SlideShare a Scribd company logo
Nakayama Lab.
Machine Perception Group
The University of Tokyo
The University of Tokyo
Grad. School of Information Science and Technology
Hideki Nakayama
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Deep learning
◦ Successive local response filters and pooling layers
◦ State-of-the-art performance on many tasks & benchmarks
 Traditional BoW-based models are often referred to as
“shallow learning” (interpreted as a single-layer network)
2
[A. Krizhevsky et al., NIPS’12]
Nakayama Lab.
Machine Perception Group
The University of Tokyo
To achieve a certain level of representational power...
 Deep models are believed to require fewer free parameters
or neurons [Larochelle et al., 2007] [Bengio, 2009] [Delalleau and Bengio, 2011]
(not fully proved except for some specific cases, though.)
 However, optimization of deep models is challenging
◦ Non-convex, local minima, many heuristic hyperparameters...
◦ Optimizing shallow network is relatively easy (convex in many cases)
3
(If successfully
trained)  Better generalization
 Computational efficiency
 Scalability
Objection:
“Do Deep Nets Really
Need to be Deep?”
[Ba & Caruana, 2014]
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Suboptimal (layer-wise)
 Reasonable performance
◦ Even random weights
could work! [Jarrette, 2009]
 Easiness in tuning
 Stability in learning
 Flexibility in the choice of
layer modules
 Global optimality through
the entire network
 State-of-the-art performance
 Difficulty in optimization
 Computational cost
 Constraints on layer modules
4
Fine-tuning (back propagation)
through the entire network is
the key to the best performance!
Structure of the deep network
itself has the primary importance!
Global training of deep models Stacking single-layer
learning modules
◎
◎△
○
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Suboptimal (layer-wise)
 Reasonable performance
◦ Even random weights
could work! [Jarrette, 2009]
 Easiness in tuning
 Stability in learning
 Flexibility in the choice of
layer modules
 Global optimality through
the entire network
 State-of-the-art performance
 Difficulty in optimization
 Computational cost
 Constraints on layer modules
5
Fine-tuning (back propagation)
through the entire network is
the key to the best performance!
Structure of the deep network
itself has the primary importance!
Global training of deep models Stacking single-layer
learning modules
◎
◎△
○
Nakayama Lab.
Machine Perception Group
The University of Tokyo
Empirically studied on top of the bag-of-words framework
 Hyperfeatures [Agarwal et al., ECCV’06]
◦ Hierarchically stack bag-of-visual-words layers
 Deep Fisher Network [Simonyan et al., NIPS’13]
 Deep Sparse Coding [He et al., SDM’14]
6
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Higher-order Local Auto-Correlation (HLAC) features
◦ Non-linear filter (mask) response + average pooling
◦ Successfully deployed in many visual recognition applications
 Cons:
◦ Higher-order correlation & masks are required to achieve good
performance, making the feature representation high-dimensional
7
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Sum-product network [Poon and Domingos, UAI’11]
◦ A deep network where each node (neuron) outputs the sum or
product of input variables
 To represent the same functions, the number of nodes
has to grow: [Delalleau & Bengio, NIPS’11]
◦ Exponentially in a shallow network
◦ Linearly in a deep network
8
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 So, why not use deep models?
9
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Hierarchically compute low-order local correlations
 Naturally includes a ConvNet-like structure
10
※LAC = Local auto correlation
Repeat multiple times
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Datasets
◦ MNIST [LeCun,1999]
 Digit recognition
 60k training/10k testing samples
 28x28 pixels
◦ CIFAR-10 [Krizhevsky, 2009]
 Object recognition
 50k training/10k testing samples
 32x32 pixels
◦ Caltech-101 [Fei-Fei, 2004]
 Object recognition
 30 training/15 testing samples
(per class)
 Classifier
◦ Logistic regression
11
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 SLAC achieves better performance than standard
HLAC with reduced feature dimensions
12
84
86
88
90
92
94
96
98
100
HLAC
2nd-order
(35 dim)
HLAC
2nd-order
mask size 5
(219 dim)
HLAC
3rd-order
(153 dim)
HLAC
3rd-order
(2245 dim)
SLAC
2-layers
(1176 dim)
0
10
20
30
40
50
60
70
HLAC
1st-order
(45 dim)
HLAC
2nd-order
(739 dim)
HLAC
2nd-order
mask size 5
(5419 dim)
HLAC
3rd-order
(8023 dim)
SLAC
2-layers
(1176 dim)
Accuracy (%) Accuracy (%)MNIST (gray scale) CIFAR-10 (color)
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Replace raw patches with densely sampled
SIFT descriptors (SIFT-SLAC)
13
0
10
20
30
40
50
60
70
SLAC
3-layers
(2628 dim)
SIFT-SLAC
1-layer
(2628 dim)
SIFT-SLAC
3-layers
(2628 dim)
SIFT-BoVW
(4000 dim)
SIFT-Fisher
(8192 dim)
Accuracy (%) Caltech-101
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Combining SLAC layers with Fisher framework boosts
the performance
◦ Different statistical properties can be exploited
14
40
45
50
55
60
65
70
SIFT-Fisher
(a)
SIFT-
SLAC(1-layer)
-Fisher
(b)
SIFT-
SLAC (2-layers)
-Fisher
(c)
(a) + (b) (a) + (b) + (c)
Accuracy (%) Caltech-101
Nakayama Lab.
Machine Perception Group
The University of Tokyo
 Deep learning by stacking is a simple but powerful, flexible
framework to integrate various single-layer modules
 Stacked local autocorrelation (SLAC) features
◦ Iterate computation of local autocorrelation and PCA compression
◦ More efficient than standard HLAC that computes everything in a
single layer
◦ Using multiple layers makes sense
 Learning polynomials is a hot topic in ML
◦ R. Livni et al., Vanishing Component Analysis, In Proc. ICML, 2013.
◦ A. Andoni et al., Learning Polynomials with Neural Networks, In Proc. ICML, 2014.
15

More Related Content

What's hot

NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...
NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...
NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...
csandit
 
A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN
A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN
A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN
csandit
 
Comparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksComparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural Networks
Vincenzo Lomonaco
 
Lecture3 xing fei-fei
Lecture3 xing fei-feiLecture3 xing fei-fei
Lecture3 xing fei-fei
Tianlu Wang
 
Deep LearningフレームワークChainerと最近の技術動向
Deep LearningフレームワークChainerと最近の技術動向Deep LearningフレームワークChainerと最近の技術動向
Deep LearningフレームワークChainerと最近の技術動向
Shunta Saito
 
教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...
教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...
教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...
cvpaper. challenge
 
Robust Ensemble Classifier Combination Based on Noise Removal with One-Class SVM
Robust Ensemble Classifier Combination Based on Noise Removal with One-Class SVMRobust Ensemble Classifier Combination Based on Noise Removal with One-Class SVM
Robust Ensemble Classifier Combination Based on Noise Removal with One-Class SVM
Ferhat Ozgur Catak
 
Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)
PetteriTeikariPhD
 
Image Restoration for 3D Computer Vision
Image Restoration for 3D Computer VisionImage Restoration for 3D Computer Vision
Image Restoration for 3D Computer Vision
PetteriTeikariPhD
 
Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...
Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...
Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...
Ferhat Ozgur Catak
 
A new multiple classifiers soft decisions fusion approach for exons predictio...
A new multiple classifiers soft decisions fusion approach for exons predictio...A new multiple classifiers soft decisions fusion approach for exons predictio...
A new multiple classifiers soft decisions fusion approach for exons predictio...Ismail M. El-Badawy
 
Accelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile SystemsAccelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile Systems
Darian Frajberg
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
Poo Kuan Hoong
 
Devil in the Details: Analysing the Performance of ConvNet Features
Devil in the Details: Analysing the Performance of ConvNet FeaturesDevil in the Details: Analysing the Performance of ConvNet Features
Devil in the Details: Analysing the Performance of ConvNet Features
Ken Chatfield
 
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleDataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
Hakka Labs
 
Dario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineeringDario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineering
Advanced-Concepts-Team
 
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
IRJET Journal
 
One shot learning
One shot learningOne shot learning
One shot learning
Vuong Ho Ngoc
 
184816386 x mining
184816386 x mining184816386 x mining
184816386 x mining496573
 
AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...
AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...
AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...
GeeksLab Odessa
 

What's hot (20)

NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...
NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...
NEURAL NETWORKS FOR HIGH PERFORMANCE TIME-DELAY ESTIMATION AND ACOUSTIC SOURC...
 
A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN
A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN
A NOVEL BACKGROUND SUBTRACTION ALGORITHM FOR PERSON TRACKING BASED ON K-NN
 
Comparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksComparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural Networks
 
Lecture3 xing fei-fei
Lecture3 xing fei-feiLecture3 xing fei-fei
Lecture3 xing fei-fei
 
Deep LearningフレームワークChainerと最近の技術動向
Deep LearningフレームワークChainerと最近の技術動向Deep LearningフレームワークChainerと最近の技術動向
Deep LearningフレームワークChainerと最近の技術動向
 
教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...
教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...
教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2018 完全読破...
 
Robust Ensemble Classifier Combination Based on Noise Removal with One-Class SVM
Robust Ensemble Classifier Combination Based on Noise Removal with One-Class SVMRobust Ensemble Classifier Combination Based on Noise Removal with One-Class SVM
Robust Ensemble Classifier Combination Based on Noise Removal with One-Class SVM
 
Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)
 
Image Restoration for 3D Computer Vision
Image Restoration for 3D Computer VisionImage Restoration for 3D Computer Vision
Image Restoration for 3D Computer Vision
 
Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...
Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...
Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Mach...
 
A new multiple classifiers soft decisions fusion approach for exons predictio...
A new multiple classifiers soft decisions fusion approach for exons predictio...A new multiple classifiers soft decisions fusion approach for exons predictio...
A new multiple classifiers soft decisions fusion approach for exons predictio...
 
Accelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile SystemsAccelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile Systems
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
Devil in the Details: Analysing the Performance of ConvNet Features
Devil in the Details: Analysing the Performance of ConvNet FeaturesDevil in the Details: Analysing the Performance of ConvNet Features
Devil in the Details: Analysing the Performance of ConvNet Features
 
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleDataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
 
Dario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineeringDario izzo - Machine Learning methods and space engineering
Dario izzo - Machine Learning methods and space engineering
 
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
 
One shot learning
One shot learningOne shot learning
One shot learning
 
184816386 x mining
184816386 x mining184816386 x mining
184816386 x mining
 
AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...
AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...
AI&BigData Lab 2016. Артем Чернодуб: Обучение глубоких, очень глубоких и реку...
 

Viewers also liked

SSII2014 詳細画像識別 (FGVC) @OS2
SSII2014 詳細画像識別 (FGVC) @OS2SSII2014 詳細画像識別 (FGVC) @OS2
SSII2014 詳細画像識別 (FGVC) @OS2nlab_utokyo
 
RecSysTV2014
RecSysTV2014RecSysTV2014
RecSysTV2014
nlab_utokyo
 
Lab introduction 2014
Lab introduction 2014Lab introduction 2014
Lab introduction 2014nlab_utokyo
 
画像処理分野における研究事例紹介
画像処理分野における研究事例紹介画像処理分野における研究事例紹介
画像処理分野における研究事例紹介
nlab_utokyo
 
20150414seminar
20150414seminar20150414seminar
20150414seminar
nlab_utokyo
 
20160601画像電子学会
20160601画像電子学会20160601画像電子学会
20160601画像電子学会
nlab_utokyo
 
Machine Translation Introduction
Machine Translation IntroductionMachine Translation Introduction
Machine Translation Introduction
nlab_utokyo
 
20150930
2015093020150930
20150930
nlab_utokyo
 
Deep Learningによる画像認識革命 ー歴史・最新理論から実践応用までー
Deep Learningによる画像認識革命 ー歴史・最新理論から実践応用までーDeep Learningによる画像認識革命 ー歴史・最新理論から実践応用までー
Deep Learningによる画像認識革命 ー歴史・最新理論から実践応用までー
nlab_utokyo
 
マシンパーセプション研究におけるChainer活用事例
マシンパーセプション研究におけるChainer活用事例マシンパーセプション研究におけるChainer活用事例
マシンパーセプション研究におけるChainer活用事例
nlab_utokyo
 
Deep Learningと画像認識   ~歴史・理論・実践~
Deep Learningと画像認識 ~歴史・理論・実践~Deep Learningと画像認識 ~歴史・理論・実践~
Deep Learningと画像認識   ~歴史・理論・実践~
nlab_utokyo
 
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Koichi Hamada
 
DeepLearningDay2016Summer
DeepLearningDay2016SummerDeepLearningDay2016Summer
DeepLearningDay2016Summer
Takayoshi Yamashita
 
Tutorial-DeepLearning-PCSJ-IMPS2016
Tutorial-DeepLearning-PCSJ-IMPS2016Tutorial-DeepLearning-PCSJ-IMPS2016
Tutorial-DeepLearning-PCSJ-IMPS2016
Takayoshi Yamashita
 
GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data
GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series dataGTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data
GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data
Yuki Hayashi
 
Deep Learningの技術と未来
Deep Learningの技術と未来Deep Learningの技術と未来
Deep Learningの技術と未来
Seiya Tokui
 
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
Takayoshi Yamashita
 
画像認識のための深層学習
画像認識のための深層学習画像認識のための深層学習
画像認識のための深層学習
Saya Katafuchi
 

Viewers also liked (20)

Seminar
SeminarSeminar
Seminar
 
SSII2014 詳細画像識別 (FGVC) @OS2
SSII2014 詳細画像識別 (FGVC) @OS2SSII2014 詳細画像識別 (FGVC) @OS2
SSII2014 詳細画像識別 (FGVC) @OS2
 
RecSysTV2014
RecSysTV2014RecSysTV2014
RecSysTV2014
 
ICME 2013
ICME 2013ICME 2013
ICME 2013
 
Lab introduction 2014
Lab introduction 2014Lab introduction 2014
Lab introduction 2014
 
画像処理分野における研究事例紹介
画像処理分野における研究事例紹介画像処理分野における研究事例紹介
画像処理分野における研究事例紹介
 
20150414seminar
20150414seminar20150414seminar
20150414seminar
 
20160601画像電子学会
20160601画像電子学会20160601画像電子学会
20160601画像電子学会
 
Machine Translation Introduction
Machine Translation IntroductionMachine Translation Introduction
Machine Translation Introduction
 
20150930
2015093020150930
20150930
 
Deep Learningによる画像認識革命 ー歴史・最新理論から実践応用までー
Deep Learningによる画像認識革命 ー歴史・最新理論から実践応用までーDeep Learningによる画像認識革命 ー歴史・最新理論から実践応用までー
Deep Learningによる画像認識革命 ー歴史・最新理論から実践応用までー
 
マシンパーセプション研究におけるChainer活用事例
マシンパーセプション研究におけるChainer活用事例マシンパーセプション研究におけるChainer活用事例
マシンパーセプション研究におけるChainer活用事例
 
Deep Learningと画像認識   ~歴史・理論・実践~
Deep Learningと画像認識 ~歴史・理論・実践~Deep Learningと画像認識 ~歴史・理論・実践~
Deep Learningと画像認識   ~歴史・理論・実践~
 
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
Laplacian Pyramid of Generative Adversarial Networks (LAPGAN) - NIPS2015読み会 #...
 
DeepLearningDay2016Summer
DeepLearningDay2016SummerDeepLearningDay2016Summer
DeepLearningDay2016Summer
 
Tutorial-DeepLearning-PCSJ-IMPS2016
Tutorial-DeepLearning-PCSJ-IMPS2016Tutorial-DeepLearning-PCSJ-IMPS2016
Tutorial-DeepLearning-PCSJ-IMPS2016
 
GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data
GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series dataGTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data
GTC Japan 2015 - Experiments to apply Deep Learning to Forex time series data
 
Deep Learningの技術と未来
Deep Learningの技術と未来Deep Learningの技術と未来
Deep Learningの技術と未来
 
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例NVIDIA Seminar ディープラーニングによる画像認識と応用事例
NVIDIA Seminar ディープラーニングによる画像認識と応用事例
 
画像認識のための深層学習
画像認識のための深層学習画像認識のための深層学習
画像認識のための深層学習
 

Similar to MIRU2014 SLAC

Deep learning: Modeling high-level face features through deep networks
Deep learning: Modeling high-level face features through deep networksDeep learning: Modeling high-level face features through deep networks
Deep learning: Modeling high-level face features through deep networks
Nelson Forte
 
Fa19_P1.pptx
Fa19_P1.pptxFa19_P1.pptx
Fa19_P1.pptx
Md Abul Hayat
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
PyData
 
LSTM Structured Pruning
LSTM Structured PruningLSTM Structured Pruning
LSTM Structured Pruning
VasileiosMezaris
 
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
datasciencekorea
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
Felipe Prado
 
REVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNNREVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNN
IRJET Journal
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
Namkug Kim
 
Deep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLabDeep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLab
NECST Lab @ Politecnico di Milano
 
Chaos Engineering - The Art of Breaking Things in Production
Chaos Engineering - The Art of Breaking Things in ProductionChaos Engineering - The Art of Breaking Things in Production
Chaos Engineering - The Art of Breaking Things in Production
Keet Sugathadasa
 
Easily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearningEasily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearning
IRJET Journal
 
Face detection ppt by Batyrbek
Face detection ppt by Batyrbek Face detection ppt by Batyrbek
Face detection ppt by Batyrbek Batyrbek Ryskhan
 
ExplainableAI.pptx
ExplainableAI.pptxExplainableAI.pptx
ExplainableAI.pptx
Andrea Morichetta
 
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
Value Amplify Consulting
 
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
Mohsen Sadok
 
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ..."Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
Edge AI and Vision Alliance
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
홍배 김
 
Low Power High-Performance Computing on the BeagleBoard Platform
Low Power High-Performance Computing on the BeagleBoard PlatformLow Power High-Performance Computing on the BeagleBoard Platform
Low Power High-Performance Computing on the BeagleBoard Platform
a3labdsp
 
Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks
Mah Sa
 
MPerceptron
MPerceptronMPerceptron
MPerceptronbutest
 

Similar to MIRU2014 SLAC (20)

Deep learning: Modeling high-level face features through deep networks
Deep learning: Modeling high-level face features through deep networksDeep learning: Modeling high-level face features through deep networks
Deep learning: Modeling high-level face features through deep networks
 
Fa19_P1.pptx
Fa19_P1.pptxFa19_P1.pptx
Fa19_P1.pptx
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
LSTM Structured Pruning
LSTM Structured PruningLSTM Structured Pruning
LSTM Structured Pruning
 
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
Deep Learning - 인공지능 기계학습의 새로운 트랜드 :김인중
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
 
REVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNNREVIEW ON OBJECT DETECTION WITH CNN
REVIEW ON OBJECT DETECTION WITH CNN
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
 
Deep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLabDeep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLab
 
Chaos Engineering - The Art of Breaking Things in Production
Chaos Engineering - The Art of Breaking Things in ProductionChaos Engineering - The Art of Breaking Things in Production
Chaos Engineering - The Art of Breaking Things in Production
 
Easily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearningEasily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearning
 
Face detection ppt by Batyrbek
Face detection ppt by Batyrbek Face detection ppt by Batyrbek
Face detection ppt by Batyrbek
 
ExplainableAI.pptx
ExplainableAI.pptxExplainableAI.pptx
ExplainableAI.pptx
 
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
 
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
 
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ..."Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
"Energy-efficient Hardware for Embedded Vision and Deep Convolutional Neural ...
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
 
Low Power High-Performance Computing on the BeagleBoard Platform
Low Power High-Performance Computing on the BeagleBoard PlatformLow Power High-Performance Computing on the BeagleBoard Platform
Low Power High-Performance Computing on the BeagleBoard Platform
 
Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks
 
MPerceptron
MPerceptronMPerceptron
MPerceptron
 

Recently uploaded

State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
Paul Groth
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
Alison B. Lowndes
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 

Recently uploaded (20)

State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 

MIRU2014 SLAC

  • 1. Nakayama Lab. Machine Perception Group The University of Tokyo The University of Tokyo Grad. School of Information Science and Technology Hideki Nakayama
  • 2. Nakayama Lab. Machine Perception Group The University of Tokyo  Deep learning ◦ Successive local response filters and pooling layers ◦ State-of-the-art performance on many tasks & benchmarks  Traditional BoW-based models are often referred to as “shallow learning” (interpreted as a single-layer network) 2 [A. Krizhevsky et al., NIPS’12]
  • 3. Nakayama Lab. Machine Perception Group The University of Tokyo To achieve a certain level of representational power...  Deep models are believed to require fewer free parameters or neurons [Larochelle et al., 2007] [Bengio, 2009] [Delalleau and Bengio, 2011] (not fully proved except for some specific cases, though.)  However, optimization of deep models is challenging ◦ Non-convex, local minima, many heuristic hyperparameters... ◦ Optimizing shallow network is relatively easy (convex in many cases) 3 (If successfully trained)  Better generalization  Computational efficiency  Scalability Objection: “Do Deep Nets Really Need to be Deep?” [Ba & Caruana, 2014]
  • 4. Nakayama Lab. Machine Perception Group The University of Tokyo  Suboptimal (layer-wise)  Reasonable performance ◦ Even random weights could work! [Jarrette, 2009]  Easiness in tuning  Stability in learning  Flexibility in the choice of layer modules  Global optimality through the entire network  State-of-the-art performance  Difficulty in optimization  Computational cost  Constraints on layer modules 4 Fine-tuning (back propagation) through the entire network is the key to the best performance! Structure of the deep network itself has the primary importance! Global training of deep models Stacking single-layer learning modules ◎ ◎△ ○
  • 5. Nakayama Lab. Machine Perception Group The University of Tokyo  Suboptimal (layer-wise)  Reasonable performance ◦ Even random weights could work! [Jarrette, 2009]  Easiness in tuning  Stability in learning  Flexibility in the choice of layer modules  Global optimality through the entire network  State-of-the-art performance  Difficulty in optimization  Computational cost  Constraints on layer modules 5 Fine-tuning (back propagation) through the entire network is the key to the best performance! Structure of the deep network itself has the primary importance! Global training of deep models Stacking single-layer learning modules ◎ ◎△ ○
  • 6. Nakayama Lab. Machine Perception Group The University of Tokyo Empirically studied on top of the bag-of-words framework  Hyperfeatures [Agarwal et al., ECCV’06] ◦ Hierarchically stack bag-of-visual-words layers  Deep Fisher Network [Simonyan et al., NIPS’13]  Deep Sparse Coding [He et al., SDM’14] 6
  • 7. Nakayama Lab. Machine Perception Group The University of Tokyo  Higher-order Local Auto-Correlation (HLAC) features ◦ Non-linear filter (mask) response + average pooling ◦ Successfully deployed in many visual recognition applications  Cons: ◦ Higher-order correlation & masks are required to achieve good performance, making the feature representation high-dimensional 7
  • 8. Nakayama Lab. Machine Perception Group The University of Tokyo  Sum-product network [Poon and Domingos, UAI’11] ◦ A deep network where each node (neuron) outputs the sum or product of input variables  To represent the same functions, the number of nodes has to grow: [Delalleau & Bengio, NIPS’11] ◦ Exponentially in a shallow network ◦ Linearly in a deep network 8
  • 9. Nakayama Lab. Machine Perception Group The University of Tokyo  So, why not use deep models? 9
  • 10. Nakayama Lab. Machine Perception Group The University of Tokyo  Hierarchically compute low-order local correlations  Naturally includes a ConvNet-like structure 10 ※LAC = Local auto correlation Repeat multiple times
  • 11. Nakayama Lab. Machine Perception Group The University of Tokyo  Datasets ◦ MNIST [LeCun,1999]  Digit recognition  60k training/10k testing samples  28x28 pixels ◦ CIFAR-10 [Krizhevsky, 2009]  Object recognition  50k training/10k testing samples  32x32 pixels ◦ Caltech-101 [Fei-Fei, 2004]  Object recognition  30 training/15 testing samples (per class)  Classifier ◦ Logistic regression 11
  • 12. Nakayama Lab. Machine Perception Group The University of Tokyo  SLAC achieves better performance than standard HLAC with reduced feature dimensions 12 84 86 88 90 92 94 96 98 100 HLAC 2nd-order (35 dim) HLAC 2nd-order mask size 5 (219 dim) HLAC 3rd-order (153 dim) HLAC 3rd-order (2245 dim) SLAC 2-layers (1176 dim) 0 10 20 30 40 50 60 70 HLAC 1st-order (45 dim) HLAC 2nd-order (739 dim) HLAC 2nd-order mask size 5 (5419 dim) HLAC 3rd-order (8023 dim) SLAC 2-layers (1176 dim) Accuracy (%) Accuracy (%)MNIST (gray scale) CIFAR-10 (color)
  • 13. Nakayama Lab. Machine Perception Group The University of Tokyo  Replace raw patches with densely sampled SIFT descriptors (SIFT-SLAC) 13 0 10 20 30 40 50 60 70 SLAC 3-layers (2628 dim) SIFT-SLAC 1-layer (2628 dim) SIFT-SLAC 3-layers (2628 dim) SIFT-BoVW (4000 dim) SIFT-Fisher (8192 dim) Accuracy (%) Caltech-101
  • 14. Nakayama Lab. Machine Perception Group The University of Tokyo  Combining SLAC layers with Fisher framework boosts the performance ◦ Different statistical properties can be exploited 14 40 45 50 55 60 65 70 SIFT-Fisher (a) SIFT- SLAC(1-layer) -Fisher (b) SIFT- SLAC (2-layers) -Fisher (c) (a) + (b) (a) + (b) + (c) Accuracy (%) Caltech-101
  • 15. Nakayama Lab. Machine Perception Group The University of Tokyo  Deep learning by stacking is a simple but powerful, flexible framework to integrate various single-layer modules  Stacked local autocorrelation (SLAC) features ◦ Iterate computation of local autocorrelation and PCA compression ◦ More efficient than standard HLAC that computes everything in a single layer ◦ Using multiple layers makes sense  Learning polynomials is a hot topic in ML ◦ R. Livni et al., Vanishing Component Analysis, In Proc. ICML, 2013. ◦ A. Andoni et al., Learning Polynomials with Neural Networks, In Proc. ICML, 2014. 15