SlideShare a Scribd company logo
1 of 22
Download to read offline
Study Meeting Presentation:



Really Quick Intro on Few-Shot Learning

Author: Noel Tay



Date: 2020/08/28 

Getting things in perspective …
Predictor
Train
Dog
Let us limit the discussion to:
- Image classification
- Supervised learning
- Close set recognition
- Requires a huge number of data for each
task
- New task needs to be retrained
- However, humans can learn it effortlessly
Image source from “The CIFAR-10 dataset” (https://www.cs.toronto.edu/~kriz/cifar.html)
Image Source: https://unsplash.com/
Image source from “The CIFAR-10 dataset” (https://www.cs.toronto.edu/~kriz/cifar.html)
Image Source:
https://unsplash.com/
Getting things in perspective …
How many people are there?
What is this place?
Where is this place?
What is the time of day?
What is the temperature?
What is the mood?
Do they practice social distancing?
Do they wear masks?
Humans:
- Can decompose/manipulate
representations
- Accommodate to task
- Don’t need extra training
Data Bias!
3
Image Source: https://unsplash.com/
Getting things in perspective …
To mimic human ability:
- Finding good priors
Blank slate vs. innate behaviors
- Good representations
Learning with the help of ‘unlabeled’ data, such as self-supervised learning
- Transfer learning
Knowledge transfer from one task to the other (For example, improving face
recognition with another model that deals with different expressions)
- Few-shot learning
This is what we will be talking about!
4
Few-Shot Learning
- To classify new data after being given a few
samples
- Extreme case is called one-shot learning
Class 1
Class 2
- It is not to solve insufficient data issue, but to provide an alternative way to
handle little data per class
5
?
Source: https://unsplash.com/
Urban Rural
Truck
Car
Few-Shot Learning
- To quickly switch to new classification task with few samples
6
Image source: https://unsplash.com/
Yellow
Red
Few-Shot Learning
- To quickly switch to new classification task with few samples
7
Image source: https://unsplash.com/
Query set
Support set
Few-Shot Learning
- N-way-K-shot
Truck
Car
2-way-4-shot
?
8
Task
Image source: https://unsplash.com/
Few-Shot Learning
Meta-Learning Framework
- Conventional approach is to train the model using dataset to perform
classification
- Meta-learning is to ‘train’ the model to learn how to use dataset to
perform classification (Learning to Learn)
Class 1
Class 2 ?
Class 1
Class 2
?
9
Meta-Learning
predictor Dog
Train
Testing
10
Conventional
Image source from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html
Meta-Learning: Learning to Learn
Testing
predictor
Train
Dog
There are no sample-class binding
11
Each data sample
is a Task
Image source from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html
Image source from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html
12
Class 1
Class 2
Class 1
Class 2
Class 1
Class 2
Meta-Learning: Classes, samples and labels shuffling
Image source modified from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html
Meta-Learning
- Based on similarity
- Matching networks
- Prototypical networks
- Relation networks
- Based on learning algorithm
- Model agnostic meta-learning (MAML)
- Memory augmented neural network
- Based on data
- Bayesian programs
13
Meta-Learning: Based on Similarity
0.08 0.02 0.1 0.8
x x x x
sum
Matching
Network
Prototypical
Network
14
[1] Vinyals, O., Blundell, C., Lillicrap, T., & Wierstra, D. (2016). Matching networks for one shot learning. Advances in neural information processing systems, 29, 3630-3638.
[2] Snell, J., Swersky, K., & Zemel, R. S. (2017). Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175.
Image source from original paper [1]
Image source from original paper [2]
Image modified from
original paper [1]
Meta-Learning: Based on Similarity
15
Image source from: https://www.borealisai.com/en/blog/tutorial-2-few-shot-learning-and-meta-learning-i/
Meta-Learning: Based on Learning Algorithm
Memory Augmented Neural Network (MANN)
Learns the algorithm to store and retrieve memories [1]
16
dog cat dog dog cat
…
NULL
[1] Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., & Lillicrap, T. (2016, June). Meta-learning with memory-augmented neural networks. In International conference on machine learning (pp.
1842-1850). PMLR.
Image source from original paper [1]
Image source from original paper [1]
Image source: https://unsplash.com/
w1
w2
Meta-Learning: Based on Learning Algorithm
Model agnostic meta-learning (MAML) [1]
17
Task 1 Task 2
Task 3
Init
[1] Finn, C., Abbeel, P., & Levine, S. (2017, July). Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning (pp. 1126-1135). PMLR.
Image source modified from:
https://lilianweng.github.io/lil-log/2018/11/30/meta-learnin
g.html
Image source modified from:
https://lilianweng.github.io/lil-log/2018/11/30/meta-learnin
g.html
w1
w2
Meta-Learning: Based on Learning Algorithm
Model agnostic meta-learning (MAML)
18
Task 1 Task 2
Task 3
data for task1
learning
data for task2
learning
data for task3
learning
w1
w2
Meta-Learning: Based on Learning Algorithm
Model agnostic meta-learning (MAML)
19
Task 1 Task 2
Task 3
data for task1 meta
learning
data for task2 meta
learning
data for task3 meta
learning
w1
w2
Meta-Learning: Based on Learning Algorithm
Model agnostic meta-learning (MAML)
20
Task 1 Task 2
Task 3
Meta-Learning: Based on Data
Modeling through Bayesian Programs
21
…
- Structure of the model contains information
on how the output is created (prior)
- Meta-learning learns a way for various
Bayesian program modules to combine to
express unseen data
- Remember probabilistic programming with
Pyro?
[1] Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015). Human-level concept learning through probabilistic program induction. Science, 350(6266), 1332-1338.
Image source from original paper [1]
22
Consideration (after getting things in perspective…)
- Do I need ‘learning to learn’ or just lack of data
Does my application justify its usage
- Is my dataset sufficient enough
Huge amount of data doesn’t mean sufficient
- What prior knowledge I have
For example: data model, invariance assumption
- Any training constraints I can impose
For example: curriculum learning, multi-loss, feature space constraints

More Related Content

What's hot

Introduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlowIntroduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlowSri Ambati
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNNAshray Bhandare
 
Optimization as a model for few shot learning
Optimization as a model for few shot learningOptimization as a model for few shot learning
Optimization as a model for few shot learningKaty Lee
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learningleopauly
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningJörgen Sandig
 
Long Short Term Memory
Long Short Term MemoryLong Short Term Memory
Long Short Term MemoryYan Xu
 
META-LEARNING.pptx
META-LEARNING.pptxMETA-LEARNING.pptx
META-LEARNING.pptxAyanaRukasar
 
Continual learning: Survey
Continual learning: SurveyContinual learning: Survey
Continual learning: SurveyWonjun Jeong
 
Neural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronNeural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronMostafa G. M. Mostafa
 
Understanding RNN and LSTM
Understanding RNN and LSTMUnderstanding RNN and LSTM
Understanding RNN and LSTM健程 杨
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsKasun Chinthaka Piyarathna
 
Recurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryRecurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryAndrii Gakhov
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsJinwon Lee
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep LearningSebastian Ruder
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersRoelof Pieters
 
Semi-Supervised Learning
Semi-Supervised LearningSemi-Supervised Learning
Semi-Supervised LearningLukas Tencer
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNNShuai Zhang
 
Convolutional neural network
Convolutional neural network Convolutional neural network
Convolutional neural network Yan Xu
 

What's hot (20)

Introduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlowIntroduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlow
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNN
 
Optimization as a model for few shot learning
Optimization as a model for few shot learningOptimization as a model for few shot learning
Optimization as a model for few shot learning
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Long Short Term Memory
Long Short Term MemoryLong Short Term Memory
Long Short Term Memory
 
META-LEARNING.pptx
META-LEARNING.pptxMETA-LEARNING.pptx
META-LEARNING.pptx
 
Continual learning: Survey
Continual learning: SurveyContinual learning: Survey
Continual learning: Survey
 
Deep learning
Deep learningDeep learning
Deep learning
 
Neural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronNeural Networks: Multilayer Perceptron
Neural Networks: Multilayer Perceptron
 
Understanding RNN and LSTM
Understanding RNN and LSTMUnderstanding RNN and LSTM
Understanding RNN and LSTM
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
 
Recurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryRecurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: Theory
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep Learning
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
 
Bert
BertBert
Bert
 
Semi-Supervised Learning
Semi-Supervised LearningSemi-Supervised Learning
Semi-Supervised Learning
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
Convolutional neural network
Convolutional neural network Convolutional neural network
Convolutional neural network
 

Similar to Introduction to Few shot learning

Logistic Regression In Data Science
Logistic Regression In Data ScienceLogistic Regression In Data Science
Logistic Regression In Data ScienceEdureka!
 
Monet banksy may2014
Monet banksy may2014Monet banksy may2014
Monet banksy may2014GailStrachan
 
Developing Computational Skills in the Sciences with Matlab Webinar 2017
Developing Computational Skills in the Sciences with Matlab Webinar 2017Developing Computational Skills in the Sciences with Matlab Webinar 2017
Developing Computational Skills in the Sciences with Matlab Webinar 2017SERC at Carleton College
 
dark futures_v3
dark futures_v3dark futures_v3
dark futures_v3Stella Lee
 
Automatic Learning Image Objects via Incremental Model
Automatic Learning Image Objects via Incremental ModelAutomatic Learning Image Objects via Incremental Model
Automatic Learning Image Objects via Incremental ModelIOSR Journals
 
An invitation to a conversation: Towards a South African ethical use of stude...
An invitation to a conversation: Towards a South African ethical use of stude...An invitation to a conversation: Towards a South African ethical use of stude...
An invitation to a conversation: Towards a South African ethical use of stude...University of South Africa (Unisa)
 
How can we train with few data
How can we train with few dataHow can we train with few data
How can we train with few dataDong Heon Cho
 
Sentiment Analysis In Retail Domain
Sentiment Analysis In Retail DomainSentiment Analysis In Retail Domain
Sentiment Analysis In Retail DomainEdureka!
 
Deep Learning Explained
Deep Learning ExplainedDeep Learning Explained
Deep Learning ExplainedMelanie Swan
 
Fast AI with Image Classification.pptx
Fast AI with Image Classification.pptxFast AI with Image Classification.pptx
Fast AI with Image Classification.pptxAbraham Kong
 
A Blind Date With (Big) Data: Student Data in (Higher) Education
A Blind Date With (Big) Data: Student Data in (Higher) EducationA Blind Date With (Big) Data: Student Data in (Higher) Education
A Blind Date With (Big) Data: Student Data in (Higher) EducationUniversity of South Africa (Unisa)
 
Data scientist enablement dse 400 week 3 roadmap
Data scientist enablement   dse 400   week 3 roadmapData scientist enablement   dse 400   week 3 roadmap
Data scientist enablement dse 400 week 3 roadmapDr. Mohan K. Bavirisetty
 
Analysing image collections with the computer vision network approach
Analysing image collections with  the computer vision network approachAnalysing image collections with  the computer vision network approach
Analysing image collections with the computer vision network approachJanna Joceli Omena
 
Philosophy of Deep Learning
Philosophy of Deep LearningPhilosophy of Deep Learning
Philosophy of Deep LearningMelanie Swan
 
Helping More Teachers Discover Your Digital Resources
Helping More Teachers Discover Your Digital ResourcesHelping More Teachers Discover Your Digital Resources
Helping More Teachers Discover Your Digital ResourcesDarren Milligan
 
Developments in Adaptive E-Learning
Developments in Adaptive E-LearningDevelopments in Adaptive E-Learning
Developments in Adaptive E-LearningChristian Glahn
 

Similar to Introduction to Few shot learning (20)

Logistic Regression In Data Science
Logistic Regression In Data ScienceLogistic Regression In Data Science
Logistic Regression In Data Science
 
Monet banksy may2014
Monet banksy may2014Monet banksy may2014
Monet banksy may2014
 
Developing Computational Skills in the Sciences with Matlab Webinar 2017
Developing Computational Skills in the Sciences with Matlab Webinar 2017Developing Computational Skills in the Sciences with Matlab Webinar 2017
Developing Computational Skills in the Sciences with Matlab Webinar 2017
 
dark futures_v3
dark futures_v3dark futures_v3
dark futures_v3
 
Automatic Learning Image Objects via Incremental Model
Automatic Learning Image Objects via Incremental ModelAutomatic Learning Image Objects via Incremental Model
Automatic Learning Image Objects via Incremental Model
 
‘Responsible’ learning analytics: A tentative proposal
‘Responsible’ learning analytics:  A tentative proposal‘Responsible’ learning analytics:  A tentative proposal
‘Responsible’ learning analytics: A tentative proposal
 
An invitation to a conversation: Towards a South African ethical use of stude...
An invitation to a conversation: Towards a South African ethical use of stude...An invitation to a conversation: Towards a South African ethical use of stude...
An invitation to a conversation: Towards a South African ethical use of stude...
 
How can we train with few data
How can we train with few dataHow can we train with few data
How can we train with few data
 
Sentiment Analysis In Retail Domain
Sentiment Analysis In Retail DomainSentiment Analysis In Retail Domain
Sentiment Analysis In Retail Domain
 
Deep Learning Explained
Deep Learning ExplainedDeep Learning Explained
Deep Learning Explained
 
Fast AI with Image Classification.pptx
Fast AI with Image Classification.pptxFast AI with Image Classification.pptx
Fast AI with Image Classification.pptx
 
A Blind Date With (Big) Data: Student Data in (Higher) Education
A Blind Date With (Big) Data: Student Data in (Higher) EducationA Blind Date With (Big) Data: Student Data in (Higher) Education
A Blind Date With (Big) Data: Student Data in (Higher) Education
 
Intro to LLMs
Intro to LLMsIntro to LLMs
Intro to LLMs
 
Data scientist enablement dse 400 week 3 roadmap
Data scientist enablement   dse 400   week 3 roadmapData scientist enablement   dse 400   week 3 roadmap
Data scientist enablement dse 400 week 3 roadmap
 
Analysing image collections with the computer vision network approach
Analysing image collections with  the computer vision network approachAnalysing image collections with  the computer vision network approach
Analysing image collections with the computer vision network approach
 
Philosophy of Deep Learning
Philosophy of Deep LearningPhilosophy of Deep Learning
Philosophy of Deep Learning
 
One shot learning
One shot learningOne shot learning
One shot learning
 
Active learning
Active learningActive learning
Active learning
 
Helping More Teachers Discover Your Digital Resources
Helping More Teachers Discover Your Digital ResourcesHelping More Teachers Discover Your Digital Resources
Helping More Teachers Discover Your Digital Resources
 
Developments in Adaptive E-Learning
Developments in Adaptive E-LearningDevelopments in Adaptive E-Learning
Developments in Adaptive E-Learning
 

More from Ridge-i, Inc.

Unsupervised Video Anomaly Detection: A brief overview
Unsupervised Video Anomaly Detection: A brief overviewUnsupervised Video Anomaly Detection: A brief overview
Unsupervised Video Anomaly Detection: A brief overviewRidge-i, Inc.
 
Continual Learning Introduction
Continual Learning IntroductionContinual Learning Introduction
Continual Learning IntroductionRidge-i, Inc.
 
May internship challenge: Font Generator
May internship challenge: Font GeneratorMay internship challenge: Font Generator
May internship challenge: Font GeneratorRidge-i, Inc.
 
How to learn with non-reliable labels?
How to learn with non-reliable labels?How to learn with non-reliable labels?
How to learn with non-reliable labels?Ridge-i, Inc.
 
How to learn with non-reliable labels? (Japanese version)
How to learn with non-reliable labels? (Japanese version)How to learn with non-reliable labels? (Japanese version)
How to learn with non-reliable labels? (Japanese version)Ridge-i, Inc.
 
May internship challenge: User Authentication System only using image data: C...
May internship challenge: User Authentication System only using image data: C...May internship challenge: User Authentication System only using image data: C...
May internship challenge: User Authentication System only using image data: C...Ridge-i, Inc.
 
May internship challenge: Estimating Distance between Two Balls App
May internship challenge: Estimating Distance between Two Balls AppMay internship challenge: Estimating Distance between Two Balls App
May internship challenge: Estimating Distance between Two Balls AppRidge-i, Inc.
 

More from Ridge-i, Inc. (8)

Unsupervised Video Anomaly Detection: A brief overview
Unsupervised Video Anomaly Detection: A brief overviewUnsupervised Video Anomaly Detection: A brief overview
Unsupervised Video Anomaly Detection: A brief overview
 
Continual Learning Introduction
Continual Learning IntroductionContinual Learning Introduction
Continual Learning Introduction
 
Explainable AI
Explainable AIExplainable AI
Explainable AI
 
May internship challenge: Font Generator
May internship challenge: Font GeneratorMay internship challenge: Font Generator
May internship challenge: Font Generator
 
How to learn with non-reliable labels?
How to learn with non-reliable labels?How to learn with non-reliable labels?
How to learn with non-reliable labels?
 
How to learn with non-reliable labels? (Japanese version)
How to learn with non-reliable labels? (Japanese version)How to learn with non-reliable labels? (Japanese version)
How to learn with non-reliable labels? (Japanese version)
 
May internship challenge: User Authentication System only using image data: C...
May internship challenge: User Authentication System only using image data: C...May internship challenge: User Authentication System only using image data: C...
May internship challenge: User Authentication System only using image data: C...
 
May internship challenge: Estimating Distance between Two Balls App
May internship challenge: Estimating Distance between Two Balls AppMay internship challenge: Estimating Distance between Two Balls App
May internship challenge: Estimating Distance between Two Balls App
 

Recently uploaded

Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 

Recently uploaded (20)

Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 

Introduction to Few shot learning

  • 1. Study Meeting Presentation:
 
 Really Quick Intro on Few-Shot Learning
 Author: Noel Tay
 
 Date: 2020/08/28 

  • 2. Getting things in perspective … Predictor Train Dog Let us limit the discussion to: - Image classification - Supervised learning - Close set recognition - Requires a huge number of data for each task - New task needs to be retrained - However, humans can learn it effortlessly Image source from “The CIFAR-10 dataset” (https://www.cs.toronto.edu/~kriz/cifar.html) Image Source: https://unsplash.com/ Image source from “The CIFAR-10 dataset” (https://www.cs.toronto.edu/~kriz/cifar.html) Image Source: https://unsplash.com/
  • 3. Getting things in perspective … How many people are there? What is this place? Where is this place? What is the time of day? What is the temperature? What is the mood? Do they practice social distancing? Do they wear masks? Humans: - Can decompose/manipulate representations - Accommodate to task - Don’t need extra training Data Bias! 3 Image Source: https://unsplash.com/
  • 4. Getting things in perspective … To mimic human ability: - Finding good priors Blank slate vs. innate behaviors - Good representations Learning with the help of ‘unlabeled’ data, such as self-supervised learning - Transfer learning Knowledge transfer from one task to the other (For example, improving face recognition with another model that deals with different expressions) - Few-shot learning This is what we will be talking about! 4
  • 5. Few-Shot Learning - To classify new data after being given a few samples - Extreme case is called one-shot learning Class 1 Class 2 - It is not to solve insufficient data issue, but to provide an alternative way to handle little data per class 5 ? Source: https://unsplash.com/
  • 6. Urban Rural Truck Car Few-Shot Learning - To quickly switch to new classification task with few samples 6 Image source: https://unsplash.com/
  • 7. Yellow Red Few-Shot Learning - To quickly switch to new classification task with few samples 7 Image source: https://unsplash.com/
  • 8. Query set Support set Few-Shot Learning - N-way-K-shot Truck Car 2-way-4-shot ? 8 Task Image source: https://unsplash.com/
  • 9. Few-Shot Learning Meta-Learning Framework - Conventional approach is to train the model using dataset to perform classification - Meta-learning is to ‘train’ the model to learn how to use dataset to perform classification (Learning to Learn) Class 1 Class 2 ? Class 1 Class 2 ? 9
  • 10. Meta-Learning predictor Dog Train Testing 10 Conventional Image source from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html
  • 11. Meta-Learning: Learning to Learn Testing predictor Train Dog There are no sample-class binding 11 Each data sample is a Task Image source from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html Image source from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html
  • 12. 12 Class 1 Class 2 Class 1 Class 2 Class 1 Class 2 Meta-Learning: Classes, samples and labels shuffling Image source modified from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html
  • 13. Meta-Learning - Based on similarity - Matching networks - Prototypical networks - Relation networks - Based on learning algorithm - Model agnostic meta-learning (MAML) - Memory augmented neural network - Based on data - Bayesian programs 13
  • 14. Meta-Learning: Based on Similarity 0.08 0.02 0.1 0.8 x x x x sum Matching Network Prototypical Network 14 [1] Vinyals, O., Blundell, C., Lillicrap, T., & Wierstra, D. (2016). Matching networks for one shot learning. Advances in neural information processing systems, 29, 3630-3638. [2] Snell, J., Swersky, K., & Zemel, R. S. (2017). Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175. Image source from original paper [1] Image source from original paper [2] Image modified from original paper [1]
  • 15. Meta-Learning: Based on Similarity 15 Image source from: https://www.borealisai.com/en/blog/tutorial-2-few-shot-learning-and-meta-learning-i/
  • 16. Meta-Learning: Based on Learning Algorithm Memory Augmented Neural Network (MANN) Learns the algorithm to store and retrieve memories [1] 16 dog cat dog dog cat … NULL [1] Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., & Lillicrap, T. (2016, June). Meta-learning with memory-augmented neural networks. In International conference on machine learning (pp. 1842-1850). PMLR. Image source from original paper [1] Image source from original paper [1] Image source: https://unsplash.com/
  • 17. w1 w2 Meta-Learning: Based on Learning Algorithm Model agnostic meta-learning (MAML) [1] 17 Task 1 Task 2 Task 3 Init [1] Finn, C., Abbeel, P., & Levine, S. (2017, July). Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning (pp. 1126-1135). PMLR. Image source modified from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learnin g.html Image source modified from: https://lilianweng.github.io/lil-log/2018/11/30/meta-learnin g.html
  • 18. w1 w2 Meta-Learning: Based on Learning Algorithm Model agnostic meta-learning (MAML) 18 Task 1 Task 2 Task 3 data for task1 learning data for task2 learning data for task3 learning
  • 19. w1 w2 Meta-Learning: Based on Learning Algorithm Model agnostic meta-learning (MAML) 19 Task 1 Task 2 Task 3 data for task1 meta learning data for task2 meta learning data for task3 meta learning
  • 20. w1 w2 Meta-Learning: Based on Learning Algorithm Model agnostic meta-learning (MAML) 20 Task 1 Task 2 Task 3
  • 21. Meta-Learning: Based on Data Modeling through Bayesian Programs 21 … - Structure of the model contains information on how the output is created (prior) - Meta-learning learns a way for various Bayesian program modules to combine to express unseen data - Remember probabilistic programming with Pyro? [1] Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015). Human-level concept learning through probabilistic program induction. Science, 350(6266), 1332-1338. Image source from original paper [1]
  • 22. 22 Consideration (after getting things in perspective…) - Do I need ‘learning to learn’ or just lack of data Does my application justify its usage - Is my dataset sufficient enough Huge amount of data doesn’t mean sufficient - What prior knowledge I have For example: data model, invariance assumption - Any training constraints I can impose For example: curriculum learning, multi-loss, feature space constraints