SlideShare a Scribd company logo
1 of 32
Download to read offline
COMPARING INCREMENTAL LEARNING STRATEGIES
FOR
CONVOLUTIONAL NEURAL NETWORKS
Vincenzo Lomonaco & Davide Maltoni
{vincenzo.lomonaco, davide.maltoni}@unibo.it
Department of Computer Science and Engineering – DISI
University of Bologna
OUTLINE
1. Introduction
• CNNs and current limitations
• Incremental learning: Why?
2. Incremental learning Strategies
for CNNs
• Definitions
• Possible instantiations used during
the experimentations
3. Datasets
• iCubWorld28
• BigBrother
4. Experiments and Results
• Exp. design
• Results analysis
5. Conclusions and Future Works
OUTLINE
1. Introduction
• CNNs and current limitations
• Incremental learning: Why?
2. Incremental learning Strategies
for CNNs
• Definitions
• Possible instantiations used during
the experimentations
3. Datasets
• iCubWorld28
• BigBrother
4. Experiments and Results
• Exp. design
• Results analysis
5. Conclusions and Future Works
INTRODUCTION – CNNs and Current Limitations
State-of-the-art algorithm for many
tasks in CV, NLP, SR, etc..
Very general and adaptive
Works directy on raw data (no
hand-engineered features required)
Computational demanding
Tricky hyper-parametrization
Applicability in Incremental
Learning Scenario?
INTRODUCTION – Incremental learnig: Why?
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .
Initial Batch Incremental Batches

INTRODUCTION – Incremental learnig: Why?
Constraints:
• Memory: We can’t afford to keep in memory all the batches.
• Computational power: We can’t afford to train our classification model from
scratch after each batch.
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .

Initial Batch Incremental Batches
INTRODUCTION – Incremental learnig: Why?
Goal:
• Maximize the Accuracy % after each batch
• Going towards a more smooth and natural learning but still using CNNs
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .

Initial Batch Incremental Batches
INTRODUCTION – Incremental learnig: Why?
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .
𝑀0
INTRODUCTION – Incremental learnig: Why?
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .
𝑀0
𝑀1
• We can free the memory
occupied by 𝐵𝑎𝑡𝑐ℎ0 and
get 𝑀1 just by updating
𝑀0 with the new coming
batch
• However, we risk to forget
what we’ve previously
learned
INTRODUCTION – Incremental learnig: Why?
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .
𝑀0
𝑀1
INTRODUCTION – Incremental learnig: Why?
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .
𝑀0
𝑀1
INTRODUCTION – Incremental learnig: Why?
𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛
. . .
𝑀0
𝑀1
. . . 𝑀 𝑛
OUTLINE
1. Introduction
• CNNs and current limitations
• Incremental learning: Why?
2. Incremental learning Strategies
for CNNs
• Definitions
• Possible instantiations used during
the experimentations
3. Datasets
• iCubWorld28
• BigBrother
4. Experiments and Results
• Exp. design
• Results analysis
5. Conclusions and Future Works
INC. LEARNING STRATEGIES FOR CNNS - Definitions
The different possibilities we explored to deal with an incremental
tuning/learning scenario, can be conveniently framed in three main strategies:
1. Training/tuning an ad hoc CNN architecture suitable for the problem.
2. Using an already trained CNN as a fixed feature extractor in conjunction with
an incremental classifier.
3. Fine-tuning an already trained CNN.
INC. LEARNING STRATEGIES FOR CNNS - Instantiations
In our experiments (with focus on image classification) we tested three instantiations of the
aforementioned strategies, respectively:
1. (Ad-hoc arch.)  LeNet7
Consists of the classical “LeNet7” proposed by Yan LeCun in 2004. Still competitive on low/medium
scale problems.
2. (CNN-fixed w. inc. Classifier)  CaffeNet + SVM
Consists of a pre-trained CNN provided in the Caffe library (“BVLC Reference CaffeNet”, based on
the “AlexNet” architecture; An incremental and linear SVM as Classifier.
3. (CNN-Finetuning)  CaffeNet + FT
Consists again of the “BVLC Reference CaffeNet” but instead of using it as a fixed feature extractor the
network is fine-tuned to suit the new task.
INC. LEARNING STRATEGIES FOR CNNS - Instantiations
Furthermore, for the “BigBrother” dataset we decided to test an additional pair of strategies:
4. (CNN-fixed w. inc. Classifier)  VGG_Face + SVM
Consists of a pre-trained (16-levels) CNN called “VGG Face” which has been trained on a very large
dataset of faces (2,622 Subjects and 2.6M images); Again, a incremental and linear SVM as Classifier.
5. (CNN-Finetuning)  VGG_Face + FT
Consists again of the “VGG_Face” CNN but instead of using it as a fixed feature extractor the network
is fine-tuned to suit the new task.
OUTLINE
1. Introduction
• CNNs and current limitations
• Incremental learning: Why?
2. Incremental Learning Strategies
for CNNs
• Definitions
• Possible instantiations used during
the experimentations
3. Datasets
• iCubWorld28
• BigBrother
4. Experiments and Results
• Exp. design
• Results analysis
5. Conclusions and Future Works
DATASETS
We were interested in datasets where:
• The objects of interest have been acquired in a number of successive sessions
• The environmental condition can change among the sessions.
We focused on two applicative fields where incremental learning is very relevant
(robotics and biometrics) and chose two datasets respectively:
• iCubWorld28
• BigBrother
DATASETS – iCubWorld28
Key Features:
• Img size: 128×128
• Num. classes: 7 (× 4 obj)
• Tot. imgs: 39,693
• Num batches: 9 +1 (test)
DATASETS – BigBrother
Key Features:
• Img size: 70×70
• Num. classes: 7
• Tot. imgs: 23,842
• Num batches: 56 +1 (test)
OUTLINE
1. Introduction
• CNNs and current limitations
• Incremental learning: Why?
2. Incremental Learning Strategies
for CNNs
• Definitions
• Possible instantiations used during
the experimentations
3. Datasets
• iCubWorld28
• BigBrother
4. Experiments and Results
• Exp. design
• Results analysis
5. Conclusions and Future Works
EXPERIMENTS AND RESULTS – Exp. Design
Experiments Policy:
• We trained the models until full convergence on the first batch of data
• We tuned them on the successive incremental batches, trying to balance the trade-off
between accuracy gain and forgetting.
EXPERIMENTS AND RESULTS – iCubWorld28 Results
EXPERIMENTS AND RESULTS – iCubWorld28 Results
• CaffeNet + SVM has a very
good recognition rate
increment
• CaffeNet + FT is the most
effective
• LeNet7 struggles to learn
complex invariant features
necessary for this problem
EXPERIMENTS AND RESULTS – BigBrother Results
EXPERIMENTS AND RESULTS – BigBrother Results
• LeNet7 model performs
slightly better than CaffeNet
+ SVM or CaffeNet + FT
• VGG_Face + SVM and
VGG_Face + FT have
impressive performance on
this problem
• VGG_Face + SVM seems to
be the best choice both for
the accuracy and the
stability
EXPERIMENTS AND RESULTS – Dealing with Forgetting
EXPERIMENTS AND RESULTS – Dealing with Forgetting
• An adjustable learning
rate is significantly more
stable
• A simple thresholding
approach has been used.
• We did not found any
significant difference using
a continuous approach
OUTLINE
1. Introduction
• CNNs and current limitations
• Incremental learning: Why?
2. Incremental Learning Strategies
for CNNs
• Definitions
• Possible instantiations used during
the experimentations
3. Datasets
• iCubWorld28
• BigBrother
4. Experiments and Results
• Exp. design
• Results analysis
5. Conclusions and Future Works
CONCLUSIONS AND FUTURE WORKS
• When possible (i.e., transfer learning from the same domain), it is preferable to use
CNN as a fixed feature extractor to feed an incremental classifier
• If the features are not optimized, the tuning of low level layers may be preferable
and the learning strength can be used to control forgetting.
• Training a CNN from scratch can be advantageous if the problem patterns (and
feature invariances) are highly specific and a sufficient number of samples are
available.
CONCLUSIONS AND FUTURE WORKS
In the near future we plan to extend this work by:
• Performing a more extensive experimental evaluation
• Finding a more principled way to control forgetting and adapting the tuning
parameters to the size (and bias) of each incremental batch.
• Studying real-world applications of semi-supervised incremental learning strategies
for CNNs.
COMPARING INCREMENTAL LEARNING STRATEGIES FOR
CONVOLUTIONAL NEURAL NETWORKS
Vincenzo Lomonaco & Davide Maltoni
{vincenzo.lomonaco, davide.maltoni}@unibo.it
Department of Computer Science and Engineering – DISI
University of Bologna
Thank you for your attention.
Any Questions?

More Related Content

What's hot

Continual learning: Survey
Continual learning: SurveyContinual learning: Survey
Continual learning: SurveyWonjun Jeong
 
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...Universitat Politècnica de Catalunya
 
Overcoming catastrophic forgetting in neural network
Overcoming catastrophic forgetting in neural networkOvercoming catastrophic forgetting in neural network
Overcoming catastrophic forgetting in neural networkKaty Lee
 
Few shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningFew shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningﺁﺻﻒ ﻋﻠﯽ ﻣﯿﺮ
 
The Deep Learning Glossary
The Deep Learning GlossaryThe Deep Learning Glossary
The Deep Learning GlossaryNVIDIA
 
Machine Learning Ml Overview Algorithms Use Cases And Applications
Machine Learning Ml Overview Algorithms Use Cases And ApplicationsMachine Learning Ml Overview Algorithms Use Cases And Applications
Machine Learning Ml Overview Algorithms Use Cases And ApplicationsSlideTeam
 
Representational Continuity for Unsupervised Continual Learning
Representational Continuity for Unsupervised Continual LearningRepresentational Continuity for Unsupervised Continual Learning
Representational Continuity for Unsupervised Continual LearningMLAI2
 
[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse Samples
[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse Samples[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse Samples
[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse SamplesJihwan Bang
 
Knn Algorithm presentation
Knn Algorithm presentationKnn Algorithm presentation
Knn Algorithm presentationRishavSharma112
 
Transfer Learning -- The Next Frontier for Machine Learning
Transfer Learning -- The Next Frontier for Machine LearningTransfer Learning -- The Next Frontier for Machine Learning
Transfer Learning -- The Next Frontier for Machine LearningSebastian Ruder
 
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...Sri Ambati
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
Online Coreset Selection for Rehearsal-based Continual Learning
Online Coreset Selection for Rehearsal-based Continual LearningOnline Coreset Selection for Rehearsal-based Continual Learning
Online Coreset Selection for Rehearsal-based Continual LearningMLAI2
 
Machine learning with scikitlearn
Machine learning with scikitlearnMachine learning with scikitlearn
Machine learning with scikitlearnPratap Dangeti
 
Smart Data Slides: Machine Learning - Case Studies
Smart Data Slides: Machine Learning - Case StudiesSmart Data Slides: Machine Learning - Case Studies
Smart Data Slides: Machine Learning - Case StudiesDATAVERSITY
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningEng Teong Cheah
 
Zero shot-learning: paper presentation
Zero shot-learning: paper presentationZero shot-learning: paper presentation
Zero shot-learning: paper presentationJérémie Kalfon
 

What's hot (20)

Continual learning: Survey
Continual learning: SurveyContinual learning: Survey
Continual learning: Survey
 
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
Life-long / Incremental Learning (DLAI D6L1 2017 UPC Deep Learning for Artifi...
 
Overcoming catastrophic forgetting in neural network
Overcoming catastrophic forgetting in neural networkOvercoming catastrophic forgetting in neural network
Overcoming catastrophic forgetting in neural network
 
Few shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningFew shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learning
 
The Deep Learning Glossary
The Deep Learning GlossaryThe Deep Learning Glossary
The Deep Learning Glossary
 
Machine Learning Ml Overview Algorithms Use Cases And Applications
Machine Learning Ml Overview Algorithms Use Cases And ApplicationsMachine Learning Ml Overview Algorithms Use Cases And Applications
Machine Learning Ml Overview Algorithms Use Cases And Applications
 
Representational Continuity for Unsupervised Continual Learning
Representational Continuity for Unsupervised Continual LearningRepresentational Continuity for Unsupervised Continual Learning
Representational Continuity for Unsupervised Continual Learning
 
[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse Samples
[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse Samples[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse Samples
[CVPR2021] Rainbow Memory: Continual Learning with a Memory of Diverse Samples
 
Knn Algorithm presentation
Knn Algorithm presentationKnn Algorithm presentation
Knn Algorithm presentation
 
Transfer Learning -- The Next Frontier for Machine Learning
Transfer Learning -- The Next Frontier for Machine LearningTransfer Learning -- The Next Frontier for Machine Learning
Transfer Learning -- The Next Frontier for Machine Learning
 
LSTM Tutorial
LSTM TutorialLSTM Tutorial
LSTM Tutorial
 
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
Interpretable Machine Learning Using LIME Framework - Kasia Kulma (PhD), Data...
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
 
Online Coreset Selection for Rehearsal-based Continual Learning
Online Coreset Selection for Rehearsal-based Continual LearningOnline Coreset Selection for Rehearsal-based Continual Learning
Online Coreset Selection for Rehearsal-based Continual Learning
 
K Nearest Neighbor Algorithm
K Nearest Neighbor AlgorithmK Nearest Neighbor Algorithm
K Nearest Neighbor Algorithm
 
Machine learning with scikitlearn
Machine learning with scikitlearnMachine learning with scikitlearn
Machine learning with scikitlearn
 
Smart Data Slides: Machine Learning - Case Studies
Smart Data Slides: Machine Learning - Case StudiesSmart Data Slides: Machine Learning - Case Studies
Smart Data Slides: Machine Learning - Case Studies
 
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Zero shot-learning: paper presentation
Zero shot-learning: paper presentationZero shot-learning: paper presentation
Zero shot-learning: paper presentation
 

Similar to Comparing Incremental Learning Strategies for Convolutional Neural Networks

Large Scale GAN Training for High Fidelity Natural Image Synthesis
Large Scale GAN Training for High Fidelity Natural Image SynthesisLarge Scale GAN Training for High Fidelity Natural Image Synthesis
Large Scale GAN Training for High Fidelity Natural Image SynthesisSeunghyun Hwang
 
Centertrack and naver airush 2020 review
Centertrack and naver airush 2020 reviewCentertrack and naver airush 2020 review
Centertrack and naver airush 2020 review경훈 김
 
Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...
Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...
Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...Aalto University
 
Deep Learning for Natural Language Processing
Deep Learning for Natural Language ProcessingDeep Learning for Natural Language Processing
Deep Learning for Natural Language ProcessingSangwoo Mo
 
ResNeSt: Split-Attention Networks
ResNeSt: Split-Attention NetworksResNeSt: Split-Attention Networks
ResNeSt: Split-Attention NetworksSeunghyun Hwang
 
Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Fernando Constantino
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.bhavinecindus
 
Experimental Design for Distributed Machine Learning with Myles Baker
Experimental Design for Distributed Machine Learning with Myles BakerExperimental Design for Distributed Machine Learning with Myles Baker
Experimental Design for Distributed Machine Learning with Myles BakerDatabricks
 
Advanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise WebinarAdvanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise WebinarSigOpt
 
Using SigOpt to Tune Deep Learning Models with Nervana Cloud
Using SigOpt to Tune Deep Learning Models with Nervana CloudUsing SigOpt to Tune Deep Learning Models with Nervana Cloud
Using SigOpt to Tune Deep Learning Models with Nervana CloudSigOpt
 
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning SystemsXavier Amatriain
 
Deep learning summary
Deep learning summaryDeep learning summary
Deep learning summaryankit_ppt
 
Bag of tricks for image classification with convolutional neural networks r...
Bag of tricks for image classification with convolutional neural networks   r...Bag of tricks for image classification with convolutional neural networks   r...
Bag of tricks for image classification with convolutional neural networks r...Dongmin Choi
 
Revisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software TestingRevisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software TestingLionel Briand
 
a deep reinforced model for abstractive summarization
a deep reinforced model for abstractive summarizationa deep reinforced model for abstractive summarization
a deep reinforced model for abstractive summarizationJEE HYUN PARK
 
Benchmarking Automated Machine Learning For Clustering
Benchmarking Automated Machine Learning For ClusteringBenchmarking Automated Machine Learning For Clustering
Benchmarking Automated Machine Learning For Clusteringbiagiolicari7
 
Discovering the New SuccessFactors LMS Admin Features
Discovering the New SuccessFactors LMS Admin FeaturesDiscovering the New SuccessFactors LMS Admin Features
Discovering the New SuccessFactors LMS Admin FeaturesAshton Plusquellec
 
Presentation of master thesis
Presentation of master thesisPresentation of master thesis
Presentation of master thesisSeoung-Ho Choi
 

Similar to Comparing Incremental Learning Strategies for Convolutional Neural Networks (20)

Large Scale GAN Training for High Fidelity Natural Image Synthesis
Large Scale GAN Training for High Fidelity Natural Image SynthesisLarge Scale GAN Training for High Fidelity Natural Image Synthesis
Large Scale GAN Training for High Fidelity Natural Image Synthesis
 
Centertrack and naver airush 2020 review
Centertrack and naver airush 2020 reviewCentertrack and naver airush 2020 review
Centertrack and naver airush 2020 review
 
Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...
Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...
Model-Based User Interface Optimization: Part IV: ADVANCED TOPICS - At SICSA ...
 
Deep Learning for Natural Language Processing
Deep Learning for Natural Language ProcessingDeep Learning for Natural Language Processing
Deep Learning for Natural Language Processing
 
nnUNet
nnUNetnnUNet
nnUNet
 
ResNeSt: Split-Attention Networks
ResNeSt: Split-Attention NetworksResNeSt: Split-Attention Networks
ResNeSt: Split-Attention Networks
 
Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.Transfer Learning: Breve introducción a modelos pre-entrenados.
Transfer Learning: Breve introducción a modelos pre-entrenados.
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.
 
Experimental Design for Distributed Machine Learning with Myles Baker
Experimental Design for Distributed Machine Learning with Myles BakerExperimental Design for Distributed Machine Learning with Myles Baker
Experimental Design for Distributed Machine Learning with Myles Baker
 
Advanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise WebinarAdvanced Optimization for the Enterprise Webinar
Advanced Optimization for the Enterprise Webinar
 
Using SigOpt to Tune Deep Learning Models with Nervana Cloud
Using SigOpt to Tune Deep Learning Models with Nervana CloudUsing SigOpt to Tune Deep Learning Models with Nervana Cloud
Using SigOpt to Tune Deep Learning Models with Nervana Cloud
 
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
 
Spoofing-aware Attention Back-end with Multiple Enrollment and Novel Trials S...
Spoofing-aware Attention Back-end with Multiple Enrollment and Novel Trials S...Spoofing-aware Attention Back-end with Multiple Enrollment and Novel Trials S...
Spoofing-aware Attention Back-end with Multiple Enrollment and Novel Trials S...
 
Deep learning summary
Deep learning summaryDeep learning summary
Deep learning summary
 
Bag of tricks for image classification with convolutional neural networks r...
Bag of tricks for image classification with convolutional neural networks   r...Bag of tricks for image classification with convolutional neural networks   r...
Bag of tricks for image classification with convolutional neural networks r...
 
Revisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software TestingRevisiting the Notion of Diversity in Software Testing
Revisiting the Notion of Diversity in Software Testing
 
a deep reinforced model for abstractive summarization
a deep reinforced model for abstractive summarizationa deep reinforced model for abstractive summarization
a deep reinforced model for abstractive summarization
 
Benchmarking Automated Machine Learning For Clustering
Benchmarking Automated Machine Learning For ClusteringBenchmarking Automated Machine Learning For Clustering
Benchmarking Automated Machine Learning For Clustering
 
Discovering the New SuccessFactors LMS Admin Features
Discovering the New SuccessFactors LMS Admin FeaturesDiscovering the New SuccessFactors LMS Admin Features
Discovering the New SuccessFactors LMS Admin Features
 
Presentation of master thesis
Presentation of master thesisPresentation of master thesis
Presentation of master thesis
 

More from Vincenzo Lomonaco

2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdfVincenzo Lomonaco
 
Toward Continual Learning on the Edge
Toward Continual Learning on the EdgeToward Continual Learning on the Edge
Toward Continual Learning on the EdgeVincenzo Lomonaco
 
Continual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent MachinesContinual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent MachinesVincenzo Lomonaco
 
Continual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary EnvironmentsContinual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary EnvironmentsVincenzo Lomonaco
 
Continual Learning for Robotics
Continual Learning for RoboticsContinual Learning for Robotics
Continual Learning for RoboticsVincenzo Lomonaco
 
Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...Vincenzo Lomonaco
 
Open-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an OverviewOpen-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an OverviewVincenzo Lomonaco
 
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...Vincenzo Lomonaco
 
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...Vincenzo Lomonaco
 
Continuous Learning with Deep Architectures
Continuous Learning with Deep ArchitecturesContinuous Learning with Deep Architectures
Continuous Learning with Deep ArchitecturesVincenzo Lomonaco
 
CORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition PosterCORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition PosterVincenzo Lomonaco
 
Continuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep ArchitecturesContinuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep ArchitecturesVincenzo Lomonaco
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Vincenzo Lomonaco
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Vincenzo Lomonaco
 
A Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in JavaA Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in JavaVincenzo Lomonaco
 
Deep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with TheanoDeep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with TheanoVincenzo Lomonaco
 
Word2vec on the italian language: first experiments
Word2vec on the italian language: first experimentsWord2vec on the italian language: first experiments
Word2vec on the italian language: first experimentsVincenzo Lomonaco
 
Machine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An OverviewMachine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An OverviewVincenzo Lomonaco
 

More from Vincenzo Lomonaco (19)

2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
2023-08-22 CoLLAs Tutorial - Beyond CIL.pdf
 
Toward Continual Learning on the Edge
Toward Continual Learning on the EdgeToward Continual Learning on the Edge
Toward Continual Learning on the Edge
 
Continual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent MachinesContinual Learning: Another Step Towards Truly Intelligent Machines
Continual Learning: Another Step Towards Truly Intelligent Machines
 
Tutorial inns2019 full
Tutorial inns2019 fullTutorial inns2019 full
Tutorial inns2019 full
 
Continual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary EnvironmentsContinual Reinforcement Learning in 3D Non-stationary Environments
Continual Reinforcement Learning in 3D Non-stationary Environments
 
Continual Learning for Robotics
Continual Learning for RoboticsContinual Learning for Robotics
Continual Learning for Robotics
 
Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...Don't forget, there is more than forgetting: new metrics for Continual Learni...
Don't forget, there is more than forgetting: new metrics for Continual Learni...
 
Open-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an OverviewOpen-Source Frameworks for Deep Learning: an Overview
Open-Source Frameworks for Deep Learning: an Overview
 
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
Continual Learning with Deep Architectures Workshop @ Computer VISIONers Conf...
 
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
CORe50: a New Dataset and Benchmark for Continual Learning and Object Recogni...
 
Continuous Learning with Deep Architectures
Continuous Learning with Deep ArchitecturesContinuous Learning with Deep Architectures
Continuous Learning with Deep Architectures
 
CORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition PosterCORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
CORe50: a New Dataset and Benchmark for Continuous Object Recognition Poster
 
Continuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep ArchitecturesContinuous Unsupervised Training of Deep Architectures
Continuous Unsupervised Training of Deep Architectures
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
 
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...Deep Learning for Computer Vision: A comparision between Convolutional Neural...
Deep Learning for Computer Vision: A comparision between Convolutional Neural...
 
A Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in JavaA Framework for Deadlock Detection in Java
A Framework for Deadlock Detection in Java
 
Deep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with TheanoDeep Learning libraries and first experiments with Theano
Deep Learning libraries and first experiments with Theano
 
Word2vec on the italian language: first experiments
Word2vec on the italian language: first experimentsWord2vec on the italian language: first experiments
Word2vec on the italian language: first experiments
 
Machine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An OverviewMachine Learning for Automated Reasoning: An Overview
Machine Learning for Automated Reasoning: An Overview
 

Recently uploaded

+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...Health
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteedamy56318795
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...gajnagarg
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...nirzagarg
 
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...gajnagarg
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareGraham Ware
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样wsppdmt
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...nirzagarg
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdfkhraisr
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabiaahmedjiabur940
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制vexqp
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...nirzagarg
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...HyderabadDolls
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraGovindSinghDasila
 
Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1ranjankumarbehera14
 
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...HyderabadDolls
 
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...gragchanchal546
 
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...gajnagarg
 
Gartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxGartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxchadhar227
 
Fun all Day Call Girls in Jaipur 9332606886 High Profile Call Girls You Ca...
Fun all Day Call Girls in Jaipur   9332606886  High Profile Call Girls You Ca...Fun all Day Call Girls in Jaipur   9332606886  High Profile Call Girls You Ca...
Fun all Day Call Girls in Jaipur 9332606886 High Profile Call Girls You Ca...kumargunjan9515
 

Recently uploaded (20)

+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
+97470301568>>weed for sale in qatar ,weed for sale in dubai,weed for sale in...
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Latur [ 7014168258 ] Call Me For Genuine Models We ...
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham Ware
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
 
20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf20240412-SmartCityIndex-2024-Full-Report.pdf
20240412-SmartCityIndex-2024-Full-Report.pdf
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 
Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1Lecture_2_Deep_Learning_Overview-newone1
Lecture_2_Deep_Learning_Overview-newone1
 
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
Nirala Nagar / Cheap Call Girls In Lucknow Phone No 9548273370 Elite Escort S...
 
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
 
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Indore [ 7014168258 ] Call Me For Genuine Models We...
 
Gartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxGartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptx
 
Fun all Day Call Girls in Jaipur 9332606886 High Profile Call Girls You Ca...
Fun all Day Call Girls in Jaipur   9332606886  High Profile Call Girls You Ca...Fun all Day Call Girls in Jaipur   9332606886  High Profile Call Girls You Ca...
Fun all Day Call Girls in Jaipur 9332606886 High Profile Call Girls You Ca...
 

Comparing Incremental Learning Strategies for Convolutional Neural Networks

  • 1. COMPARING INCREMENTAL LEARNING STRATEGIES FOR CONVOLUTIONAL NEURAL NETWORKS Vincenzo Lomonaco & Davide Maltoni {vincenzo.lomonaco, davide.maltoni}@unibo.it Department of Computer Science and Engineering – DISI University of Bologna
  • 2. OUTLINE 1. Introduction • CNNs and current limitations • Incremental learning: Why? 2. Incremental learning Strategies for CNNs • Definitions • Possible instantiations used during the experimentations 3. Datasets • iCubWorld28 • BigBrother 4. Experiments and Results • Exp. design • Results analysis 5. Conclusions and Future Works
  • 3. OUTLINE 1. Introduction • CNNs and current limitations • Incremental learning: Why? 2. Incremental learning Strategies for CNNs • Definitions • Possible instantiations used during the experimentations 3. Datasets • iCubWorld28 • BigBrother 4. Experiments and Results • Exp. design • Results analysis 5. Conclusions and Future Works
  • 4. INTRODUCTION – CNNs and Current Limitations State-of-the-art algorithm for many tasks in CV, NLP, SR, etc.. Very general and adaptive Works directy on raw data (no hand-engineered features required) Computational demanding Tricky hyper-parametrization Applicability in Incremental Learning Scenario?
  • 5. INTRODUCTION – Incremental learnig: Why? 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . . Initial Batch Incremental Batches 
  • 6. INTRODUCTION – Incremental learnig: Why? Constraints: • Memory: We can’t afford to keep in memory all the batches. • Computational power: We can’t afford to train our classification model from scratch after each batch. 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . .  Initial Batch Incremental Batches
  • 7. INTRODUCTION – Incremental learnig: Why? Goal: • Maximize the Accuracy % after each batch • Going towards a more smooth and natural learning but still using CNNs 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . .  Initial Batch Incremental Batches
  • 8. INTRODUCTION – Incremental learnig: Why? 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . . 𝑀0
  • 9. INTRODUCTION – Incremental learnig: Why? 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . . 𝑀0 𝑀1 • We can free the memory occupied by 𝐵𝑎𝑡𝑐ℎ0 and get 𝑀1 just by updating 𝑀0 with the new coming batch • However, we risk to forget what we’ve previously learned
  • 10. INTRODUCTION – Incremental learnig: Why? 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . . 𝑀0 𝑀1
  • 11. INTRODUCTION – Incremental learnig: Why? 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . . 𝑀0 𝑀1
  • 12. INTRODUCTION – Incremental learnig: Why? 𝐵𝑎𝑡𝑐ℎ0 𝐵𝑎𝑡𝑐ℎ1 𝐵𝑎𝑡𝑐ℎ 𝑛 . . . 𝑀0 𝑀1 . . . 𝑀 𝑛
  • 13. OUTLINE 1. Introduction • CNNs and current limitations • Incremental learning: Why? 2. Incremental learning Strategies for CNNs • Definitions • Possible instantiations used during the experimentations 3. Datasets • iCubWorld28 • BigBrother 4. Experiments and Results • Exp. design • Results analysis 5. Conclusions and Future Works
  • 14. INC. LEARNING STRATEGIES FOR CNNS - Definitions The different possibilities we explored to deal with an incremental tuning/learning scenario, can be conveniently framed in three main strategies: 1. Training/tuning an ad hoc CNN architecture suitable for the problem. 2. Using an already trained CNN as a fixed feature extractor in conjunction with an incremental classifier. 3. Fine-tuning an already trained CNN.
  • 15. INC. LEARNING STRATEGIES FOR CNNS - Instantiations In our experiments (with focus on image classification) we tested three instantiations of the aforementioned strategies, respectively: 1. (Ad-hoc arch.)  LeNet7 Consists of the classical “LeNet7” proposed by Yan LeCun in 2004. Still competitive on low/medium scale problems. 2. (CNN-fixed w. inc. Classifier)  CaffeNet + SVM Consists of a pre-trained CNN provided in the Caffe library (“BVLC Reference CaffeNet”, based on the “AlexNet” architecture; An incremental and linear SVM as Classifier. 3. (CNN-Finetuning)  CaffeNet + FT Consists again of the “BVLC Reference CaffeNet” but instead of using it as a fixed feature extractor the network is fine-tuned to suit the new task.
  • 16. INC. LEARNING STRATEGIES FOR CNNS - Instantiations Furthermore, for the “BigBrother” dataset we decided to test an additional pair of strategies: 4. (CNN-fixed w. inc. Classifier)  VGG_Face + SVM Consists of a pre-trained (16-levels) CNN called “VGG Face” which has been trained on a very large dataset of faces (2,622 Subjects and 2.6M images); Again, a incremental and linear SVM as Classifier. 5. (CNN-Finetuning)  VGG_Face + FT Consists again of the “VGG_Face” CNN but instead of using it as a fixed feature extractor the network is fine-tuned to suit the new task.
  • 17. OUTLINE 1. Introduction • CNNs and current limitations • Incremental learning: Why? 2. Incremental Learning Strategies for CNNs • Definitions • Possible instantiations used during the experimentations 3. Datasets • iCubWorld28 • BigBrother 4. Experiments and Results • Exp. design • Results analysis 5. Conclusions and Future Works
  • 18. DATASETS We were interested in datasets where: • The objects of interest have been acquired in a number of successive sessions • The environmental condition can change among the sessions. We focused on two applicative fields where incremental learning is very relevant (robotics and biometrics) and chose two datasets respectively: • iCubWorld28 • BigBrother
  • 19. DATASETS – iCubWorld28 Key Features: • Img size: 128×128 • Num. classes: 7 (× 4 obj) • Tot. imgs: 39,693 • Num batches: 9 +1 (test)
  • 20. DATASETS – BigBrother Key Features: • Img size: 70×70 • Num. classes: 7 • Tot. imgs: 23,842 • Num batches: 56 +1 (test)
  • 21. OUTLINE 1. Introduction • CNNs and current limitations • Incremental learning: Why? 2. Incremental Learning Strategies for CNNs • Definitions • Possible instantiations used during the experimentations 3. Datasets • iCubWorld28 • BigBrother 4. Experiments and Results • Exp. design • Results analysis 5. Conclusions and Future Works
  • 22. EXPERIMENTS AND RESULTS – Exp. Design Experiments Policy: • We trained the models until full convergence on the first batch of data • We tuned them on the successive incremental batches, trying to balance the trade-off between accuracy gain and forgetting.
  • 23. EXPERIMENTS AND RESULTS – iCubWorld28 Results
  • 24. EXPERIMENTS AND RESULTS – iCubWorld28 Results • CaffeNet + SVM has a very good recognition rate increment • CaffeNet + FT is the most effective • LeNet7 struggles to learn complex invariant features necessary for this problem
  • 25. EXPERIMENTS AND RESULTS – BigBrother Results
  • 26. EXPERIMENTS AND RESULTS – BigBrother Results • LeNet7 model performs slightly better than CaffeNet + SVM or CaffeNet + FT • VGG_Face + SVM and VGG_Face + FT have impressive performance on this problem • VGG_Face + SVM seems to be the best choice both for the accuracy and the stability
  • 27. EXPERIMENTS AND RESULTS – Dealing with Forgetting
  • 28. EXPERIMENTS AND RESULTS – Dealing with Forgetting • An adjustable learning rate is significantly more stable • A simple thresholding approach has been used. • We did not found any significant difference using a continuous approach
  • 29. OUTLINE 1. Introduction • CNNs and current limitations • Incremental learning: Why? 2. Incremental Learning Strategies for CNNs • Definitions • Possible instantiations used during the experimentations 3. Datasets • iCubWorld28 • BigBrother 4. Experiments and Results • Exp. design • Results analysis 5. Conclusions and Future Works
  • 30. CONCLUSIONS AND FUTURE WORKS • When possible (i.e., transfer learning from the same domain), it is preferable to use CNN as a fixed feature extractor to feed an incremental classifier • If the features are not optimized, the tuning of low level layers may be preferable and the learning strength can be used to control forgetting. • Training a CNN from scratch can be advantageous if the problem patterns (and feature invariances) are highly specific and a sufficient number of samples are available.
  • 31. CONCLUSIONS AND FUTURE WORKS In the near future we plan to extend this work by: • Performing a more extensive experimental evaluation • Finding a more principled way to control forgetting and adapting the tuning parameters to the size (and bias) of each incremental batch. • Studying real-world applications of semi-supervised incremental learning strategies for CNNs.
  • 32. COMPARING INCREMENTAL LEARNING STRATEGIES FOR CONVOLUTIONAL NEURAL NETWORKS Vincenzo Lomonaco & Davide Maltoni {vincenzo.lomonaco, davide.maltoni}@unibo.it Department of Computer Science and Engineering – DISI University of Bologna Thank you for your attention. Any Questions?