the presentation of the paper entitled "Enhancing Partition Crossover with Articulation Points Analysis" at the ECOM track in gECCO 2018 (Kyoto). This paper was awarded with a "Best Paper Award"
Towards new solutions for scientific computing: the case of JuliaMaurizio Tomasi
The year 2018 marks the consolidation of Julia (https://julialang.org/), a programming language designed for scientific computing, as the first stable version (1.0) has been released, in August 2018. Among its main features, expressiveness and high execution speeds are the most prominent: the performance of Julia code is similar to
statically compiled languages, yet Julia provides a nice interactive shell and fully supports Jupyter; moreover, it can transparently call external codes written in C, Fortran, and even Python and R without the need of wrappers. The usage of Julia in the astronomical community is growing, and a GitHub oganization named JuliaAstro takes care of coordinating the development of packages. In this ADASS talk we present the features and shortcomings of this language, and discuss its application in astronomy and astrophysics.
C. Guyon, T. Bouwmans. E. Zahzah, “Foreground Detection via Robust Low Rank Matrix Factorization including Spatial Constraint with Iterative Reweighted Regression”, International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, November 2012.
Mini useR! in Melbourne https://www.meetup.com/fr-FR/MelbURN-Melbourne-Users-of-R-Network/events/251933078/
MelbURN (Melbourne useR group) https://www.meetup.com/fr-FR/MelbURN-Melbourne-Users-of-R-Network
July 16th, 2018
Melbourne, Australia
Reviews on Deep Generative Models in the early days / GANs & VAEs paper reviewchangedaeoh
GAN, VAE등 초창기 생성모델(generative models)들을 리뷰한다.
coverage는 다음과 같다.
- VAE (2013)
- GAN (2014)
- Conditional GAN (2014)
- Conditional VAE (2015)
- Deep Convolutional GAN (2015)
- Information Maximizing GAN (2016)
TAVE research seminar 21.07.06 발표자료
발표자: 오창대
Representation Learning & Generative Modeling with Variational Autoencoder(VA...changedaeoh
표현학습(representation learning)과 생성모델링(generative modeling)에 대한 개요를 설명하고 이를 Auto-Encoding Variational Bayes 논문의 내용과 연결시켜 VAE를 이해한다.
연합동아리 TAVE research seminar 21.05.18 발표자료
발표자: 오창대
Kernel methods and variable selection for exploratory analysis and multi-omic...tuxette
Nathalie Vialaneix
4th course on Computational Systems Biology of Cancer: Multi-omics and Machine Learning Approaches
International course, Curie training
https://training.institut-curie.org/courses/sysbiocancer2021
(remote)
September 29th, 2021
Enhancing Partition Crossover with Articulation Points Analysisjfrchicanog
This is the presentation of the paper entitled "Enhancing Partition Crossover with Articulation Points Analysis" at the ECOM track in gECCO 2018 (Kyoto). This paper was awarded with a "Best Paper Award"
Towards new solutions for scientific computing: the case of JuliaMaurizio Tomasi
The year 2018 marks the consolidation of Julia (https://julialang.org/), a programming language designed for scientific computing, as the first stable version (1.0) has been released, in August 2018. Among its main features, expressiveness and high execution speeds are the most prominent: the performance of Julia code is similar to
statically compiled languages, yet Julia provides a nice interactive shell and fully supports Jupyter; moreover, it can transparently call external codes written in C, Fortran, and even Python and R without the need of wrappers. The usage of Julia in the astronomical community is growing, and a GitHub oganization named JuliaAstro takes care of coordinating the development of packages. In this ADASS talk we present the features and shortcomings of this language, and discuss its application in astronomy and astrophysics.
C. Guyon, T. Bouwmans. E. Zahzah, “Foreground Detection via Robust Low Rank Matrix Factorization including Spatial Constraint with Iterative Reweighted Regression”, International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, November 2012.
Mini useR! in Melbourne https://www.meetup.com/fr-FR/MelbURN-Melbourne-Users-of-R-Network/events/251933078/
MelbURN (Melbourne useR group) https://www.meetup.com/fr-FR/MelbURN-Melbourne-Users-of-R-Network
July 16th, 2018
Melbourne, Australia
Reviews on Deep Generative Models in the early days / GANs & VAEs paper reviewchangedaeoh
GAN, VAE등 초창기 생성모델(generative models)들을 리뷰한다.
coverage는 다음과 같다.
- VAE (2013)
- GAN (2014)
- Conditional GAN (2014)
- Conditional VAE (2015)
- Deep Convolutional GAN (2015)
- Information Maximizing GAN (2016)
TAVE research seminar 21.07.06 발표자료
발표자: 오창대
Representation Learning & Generative Modeling with Variational Autoencoder(VA...changedaeoh
표현학습(representation learning)과 생성모델링(generative modeling)에 대한 개요를 설명하고 이를 Auto-Encoding Variational Bayes 논문의 내용과 연결시켜 VAE를 이해한다.
연합동아리 TAVE research seminar 21.05.18 발표자료
발표자: 오창대
Bayesian inference for mixed-effects models driven by SDEs and other stochast...Umberto Picchini
An important, and well studied, class of stochastic models is given by stochastic differential equations (SDEs). In this talk, we consider Bayesian inference based on measurements from several individuals, to provide inference at the "population level" using mixed-effects modelling. We consider the case where dynamics are expressed via SDEs or other stochastic (Markovian) models. Stochastic differential equation mixed-effects models (SDEMEMs) are flexible hierarchical models that account for (i) the intrinsic random variability in the latent states dynamics, as well as (ii) the variability between individuals, and also (iii) account for measurement error. This flexibility gives rise to methodological and computational difficulties.
Fully Bayesian inference for nonlinear SDEMEMs is complicated by the typical intractability of the observed data likelihood which motivates the use of sampling-based approaches such as Markov chain Monte Carlo. A Gibbs sampler is proposed to target the marginal posterior of all parameters of interest. The algorithm is made computationally efficient through careful use of blocking strategies, particle filters (sequential Monte Carlo) and correlated pseudo-marginal approaches. The resulting methodology is is flexible, general and is able to deal with a large class of nonlinear SDEMEMs [1]. In a more recent work [2], we also explored ways to make inference even more scalable to an increasing number of individuals, while also dealing with state-space models driven by other stochastic dynamic models than SDEs, eg Markov jump processes and nonlinear solvers typically used in systems biology.
[1] S. Wiqvist, A. Golightly, AT McLean, U. Picchini (2020). Efficient inference for stochastic differential mixed-effects models using correlated particle pseudo-marginal algorithms, CSDA, https://doi.org/10.1016/j.csda.2020.107151
[2] S. Persson, N. Welkenhuysen, S. Shashkova, S. Wiqvist, P. Reith, G. W. Schmidt, U. Picchini, M. Cvijovic (2021). PEPSDI: Scalable and flexible inference framework for stochastic dynamic single-cell models, bioRxiv doi:10.1101/2021.07.01.450748.
Using AI Planning to Automate the Performance Analysis of SimulatorsRoland Ewald
Analyzing simulation algorithm performance is cumbersome: execute some runs, observe a performance metric, and analyze the results. Often, the results motivate follow-up experiments, which in turn may lead to additional experiments, and so on. This time-consuming and error-prone process can be automated with planning approaches from artificial intelligence, making simulator performance analysis more convenient and rigorous. This paper introduces ALeSiA, a prototypical system for automatic simulator performance analysis. It is independent of any specific simulation system and realizes a hypothesis-driven approach to evaluate performance.
Keynote of HOP-Rec @ RecSys 2018
Presenter: Jheng-Hong Yang
These slides aim to be a complementary material for the short paper: HOP-Rec @ RecSys18. It explains the intuition and some abstract idea behind the descriptions and mathematical symbols by illustrating some plots and figures.
Chap 8. Optimization for training deep modelsYoung-Geun Choi
연구실 내부 세미나 자료. Goodfellow et al. (2016), Deep Learning, MIT Press의 Chapter 8을 요약/발췌하였습니다. 깊은 신경망(deep neural network) 모형 훈련시 목적함수 최적화 방법으로 흔히 사용되는 방법들을 소개합니다.
Fashionista Chic Couture Maze & Coloring Adventures is a coloring and activity book filled with many maze games and coloring activities designed to delight and engage young fashion enthusiasts. Each page offers a unique blend of fashion-themed mazes and stylish illustrations to color, inspiring creativity and problem-solving skills in children.
This tutorial offers a step-by-step guide on how to effectively use Pinterest. It covers the basics such as account creation and navigation, as well as advanced techniques including creating eye-catching pins and optimizing your profile. The tutorial also explores collaboration and networking on the platform. With visual illustrations and clear instructions, this tutorial will equip you with the skills to navigate Pinterest confidently and achieve your goals.
Brushstrokes of Inspiration: Four Major Influences in Victor Gilbert’s Artist...KendraJohnson54
Throughout his career, Victor Gilbert was influenced heavily by various factors, the most notable being his upbringing and the artistic movements of his time. A rich tapestry of inspirations appears in Gilbert’s work, ranging from their own experiences to the art movements of that period.
The cherry: beauty, softness, its heart-shaped plastic has inspired artists since Antiquity. Cherries and strawberries were considered the fruits of paradise and thus represented the souls of men.
This document announces the winners of the 2024 Youth Poster Contest organized by MATFORCE. It lists the grand prize and age category winners for grades K-6, 7-12, and individual age groups from 5 years old to 18 years old.
Hadj Ounis's most notable work is his sculpture titled "Metamorphosis." This piece showcases Ounis's mastery of form and texture, as he seamlessly combines metal and wood to create a dynamic and visually striking composition. The juxtaposition of the two materials creates a sense of tension and harmony, inviting viewers to contemplate the relationship between nature and industry.
43. F B f W d t T t l SFrom Bag‐of‐Words to Total Scene
Understanding:
Evolutions of Topic Models in Vision
‐ Part 2 ‐‐ Part 2 ‐
L. Fei‐Fei
Computer Science Dept.
f dStanford University
44. Machine learning in computer vision
• Aug 15+16, Lecture 14 + 17: Topic modelsAug 15+16, Lecture 14 + 17: Topic models
– Object recognition
– Scene classification, image annotation, large‐scale image clustering
l d d– Total scene understanding
Aug 16: Part 2 – nonparametric topic models
8/8/2010 44L. Fei-Fei, Dragon Star 2010, Stanford
45. Case studies in visualCase studies in visual
• Sudderth et al:Sudderth et al:
– HDP for object recognition
• OPTIMOL• OPTIMOL:
– HDP for object recognition: incremental learning
• Li et al:
– CRP for large‐scale image clustering
46. Case studies in visualCase studies in visual
• Sudderth et al:Sudderth et al:
– HDP for object recognition
• OPTIMOL• OPTIMOL:
– HDP for object recognition: incremental learning
• Li et al:
– CRP for large‐scale image clustering
49. From Images to Features
Affinely Adapted Maximally Stable Linked SequencesAffinely Adapted
Harris Corners
y
Extremal Regions
q
of Canny Edges
• Some invariance to lighting & pose variationsSome invariance to lighting & pose variations
• Dense, multiscale, over-segmentation of image
50. A Discrete Feature Vocabulary
• Normalized histograms
SIFT Descriptors
Normalized histograms
of orientation energy
• Compute ~1,000 word Lowe IJCV 2004Compute 1,000 word
dictionary via K-means
• Map each feature to
appearance of
feature i in image j
Lowe, IJCV 2004
p
nearest visual word 2D position of
feature i in image j
51. Generative Model for Objects
For each image: Sample a reference position
For each feature:
Randomly choose one part
Sample from that part’s feature distribution
52. Objects as Mixture Models
• For a fixed reference position, our generative
model is equivalent to a finite mixture model:q
Feature Pr(part)
appearance
Feature
position
( )
Pr(appearance | part)
Pr(position | part)
• How many parts should we choose?
Too few reduces model accuracy Too few reduces model accuracy
Too many causes overfitting & poor generalization
53. Dirichlet Process Mixtures
• Dirichlet processes define a prior distribution
i ht i d t i t ton weights assigned to mixture components:
0 1
concentration
parameter
Stick-Breaking Construction: Sethuraman, 1994
54. Objects as Distributions
Feature
appearance
Feature
position
Pr(appearance | part) Pr(position | part)
• Parts are defined by parameters, which
encode distributions on visual features:
Obj t d fi d b di t ib ti th• Objects are defined by distributions on the
infinitely many potential part parameters:
55. Dirichlet Process Object Model
H RPart-based object model
sampled from DP prior:
G
For each of J
images, sample a
reference position:
For each of N features,
sample part parameters:
JN
w vSample multinomial
feature appearance:
Sample Gaussian
feature position:Jfeature appearance: p
56. Learning DPs: Gibbs Sampling
P t S l &
H R
Image Scale
(insensitive)
Part Scale &
Visual Sparsity
(insensitive)
G Sample Integrate
Sample
Integrate parameters
defining feature distributions
Sample assignments
clustering features to parts
JN
w v
J
Dirichlet processes have many desirable analytic properties,
which lead to efficient Rao-Blackwellized learning algorithms
59. Learning Shared Parts
• Objects are often locally similar in appearance
• Discover parts shared across categories
How many total parts should we share?y p
How many parts should each category use?
67. Visualization of Part Densities
Horse Face
Llama Body
Wheelchair
Dog Face
Cow Face
Llama Face
Cat Face
Cougar Face
Leopard Face
g
Motorbike
Bicycle
Cannon
Cat Face
Rhino Body
Horse Body
Leopard Body
Motorbike
Hierarchical Clustering of Pr(part | object)
Elephant Body
Rhino Body
69. Detection Results
Shared Parts
more accurate than
Unshared PartsUnshared Parts
Modeling feature positions
improves shared detection, but
hurts unshared detectionhurts unshared detection
6 Training Images per Category
(ROC Curves)
73. Recognition Results
6 Training Images per Category
(ROC C )
Detection vs. Training Set Size
(ROC Curves) (Area Under ROC)
74. Case studies in visualCase studies in visual
• Sudderth et al:Sudderth et al:
– HDP for object recognition
• OPTIMOL• OPTIMOL:
– HDP for object recognition: incremental learning
• Li et al:
– CRP for large‐scale image clustering
85. OPTIMOLOPTIMOL Pitfall: model over‐specializationPitfall: model over specialization
Object Model…
Good Images “Bad” Images
Li, Wang & Fei-Fei, CVPR 2007
88. The “cache set”OPTIMOLOPTIMOL
C h S tC h S t C h S tC h S td t td t t d t td t t
Li, Wang & Fei-Fei, CVPR 2007
Cache SetCache Set Cache SetCache Setdatasetdataset datasetdataset
103. Case studies in visualCase studies in visual
• Sudderth et al:Sudderth et al:
– HDP for object recognition
• OPTIMOL• OPTIMOL:
– HDP for object recognition: incremental learning
• Li et al:
– CRP for large‐scale image clustering
104. From 1 image ‐> 100…0000 imagesFrom 1 image > 100…0000 images
70GB; 10^5‐10^6 images
10^7 or 10^810^7 or 10^8