SlideShare ist ein Scribd-Unternehmen logo
1 von 21
Downloaden Sie, um offline zu lesen
MorphNet: Fast & Simple Resource-Constrained Structure
Learning of Deep Networks
주성훈, 삼성SDS AI선행연구Lab.
2019. 8. 11.
PR-187
Ariel Gordon1, Elad Eban1, Ofir Nachum2, Bo Chen1, Hao Wu1, Tien-Ju Yang1,3, and Edward Choi1,4
1 Google Research
2 Google Brain
3 Energy-efficient multimedia systems group, MIT
4 Georgia Institute of Technology
CVPR 2018
1. Research Background
1. Research Background
Introduction
2/20
• What & Why - Automated architecture search
- Automating structure design in DNNs is an active research field that is gaining significance as DNNs become
more ubiquitous in a variety of applications and platforms.
• Previous works
- Sparsifying regularizers (pruning, L1 regularization on weight matrices, designed regularizers
They do not target reduction of a particular resource (e.g., the number of floating point operations, or FLOPs, per inference).
- Optimizing every aspect of network structure (from trial-and-error attemps – RL, evolutionary
algorithm)
but, this methods require months or years of GPU time
• Automatic neural network architecture design is currently effective only under limited
conditions and given knowledge of the right tool to use.
Authors propose a simple and general technique for resource-constrained optimization of DNN architectures.
1. Research Background 3/20
Three advantages :
• (1) it is scalable to large models and large datasets
• (2) it can optimize a DNN structure targeting a specific resource (FLOPs, model size).
• (3) it can learn a structures that improves performance while reducing the targeted resource usage.
MorphNet takes an existing neural network as input and produces a new
neural network that is smaller, faster, and yields better performance tailored
to a new problem.
Objective
2. Methods
2. Methods
Problem setup
5/20
• To optimize over the output widths of all layers
Seed network
Constraint (FLOPs, model size)
Output channels of layer L
a loss measuring a combination of how well the neural network fits the data
and any additional regularization terms
2. Methods
A cycle of shrinking and expanding phases
6/20
Step 1-2: Shrinking
Consuming resource ↓
Performance ↓
(Sparsifying regularizer)
Step 3 : Expansion
(width multiplier)
2. Methods
Two types of constraints
7/20
Model size constraint
FLOPs constraint
Input spatial dimensions : w,x
Output spatial dimensions : y, z
Filter dimensions : f, g
2. Methods
1) Shrinking phase - Sparsifying regularizer (pruning)
8/20
• When shrinking a network, we wish to minimize the loss of the DNN subject to a constraint.
L0 norm : Corresponds to the total number of nonzero elements in a vector.
It is necessary to replace the discontinuous L0 norm with a continuous proxy norm.
Differentiable almost everywhere!
"Batch normalization: Accelerating deep network training by reducing internal covariate shift." (2015).
2. Methods
2) Expanding phase - Width multiplier
9/20
• Uniformly expand all layer sizes
- "Mobilenets: Efficient convolutional neural networks for mobile vision applications." (2017).
- Application of a width multiplier is essentially free.
- The approach suffers, however, with decreased quality of the initial network design.
3. Experimental Results
3. Experimental Results
The effect of the regularizer on the actual FLOPs during training
11/20
• Inception V2 on ImageNet
Seed network : Inception V2
A learning rate of 10-3 (constant in time)
3. Experimental Results
Applying constraint with different strengths (different values of λ)
12/20
0.7×10-9
1.0×10-9
1.3×10-9
2.0×10-9
3.0×10-9
• The accuracy of the DNN can be improved while maintaining a constrained resource usage (FLOPs in
this case).
Seed network : Inception V2, trained on ImageNet
A learning rate of 10-3 (constant in time)
Baseline method : Naïve width multiplier
3. Experimental Results
Improvement the accuracy by shrink-expansion
13/20
λ=1.3×10-9
• Although the number of FLOPs is constant, our method is capable of and chooses to increase the
number of weights in the model.
3. Experimental Results
Improved Performance at No Cost
14/20
• Evaluation MAP (mean-average-precision) on various seeds and data.
* JTL dataset : 350M images and about 20K labels
* Two iteration
* AudioSet : 20M labelled audio segments
1) "CNN architectures for large-scale audio classification." 2017
1)
• Each result requires up to three training runs.
• The first training run is run until the convergence of the FLOPs cost, which is approximately 20 times
faster than the convergence of the performance metric (MAP).
3. Experimental Results
The regularizer methodically targets a particular resource
15/20
AudioResNet-AudioSet
ResNet 101-JFT
FLOP regularizer Size regularizer
• FLOP regularizer tends to remove neurons from the lower layers near the input,
whereas the model size regularizer tends to remove neurons from upper layers near the output.
3. Experimental Results
The regularizer methodically targets a particular resource
16/20
MAP : 0.405 MAP : 0.428 MAP : 0.421
3. Experimental Results
Morphing Networks
17/20
https://ai.googleblog.com/2019/04/morphnet-towards-faster-and-smaller.html
• MorphNet can remove residual connections in ResNet-style networks,
and parallel towers in Inception-style networks.
3. Experimental Results
The MorphNet is capable of generating pretty stable DNN architectures.
18/20
The relative standard deviation for FLOPs and test accuracy across 10 runs
are 1.12% and 0.208% respectively.
4. Conclusion
4. Conclusions 20/20
• Furthermore, we have applied MorphNet to large scale
problems to achieve improvements over human-designed
DNN structures, with little extra training cost compared to
training the DNN once.
Thank you.
• MorphNet can successfully navigate this tradeoff when
targeting either FLOPs or model size.
• As future work, the iterative process of shrinking and
expanding easily lends itself to optimizing over other aspects
(not width of layer output) of network design.

Weitere ähnliche Inhalte

Was ist angesagt?

Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...
Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...
Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...ijtsrd
 
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...InVID Project
 
Towards an objective comparison of feature extraction techniques for automati...
Towards an objective comparison of feature extraction techniques for automati...Towards an objective comparison of feature extraction techniques for automati...
Towards an objective comparison of feature extraction techniques for automati...journalBEEI
 
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...Lviv Data Science Summer School
 
Software effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN networkSoftware effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN networkIOSR Journals
 
PCA and Classification
PCA and ClassificationPCA and Classification
PCA and ClassificationFatwa Ramdani
 
In datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unitIn datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unitJinwon Lee
 
PR-197: One ticket to win them all: generalizing lottery ticket initializatio...
PR-197: One ticket to win them all: generalizing lottery ticket initializatio...PR-197: One ticket to win them all: generalizing lottery ticket initializatio...
PR-197: One ticket to win them all: generalizing lottery ticket initializatio...Jinwon Lee
 
Feature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component AnalysisFeature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component AnalysisIT Industry
 
Pelee: a real time object detection system on mobile devices Paper Review
Pelee: a real time object detection system on mobile devices Paper ReviewPelee: a real time object detection system on mobile devices Paper Review
Pelee: a real time object detection system on mobile devices Paper ReviewLEE HOSEONG
 
Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback  Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback dannyijwest
 
Using parallel hierarchical clustering to
Using parallel hierarchical clustering toUsing parallel hierarchical clustering to
Using parallel hierarchical clustering toBiniam Behailu
 
Computational Performance of Phase Field Calculations using a Matrix-Free (Su...
Computational Performance of Phase Field Calculations using a Matrix-Free (Su...Computational Performance of Phase Field Calculations using a Matrix-Free (Su...
Computational Performance of Phase Field Calculations using a Matrix-Free (Su...Stephen DeWitt
 
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksPR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksJinwon Lee
 
ICML 2017 Meta network
ICML 2017 Meta networkICML 2017 Meta network
ICML 2017 Meta networkKaty Lee
 
Algorithm selection for sorting in embedded and mobile systems
Algorithm selection for sorting in embedded and mobile systemsAlgorithm selection for sorting in embedded and mobile systems
Algorithm selection for sorting in embedded and mobile systemsJigisha Aryya
 
Multi Wavelet for Image Retrival Based On Using Texture and Color Querys
Multi Wavelet for Image Retrival Based On Using Texture and  Color QuerysMulti Wavelet for Image Retrival Based On Using Texture and  Color Querys
Multi Wavelet for Image Retrival Based On Using Texture and Color QuerysIOSR Journals
 
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AIT. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AIMLILAB
 
Green wsn optimization of energy use
Green wsn  optimization of energy useGreen wsn  optimization of energy use
Green wsn optimization of energy useijfcstjournal
 

Was ist angesagt? (20)

Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...
Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...
Acoustic Scene Classification by using Combination of MODWPT and Spectral Fea...
 
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
 
Towards an objective comparison of feature extraction techniques for automati...
Towards an objective comparison of feature extraction techniques for automati...Towards an objective comparison of feature extraction techniques for automati...
Towards an objective comparison of feature extraction techniques for automati...
 
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
Master defence 2020 -Volodymyr Lut-Neural Architecture Search: a Probabilisti...
 
Software effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN networkSoftware effort estimation through clustering techniques of RBFN network
Software effort estimation through clustering techniques of RBFN network
 
PCA and Classification
PCA and ClassificationPCA and Classification
PCA and Classification
 
In datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unitIn datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unit
 
Ieek fall Conference 2013
Ieek fall Conference 2013Ieek fall Conference 2013
Ieek fall Conference 2013
 
PR-197: One ticket to win them all: generalizing lottery ticket initializatio...
PR-197: One ticket to win them all: generalizing lottery ticket initializatio...PR-197: One ticket to win them all: generalizing lottery ticket initializatio...
PR-197: One ticket to win them all: generalizing lottery ticket initializatio...
 
Feature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component AnalysisFeature Based Image Classification by using Principal Component Analysis
Feature Based Image Classification by using Principal Component Analysis
 
Pelee: a real time object detection system on mobile devices Paper Review
Pelee: a real time object detection system on mobile devices Paper ReviewPelee: a real time object detection system on mobile devices Paper Review
Pelee: a real time object detection system on mobile devices Paper Review
 
Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback  Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback
 
Using parallel hierarchical clustering to
Using parallel hierarchical clustering toUsing parallel hierarchical clustering to
Using parallel hierarchical clustering to
 
Computational Performance of Phase Field Calculations using a Matrix-Free (Su...
Computational Performance of Phase Field Calculations using a Matrix-Free (Su...Computational Performance of Phase Field Calculations using a Matrix-Free (Su...
Computational Performance of Phase Field Calculations using a Matrix-Free (Su...
 
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksPR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
 
ICML 2017 Meta network
ICML 2017 Meta networkICML 2017 Meta network
ICML 2017 Meta network
 
Algorithm selection for sorting in embedded and mobile systems
Algorithm selection for sorting in embedded and mobile systemsAlgorithm selection for sorting in embedded and mobile systems
Algorithm selection for sorting in embedded and mobile systems
 
Multi Wavelet for Image Retrival Based On Using Texture and Color Querys
Multi Wavelet for Image Retrival Based On Using Texture and  Color QuerysMulti Wavelet for Image Retrival Based On Using Texture and  Color Querys
Multi Wavelet for Image Retrival Based On Using Texture and Color Querys
 
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AIT. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
 
Green wsn optimization of energy use
Green wsn  optimization of energy useGreen wsn  optimization of energy use
Green wsn optimization of energy use
 

Ähnlich wie PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013Pedro Lopes
 
Tutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdfTutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdfDuy-Hieu Bui
 
M3AT: Monitoring Agents Assignment Model for the Data-Intensive Applications
M3AT: Monitoring Agents Assignment Model for the Data-Intensive ApplicationsM3AT: Monitoring Agents Assignment Model for the Data-Intensive Applications
M3AT: Monitoring Agents Assignment Model for the Data-Intensive ApplicationsVladislavKashansky
 
Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...
Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...
Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...Luca Sinico
 
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...Virendra Uppalwar
 
Efficient de cvpr_2020_paper
Efficient de cvpr_2020_paperEfficient de cvpr_2020_paper
Efficient de cvpr_2020_papershanullah3
 
Wireless sensor networks, clustering, Energy efficient protocols, Particles S...
Wireless sensor networks, clustering, Energy efficient protocols, Particles S...Wireless sensor networks, clustering, Energy efficient protocols, Particles S...
Wireless sensor networks, clustering, Energy efficient protocols, Particles S...IJMIT JOURNAL
 
Implementation of energy efficient coverage aware routing protocol for wirele...
Implementation of energy efficient coverage aware routing protocol for wirele...Implementation of energy efficient coverage aware routing protocol for wirele...
Implementation of energy efficient coverage aware routing protocol for wirele...ijfcstjournal
 
WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...
WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...
WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...IJMIT JOURNAL
 
Neural Networks in Data Mining - “An Overview”
Neural Networks  in Data Mining -   “An Overview”Neural Networks  in Data Mining -   “An Overview”
Neural Networks in Data Mining - “An Overview”Dr.(Mrs).Gethsiyal Augasta
 
Beyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networksBeyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networksJunKudo2
 
Analytical Modeling of End-to-End Delay in OpenFlow Based Networks
Analytical Modeling of End-to-End Delay in OpenFlow Based NetworksAnalytical Modeling of End-to-End Delay in OpenFlow Based Networks
Analytical Modeling of End-to-End Delay in OpenFlow Based NetworksAzeem Iqbal
 
Kickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.io
Kickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.ioKickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.io
Kickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.ioHostedbyConfluent
 
Clustering-based Analysis for Heavy-Hitter Flow Detection
Clustering-based Analysis for Heavy-Hitter Flow DetectionClustering-based Analysis for Heavy-Hitter Flow Detection
Clustering-based Analysis for Heavy-Hitter Flow DetectionAPNIC
 
Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...
Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...
Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...Łukasz Król
 
Policy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detectionPolicy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detectionKishor Datta Gupta
 
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
AI optimizing HPC simulations (presentation from  6th EULAG Workshop)AI optimizing HPC simulations (presentation from  6th EULAG Workshop)
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)byteLAKE
 

Ähnlich wie PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks (20)

Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013
 
Tutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdfTutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdf
 
M3AT: Monitoring Agents Assignment Model for the Data-Intensive Applications
M3AT: Monitoring Agents Assignment Model for the Data-Intensive ApplicationsM3AT: Monitoring Agents Assignment Model for the Data-Intensive Applications
M3AT: Monitoring Agents Assignment Model for the Data-Intensive Applications
 
Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...
Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...
Review of the paper: Traffic-aware Frequency Scaling for Balanced On-Chip Net...
 
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
“Design of Efficient Mobile Femtocell by Compression and Aggregation Technolo...
 
Efficient de cvpr_2020_paper
Efficient de cvpr_2020_paperEfficient de cvpr_2020_paper
Efficient de cvpr_2020_paper
 
Wireless sensor networks, clustering, Energy efficient protocols, Particles S...
Wireless sensor networks, clustering, Energy efficient protocols, Particles S...Wireless sensor networks, clustering, Energy efficient protocols, Particles S...
Wireless sensor networks, clustering, Energy efficient protocols, Particles S...
 
Implementation of energy efficient coverage aware routing protocol for wirele...
Implementation of energy efficient coverage aware routing protocol for wirele...Implementation of energy efficient coverage aware routing protocol for wirele...
Implementation of energy efficient coverage aware routing protocol for wirele...
 
WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...
WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...
WIRELESS SENSOR NETWORK CLUSTERING USING PARTICLES SWARM OPTIMIZATION FOR RED...
 
Neural Networks in Data Mining - “An Overview”
Neural Networks  in Data Mining -   “An Overview”Neural Networks  in Data Mining -   “An Overview”
Neural Networks in Data Mining - “An Overview”
 
Beyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networksBeyond data and model parallelism for deep neural networks
Beyond data and model parallelism for deep neural networks
 
Analytical Modeling of End-to-End Delay in OpenFlow Based Networks
Analytical Modeling of End-to-End Delay in OpenFlow Based NetworksAnalytical Modeling of End-to-End Delay in OpenFlow Based Networks
Analytical Modeling of End-to-End Delay in OpenFlow Based Networks
 
Kickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.io
Kickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.ioKickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.io
Kickstart your Kafka with Faker Data | Francesco Tisiot, Aiven.io
 
CNN Dataflow implementation on FPGAs
CNN Dataflow implementation on FPGAsCNN Dataflow implementation on FPGAs
CNN Dataflow implementation on FPGAs
 
Clustering-based Analysis for Heavy-Hitter Flow Detection
Clustering-based Analysis for Heavy-Hitter Flow DetectionClustering-based Analysis for Heavy-Hitter Flow Detection
Clustering-based Analysis for Heavy-Hitter Flow Detection
 
Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...
Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...
Distributed Monte Carlo Feature Selection: Extracting Informative Features Ou...
 
FrackingPaper
FrackingPaperFrackingPaper
FrackingPaper
 
Policy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detectionPolicy Based reinforcement Learning for time series Anomaly detection
Policy Based reinforcement Learning for time series Anomaly detection
 
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
AI optimizing HPC simulations (presentation from  6th EULAG Workshop)AI optimizing HPC simulations (presentation from  6th EULAG Workshop)
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
 

Mehr von Sunghoon Joo

PR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But FasterPR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But FasterSunghoon Joo
 
PR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked AutoencodersPR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked AutoencodersSunghoon Joo
 
PR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdfPR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdfSunghoon Joo
 
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...Sunghoon Joo
 
PR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed RecognitionPR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed RecognitionSunghoon Joo
 
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...Sunghoon Joo
 
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.Sunghoon Joo
 
PR-351: Adaptive Aggregation Networks for Class-Incremental Learning
PR-351: Adaptive Aggregation Networks for Class-Incremental LearningPR-351: Adaptive Aggregation Networks for Class-Incremental Learning
PR-351: Adaptive Aggregation Networks for Class-Incremental LearningSunghoon Joo
 
PR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learningPR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learningSunghoon Joo
 
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...Sunghoon Joo
 
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...Sunghoon Joo
 
PR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document rerankingPR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document rerankingSunghoon Joo
 
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...Sunghoon Joo
 
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector QuantizationPR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector QuantizationSunghoon Joo
 
PR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseasesPR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseasesSunghoon Joo
 
PR-232: AutoML-Zero:Evolving Machine Learning Algorithms From Scratch
PR-232:  AutoML-Zero:Evolving Machine Learning Algorithms From ScratchPR-232:  AutoML-Zero:Evolving Machine Learning Algorithms From Scratch
PR-232: AutoML-Zero:Evolving Machine Learning Algorithms From ScratchSunghoon Joo
 
PR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture SearchPR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture SearchSunghoon Joo
 
PR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesPR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesSunghoon Joo
 
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...Sunghoon Joo
 
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...Sunghoon Joo
 

Mehr von Sunghoon Joo (20)

PR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But FasterPR-445: Token Merging: Your ViT But Faster
PR-445: Token Merging: Your ViT But Faster
 
PR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked AutoencodersPR-433: Test-time Training with Masked Autoencoders
PR-433: Test-time Training with Masked Autoencoders
 
PR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdfPR422_hyper-deep ensembles.pdf
PR422_hyper-deep ensembles.pdf
 
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
PR-411: Model soups: averaging weights of multiple fine-tuned models improves...
 
PR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed RecognitionPR-393: ResLT: Residual Learning for Long-tailed Recognition
PR-393: ResLT: Residual Learning for Long-tailed Recognition
 
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
PR-383: Solving ImageNet: a Unified Scheme for Training any Backbone to Top R...
 
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
PR-373: Revisiting ResNets: Improved Training and Scaling Strategies.
 
PR-351: Adaptive Aggregation Networks for Class-Incremental Learning
PR-351: Adaptive Aggregation Networks for Class-Incremental LearningPR-351: Adaptive Aggregation Networks for Class-Incremental Learning
PR-351: Adaptive Aggregation Networks for Class-Incremental Learning
 
PR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learningPR-339: Maintaining discrimination and fairness in class incremental learning
PR-339: Maintaining discrimination and fairness in class incremental learning
 
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
 
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
PR-313 Training BatchNorm and Only BatchNorm: On the Expressive Power of Rand...
 
PR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document rerankingPR-298 PARADE: Passage representation aggregation for document reranking
PR-298 PARADE: Passage representation aggregation for document reranking
 
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
PR-285 Leveraging Semantic and Lexical Matching to Improve the Recall of Docu...
 
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector QuantizationPR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
PR-272: Accelerating Large-Scale Inference with Anisotropic Vector Quantization
 
PR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseasesPR-246: A deep learning system for differential diagnosis of skin diseases
PR-246: A deep learning system for differential diagnosis of skin diseases
 
PR-232: AutoML-Zero:Evolving Machine Learning Algorithms From Scratch
PR-232:  AutoML-Zero:Evolving Machine Learning Algorithms From ScratchPR-232:  AutoML-Zero:Evolving Machine Learning Algorithms From Scratch
PR-232: AutoML-Zero:Evolving Machine Learning Algorithms From Scratch
 
PR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture SearchPR-218: MFAS: Multimodal Fusion Architecture Search
PR-218: MFAS: Multimodal Fusion Architecture Search
 
PR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesPR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of Samples
 
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
PR173 : Automatic Chemical Design Using a Data-Driven Continuous Representati...
 
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
PR-159 : Synergistic Image and Feature Adaptation: Towards Cross-Modality Dom...
 

Kürzlich hochgeladen

Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Call Girls in Nagpur High Profile
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escortsranjana rawat
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduitsrknatarajan
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations120cr0395
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...ranjana rawat
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130Suhani Kapoor
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...Soham Mondal
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSSIVASHANKAR N
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSKurinjimalarL3
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...ranjana rawat
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performancesivaprakash250
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college projectTonystark477637
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)simmis5
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxAsutosh Ranjan
 

Kürzlich hochgeladen (20)

Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINEDJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college project
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
 

PR-187 : MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

  • 1. MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks 주성훈, 삼성SDS AI선행연구Lab. 2019. 8. 11. PR-187 Ariel Gordon1, Elad Eban1, Ofir Nachum2, Bo Chen1, Hao Wu1, Tien-Ju Yang1,3, and Edward Choi1,4 1 Google Research 2 Google Brain 3 Energy-efficient multimedia systems group, MIT 4 Georgia Institute of Technology CVPR 2018
  • 3. 1. Research Background Introduction 2/20 • What & Why - Automated architecture search - Automating structure design in DNNs is an active research field that is gaining significance as DNNs become more ubiquitous in a variety of applications and platforms. • Previous works - Sparsifying regularizers (pruning, L1 regularization on weight matrices, designed regularizers They do not target reduction of a particular resource (e.g., the number of floating point operations, or FLOPs, per inference). - Optimizing every aspect of network structure (from trial-and-error attemps – RL, evolutionary algorithm) but, this methods require months or years of GPU time • Automatic neural network architecture design is currently effective only under limited conditions and given knowledge of the right tool to use. Authors propose a simple and general technique for resource-constrained optimization of DNN architectures.
  • 4. 1. Research Background 3/20 Three advantages : • (1) it is scalable to large models and large datasets • (2) it can optimize a DNN structure targeting a specific resource (FLOPs, model size). • (3) it can learn a structures that improves performance while reducing the targeted resource usage. MorphNet takes an existing neural network as input and produces a new neural network that is smaller, faster, and yields better performance tailored to a new problem. Objective
  • 6. 2. Methods Problem setup 5/20 • To optimize over the output widths of all layers Seed network Constraint (FLOPs, model size) Output channels of layer L a loss measuring a combination of how well the neural network fits the data and any additional regularization terms
  • 7. 2. Methods A cycle of shrinking and expanding phases 6/20 Step 1-2: Shrinking Consuming resource ↓ Performance ↓ (Sparsifying regularizer) Step 3 : Expansion (width multiplier)
  • 8. 2. Methods Two types of constraints 7/20 Model size constraint FLOPs constraint Input spatial dimensions : w,x Output spatial dimensions : y, z Filter dimensions : f, g
  • 9. 2. Methods 1) Shrinking phase - Sparsifying regularizer (pruning) 8/20 • When shrinking a network, we wish to minimize the loss of the DNN subject to a constraint. L0 norm : Corresponds to the total number of nonzero elements in a vector. It is necessary to replace the discontinuous L0 norm with a continuous proxy norm. Differentiable almost everywhere! "Batch normalization: Accelerating deep network training by reducing internal covariate shift." (2015).
  • 10. 2. Methods 2) Expanding phase - Width multiplier 9/20 • Uniformly expand all layer sizes - "Mobilenets: Efficient convolutional neural networks for mobile vision applications." (2017). - Application of a width multiplier is essentially free. - The approach suffers, however, with decreased quality of the initial network design.
  • 12. 3. Experimental Results The effect of the regularizer on the actual FLOPs during training 11/20 • Inception V2 on ImageNet Seed network : Inception V2 A learning rate of 10-3 (constant in time)
  • 13. 3. Experimental Results Applying constraint with different strengths (different values of λ) 12/20 0.7×10-9 1.0×10-9 1.3×10-9 2.0×10-9 3.0×10-9 • The accuracy of the DNN can be improved while maintaining a constrained resource usage (FLOPs in this case). Seed network : Inception V2, trained on ImageNet A learning rate of 10-3 (constant in time) Baseline method : Naïve width multiplier
  • 14. 3. Experimental Results Improvement the accuracy by shrink-expansion 13/20 λ=1.3×10-9 • Although the number of FLOPs is constant, our method is capable of and chooses to increase the number of weights in the model.
  • 15. 3. Experimental Results Improved Performance at No Cost 14/20 • Evaluation MAP (mean-average-precision) on various seeds and data. * JTL dataset : 350M images and about 20K labels * Two iteration * AudioSet : 20M labelled audio segments 1) "CNN architectures for large-scale audio classification." 2017 1) • Each result requires up to three training runs. • The first training run is run until the convergence of the FLOPs cost, which is approximately 20 times faster than the convergence of the performance metric (MAP).
  • 16. 3. Experimental Results The regularizer methodically targets a particular resource 15/20 AudioResNet-AudioSet ResNet 101-JFT FLOP regularizer Size regularizer
  • 17. • FLOP regularizer tends to remove neurons from the lower layers near the input, whereas the model size regularizer tends to remove neurons from upper layers near the output. 3. Experimental Results The regularizer methodically targets a particular resource 16/20 MAP : 0.405 MAP : 0.428 MAP : 0.421
  • 18. 3. Experimental Results Morphing Networks 17/20 https://ai.googleblog.com/2019/04/morphnet-towards-faster-and-smaller.html • MorphNet can remove residual connections in ResNet-style networks, and parallel towers in Inception-style networks.
  • 19. 3. Experimental Results The MorphNet is capable of generating pretty stable DNN architectures. 18/20 The relative standard deviation for FLOPs and test accuracy across 10 runs are 1.12% and 0.208% respectively.
  • 21. 4. Conclusions 20/20 • Furthermore, we have applied MorphNet to large scale problems to achieve improvements over human-designed DNN structures, with little extra training cost compared to training the DNN once. Thank you. • MorphNet can successfully navigate this tradeoff when targeting either FLOPs or model size. • As future work, the iterative process of shrinking and expanding easily lends itself to optimizing over other aspects (not width of layer output) of network design.