SlideShare a Scribd company logo
1 of 12
Semi Supervised Learning
Devansh
Context
Supervised learning is amazing. It has been used to solve a whole bunch of
problems.
It is also very intuitive when it comes to the idea. With lots of data and a directed
learning mechanism, it makes sense that our agents should be able to learn
specific things.
Labeling/annotating data can get extremely expensive. For eg. medical images
are typically very expensive to annotate (check out the video on SinGAN-Seg for
more details).
There is a lot of unlabeled data that is lying around, which can be used for cheap.
Enter Semi-Supervised Learning (Prequel)
Don’t confuse this with Self-Supervised Learning (I make that mistake a lot.)
How can we use the simpler concept and higher performance of Supervised
Learning with the cheap, large scale data availability of using Unsupervised
Learning?
That’s a good question. How would you try to use both processes to leverage the
strengths of both types (pause the video and think for a second)
An Image to help you think
SSL: Overview
We take a (relatively) small amount of labelled
data. Use that to learn.
Then take the unlabeled data use your model
to figure out the (pseudo) labels. Use that to
train our models further.
(Optional)
Rinse and Repeat. Do some other things like
add noise if you have the resources/want to
get creative
Transduction vs Induction
Often you will see learning presented as
either transductive or inductive learning.
Transductive learning: I give you specific
examples and ask you to predict specific
examples.
Inductive learning: I give you examples, and
you figure out a pattern. Use that pattern to
predict samples.
Sound similar? Think back to the video on
discriminative vs generative classification.
Assumptions used in Semi Supervised Learning
Take a second to pause. Think about the kinds of assumptions you make when
implementing SSL. This is a good habit when dealing with ML/Data.
Understanding your implicit assumptions gives you a way to figure out how to
improve.
SSL algorithms have 3 assumptions. To use SSL we need to make atleast one:
● Continuity assumption
● Cluster assumption
● Manifold assumption
Assumptions- Continuity
Wikipedia: Points that are close to each other are more likely to share a label. This
is also generally assumed in supervised learning and yields a preference for
geometrically simple decision boundaries. In the case of semi-supervised learning,
the smoothness assumption additionally yields a preference for decision
boundaries in low-density regions, so few points are close to each other but in
different classes.
Assumptions: Cluster
Wikipedia: The data tend to form discrete clusters, and points in the same cluster
are more likely to share a label (although data that shares a label may spread
across multiple clusters).
Gives rise to feature learning with clustering algorithms.
Assumptions: Manifold
The data lie approximately on a manifold of much lower dimension than the input
space. Learning the manifold using both the labeled and unlabeled data can avoid
the curse of dimensionality. Then learning can proceed using distances and
densities defined on the manifold.
SSL-> Most human way to learn?
Semi Supervised Learning is often compared to how we humans learn.
Think back to your favorite skills. How did you learn to do them? The SSL formula:
1) Have the learner train through specific guided examples with lots of detail.
2) As the learner becomes more proficient, we start using mixing in samples that
aren’t fully worked out. Learner must work through them on their own.
3) If we really want to check proficiency of the learner, we throw in
incorrect/broken examples, and have the student correct the mistakes.
Let’s see how this squares with our learning process. Let’s take 3 skills I learnt:
Math, French, and Brazilian JiuJitsu.
Reach out to me
Check out my other articles on Medium. : https://machine-learning-made-
simple.medium.com/
My YouTube: https://rb.gy/88iwdd
Reach out to me on LinkedIn: https://www.linkedin.com/in/devansh-devansh-516004168/
My Instagram: https://rb.gy/gmvuy9
My Twitter: https://twitter.com/Machine01776819
My Substack: https://devanshacc.substack.com/
Live conversations at twitch here: https://rb.gy/zlhk9y
Get a free stock on Robinhood: https://join.robinhood.com/fnud75

More Related Content

What's hot

Cross-validation Tutorial: What, how and which?
Cross-validation Tutorial: What, how and which?Cross-validation Tutorial: What, how and which?
Cross-validation Tutorial: What, how and which?Pradeep Redddy Raamana
 
Data mining: Classification and prediction
Data mining: Classification and predictionData mining: Classification and prediction
Data mining: Classification and predictionDataminingTools Inc
 
Support vector machines (svm)
Support vector machines (svm)Support vector machines (svm)
Support vector machines (svm)Sharayu Patil
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extractionskylian
 
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
 
Vc dimension in Machine Learning
Vc dimension in Machine LearningVc dimension in Machine Learning
Vc dimension in Machine LearningVARUN KUMAR
 
Outlier analysis,Chapter-12, Data Mining: Concepts and Techniques
Outlier analysis,Chapter-12, Data Mining: Concepts and TechniquesOutlier analysis,Chapter-12, Data Mining: Concepts and Techniques
Outlier analysis,Chapter-12, Data Mining: Concepts and TechniquesAshikur Rahman
 
Data Mining: Outlier analysis
Data Mining: Outlier analysisData Mining: Outlier analysis
Data Mining: Outlier analysisDatamining Tools
 
Feature selection
Feature selectionFeature selection
Feature selectionDong Guo
 
Support vector machine
Support vector machineSupport vector machine
Support vector machineMusa Hawamdah
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Appsilon Data Science
 
Neural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronNeural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronMostafa G. M. Mostafa
 
Data Mining: clustering and analysis
Data Mining: clustering and analysisData Mining: clustering and analysis
Data Mining: clustering and analysisDataminingTools Inc
 
Classification and Clustering
Classification and ClusteringClassification and Clustering
Classification and ClusteringEng Teong Cheah
 
5.1 mining data streams
5.1 mining data streams5.1 mining data streams
5.1 mining data streamsKrish_ver2
 
K-Folds Cross Validation Method
K-Folds Cross Validation MethodK-Folds Cross Validation Method
K-Folds Cross Validation MethodSHUBHAM GUPTA
 

What's hot (20)

Cross-validation Tutorial: What, how and which?
Cross-validation Tutorial: What, how and which?Cross-validation Tutorial: What, how and which?
Cross-validation Tutorial: What, how and which?
 
Data mining: Classification and prediction
Data mining: Classification and predictionData mining: Classification and prediction
Data mining: Classification and prediction
 
Support vector machines (svm)
Support vector machines (svm)Support vector machines (svm)
Support vector machines (svm)
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
 
K Nearest Neighbors
K Nearest NeighborsK Nearest Neighbors
K Nearest Neighbors
 
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
 
Vc dimension in Machine Learning
Vc dimension in Machine LearningVc dimension in Machine Learning
Vc dimension in Machine Learning
 
Outlier analysis,Chapter-12, Data Mining: Concepts and Techniques
Outlier analysis,Chapter-12, Data Mining: Concepts and TechniquesOutlier analysis,Chapter-12, Data Mining: Concepts and Techniques
Outlier analysis,Chapter-12, Data Mining: Concepts and Techniques
 
Data Mining: Outlier analysis
Data Mining: Outlier analysisData Mining: Outlier analysis
Data Mining: Outlier analysis
 
Feature selection
Feature selectionFeature selection
Feature selection
 
Support vector machine
Support vector machineSupport vector machine
Support vector machine
 
Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)Introduction to Generative Adversarial Networks (GANs)
Introduction to Generative Adversarial Networks (GANs)
 
Neural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronNeural Networks: Multilayer Perceptron
Neural Networks: Multilayer Perceptron
 
Elhabian lda09
Elhabian lda09Elhabian lda09
Elhabian lda09
 
Data Mining
Data MiningData Mining
Data Mining
 
Data Mining: clustering and analysis
Data Mining: clustering and analysisData Mining: clustering and analysis
Data Mining: clustering and analysis
 
Classification and Clustering
Classification and ClusteringClassification and Clustering
Classification and Clustering
 
Transfer Learning
Transfer LearningTransfer Learning
Transfer Learning
 
5.1 mining data streams
5.1 mining data streams5.1 mining data streams
5.1 mining data streams
 
K-Folds Cross Validation Method
K-Folds Cross Validation MethodK-Folds Cross Validation Method
K-Folds Cross Validation Method
 

Similar to Semi supervised learning machine learning made simple

ML crash course
ML crash courseML crash course
ML crash coursemikaelhuss
 
Week 4 advanced labeling, augmentation and data preprocessing
Week 4   advanced labeling, augmentation and data preprocessingWeek 4   advanced labeling, augmentation and data preprocessing
Week 4 advanced labeling, augmentation and data preprocessingAjay Taneja
 
E-Learning Balancing Act: Good vs Efficient development-web_version092010
E-Learning Balancing Act: Good vs Efficient development-web_version092010E-Learning Balancing Act: Good vs Efficient development-web_version092010
E-Learning Balancing Act: Good vs Efficient development-web_version092010tmharpster
 
Survey on contrastive self supervised l earning
Survey on contrastive self supervised l earningSurvey on contrastive self supervised l earning
Survey on contrastive self supervised l earningAnirudh Ganguly
 
Semi-Supervised.pptx
Semi-Supervised.pptxSemi-Supervised.pptx
Semi-Supervised.pptxTamer Nadeem
 
Instructional Design Today: What We Really Need to Know as Practitioners, Res...
Instructional Design Today: What We Really Need to Know as Practitioners, Res...Instructional Design Today: What We Really Need to Know as Practitioners, Res...
Instructional Design Today: What We Really Need to Know as Practitioners, Res...Karl Kapp
 
Lessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systemsLessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systemsXavier Amatriain
 
Machine Learning Tutorial for Beginners
Machine Learning Tutorial for BeginnersMachine Learning Tutorial for Beginners
Machine Learning Tutorial for Beginnersgrinu
 
Machine Learning Landscape
Machine Learning LandscapeMachine Learning Landscape
Machine Learning LandscapeEng Teong Cheah
 
M08 BiasVarianceTradeoff
M08 BiasVarianceTradeoffM08 BiasVarianceTradeoff
M08 BiasVarianceTradeoffRaman Kannan
 
Lect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdfLect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdfHassanElalfy4
 
23 rote learning and explanation based.doc
23 rote learning and explanation based.doc23 rote learning and explanation based.doc
23 rote learning and explanation based.docjdinfo444
 
Prior On Model Space
Prior On Model SpacePrior On Model Space
Prior On Model SpaceMeir Maor
 
Chapter01 introductory handbook
Chapter01 introductory handbookChapter01 introductory handbook
Chapter01 introductory handbookRaman Kannan
 
ELearning Design and Rollout
ELearning Design and RolloutELearning Design and Rollout
ELearning Design and RolloutJen Milner
 

Similar to Semi supervised learning machine learning made simple (20)

ML crash course
ML crash courseML crash course
ML crash course
 
Groupcfinalppt
GroupcfinalpptGroupcfinalppt
Groupcfinalppt
 
Group Bfinalppt
Group BfinalpptGroup Bfinalppt
Group Bfinalppt
 
Week 4 advanced labeling, augmentation and data preprocessing
Week 4   advanced labeling, augmentation and data preprocessingWeek 4   advanced labeling, augmentation and data preprocessing
Week 4 advanced labeling, augmentation and data preprocessing
 
E-Learning Balancing Act: Good vs Efficient development-web_version092010
E-Learning Balancing Act: Good vs Efficient development-web_version092010E-Learning Balancing Act: Good vs Efficient development-web_version092010
E-Learning Balancing Act: Good vs Efficient development-web_version092010
 
Blended e Assessment
Blended e AssessmentBlended e Assessment
Blended e Assessment
 
Survey on contrastive self supervised l earning
Survey on contrastive self supervised l earningSurvey on contrastive self supervised l earning
Survey on contrastive self supervised l earning
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
Semi-Supervised.pptx
Semi-Supervised.pptxSemi-Supervised.pptx
Semi-Supervised.pptx
 
Instructional Design Today: What We Really Need to Know as Practitioners, Res...
Instructional Design Today: What We Really Need to Know as Practitioners, Res...Instructional Design Today: What We Really Need to Know as Practitioners, Res...
Instructional Design Today: What We Really Need to Know as Practitioners, Res...
 
Lessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systemsLessons learned from building practical deep learning systems
Lessons learned from building practical deep learning systems
 
Machine Learning Tutorial for Beginners
Machine Learning Tutorial for BeginnersMachine Learning Tutorial for Beginners
Machine Learning Tutorial for Beginners
 
Machine Learning Landscape
Machine Learning LandscapeMachine Learning Landscape
Machine Learning Landscape
 
M08 BiasVarianceTradeoff
M08 BiasVarianceTradeoffM08 BiasVarianceTradeoff
M08 BiasVarianceTradeoff
 
Lect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdfLect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdf
 
23 rote learning and explanation based.doc
23 rote learning and explanation based.doc23 rote learning and explanation based.doc
23 rote learning and explanation based.doc
 
Machine_Learning.pptx
Machine_Learning.pptxMachine_Learning.pptx
Machine_Learning.pptx
 
Prior On Model Space
Prior On Model SpacePrior On Model Space
Prior On Model Space
 
Chapter01 introductory handbook
Chapter01 introductory handbookChapter01 introductory handbook
Chapter01 introductory handbook
 
ELearning Design and Rollout
ELearning Design and RolloutELearning Design and Rollout
ELearning Design and Rollout
 

More from Devansh16

Spine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localizationSpine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localizationDevansh16
 
Sigmoid function machine learning made simple
Sigmoid function  machine learning made simpleSigmoid function  machine learning made simple
Sigmoid function machine learning made simpleDevansh16
 
Accounting for variance in machine learning benchmarks
Accounting for variance in machine learning benchmarksAccounting for variance in machine learning benchmarks
Accounting for variance in machine learning benchmarksDevansh16
 
When deep learners change their mind learning dynamics for active learning
When deep learners change their mind  learning dynamics for active learningWhen deep learners change their mind  learning dynamics for active learning
When deep learners change their mind learning dynamics for active learningDevansh16
 
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...Devansh16
 
A simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsA simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsDevansh16
 
Recurrence relationships
Recurrence relationshipsRecurrence relationships
Recurrence relationshipsDevansh16
 
Paper Explained: Deep learning framework for measuring the digital strategy o...
Paper Explained: Deep learning framework for measuring the digital strategy o...Paper Explained: Deep learning framework for measuring the digital strategy o...
Paper Explained: Deep learning framework for measuring the digital strategy o...Devansh16
 
Paper Explained: One Pixel Attack for Fooling Deep Neural Networks
Paper Explained: One Pixel Attack for Fooling Deep Neural NetworksPaper Explained: One Pixel Attack for Fooling Deep Neural Networks
Paper Explained: One Pixel Attack for Fooling Deep Neural NetworksDevansh16
 
Paper Explained: Understanding the wiring evolution in differentiable neural ...
Paper Explained: Understanding the wiring evolution in differentiable neural ...Paper Explained: Understanding the wiring evolution in differentiable neural ...
Paper Explained: Understanding the wiring evolution in differentiable neural ...Devansh16
 
Machine Learning Made Simple: Differential evolution
Machine Learning Made Simple: Differential evolutionMachine Learning Made Simple: Differential evolution
Machine Learning Made Simple: Differential evolutionDevansh16
 
Paper Explained: RandAugment: Practical automated data augmentation with a re...
Paper Explained: RandAugment: Practical automated data augmentation with a re...Paper Explained: RandAugment: Practical automated data augmentation with a re...
Paper Explained: RandAugment: Practical automated data augmentation with a re...Devansh16
 
Noisy student images
Noisy student imagesNoisy student images
Noisy student imagesDevansh16
 
Deep learning ensembles loss landscape
Deep learning ensembles loss landscapeDeep learning ensembles loss landscape
Deep learning ensembles loss landscapeDevansh16
 

More from Devansh16 (14)

Spine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localizationSpine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localization
 
Sigmoid function machine learning made simple
Sigmoid function  machine learning made simpleSigmoid function  machine learning made simple
Sigmoid function machine learning made simple
 
Accounting for variance in machine learning benchmarks
Accounting for variance in machine learning benchmarksAccounting for variance in machine learning benchmarks
Accounting for variance in machine learning benchmarks
 
When deep learners change their mind learning dynamics for active learning
When deep learners change their mind  learning dynamics for active learningWhen deep learners change their mind  learning dynamics for active learning
When deep learners change their mind learning dynamics for active learning
 
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...
Paper Annotated: SinGAN-Seg: Synthetic Training Data Generation for Medical I...
 
A simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsA simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representations
 
Recurrence relationships
Recurrence relationshipsRecurrence relationships
Recurrence relationships
 
Paper Explained: Deep learning framework for measuring the digital strategy o...
Paper Explained: Deep learning framework for measuring the digital strategy o...Paper Explained: Deep learning framework for measuring the digital strategy o...
Paper Explained: Deep learning framework for measuring the digital strategy o...
 
Paper Explained: One Pixel Attack for Fooling Deep Neural Networks
Paper Explained: One Pixel Attack for Fooling Deep Neural NetworksPaper Explained: One Pixel Attack for Fooling Deep Neural Networks
Paper Explained: One Pixel Attack for Fooling Deep Neural Networks
 
Paper Explained: Understanding the wiring evolution in differentiable neural ...
Paper Explained: Understanding the wiring evolution in differentiable neural ...Paper Explained: Understanding the wiring evolution in differentiable neural ...
Paper Explained: Understanding the wiring evolution in differentiable neural ...
 
Machine Learning Made Simple: Differential evolution
Machine Learning Made Simple: Differential evolutionMachine Learning Made Simple: Differential evolution
Machine Learning Made Simple: Differential evolution
 
Paper Explained: RandAugment: Practical automated data augmentation with a re...
Paper Explained: RandAugment: Practical automated data augmentation with a re...Paper Explained: RandAugment: Practical automated data augmentation with a re...
Paper Explained: RandAugment: Practical automated data augmentation with a re...
 
Noisy student images
Noisy student imagesNoisy student images
Noisy student images
 
Deep learning ensembles loss landscape
Deep learning ensembles loss landscapeDeep learning ensembles loss landscape
Deep learning ensembles loss landscape
 

Recently uploaded

Statistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbersStatistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numberssuginr1
 
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
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...gajnagarg
 
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
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubaikojalkojal131
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...Elaine Werffeli
 
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...nirzagarg
 
Giridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime Giridih
Giridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime GiridihGiridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime Giridih
Giridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime Giridihmeghakumariji156
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...nirzagarg
 
Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...
Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...
Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...HyderabadDolls
 
Introduction to Statistics Presentation.pptx
Introduction to Statistics Presentation.pptxIntroduction to Statistics Presentation.pptx
Introduction to Statistics Presentation.pptxAniqa Zai
 
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...gajnagarg
 
👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...
👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...
👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...vershagrag
 
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...HyderabadDolls
 
Call Girls In GOA North Goa +91-8588052666 Direct Cash Escorts Service
Call Girls In GOA North Goa +91-8588052666 Direct Cash Escorts ServiceCall Girls In GOA North Goa +91-8588052666 Direct Cash Escorts Service
Call Girls In GOA North Goa +91-8588052666 Direct Cash Escorts Servicenishakur201
 
Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...
Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...
Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...HyderabadDolls
 
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
 
Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...gajnagarg
 
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
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...gajnagarg
 

Recently uploaded (20)

Statistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbersStatistics notes ,it includes mean to index numbers
Statistics notes ,it includes mean to index numbers
 
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...
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
 
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
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubai
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
 
Giridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime Giridih
Giridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime GiridihGiridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime Giridih
Giridih Escorts Service Girl ^ 9332606886, WhatsApp Anytime Giridih
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
 
Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...
Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...
Lake Town / Independent Kolkata Call Girls Phone No 8005736733 Elite Escort S...
 
Introduction to Statistics Presentation.pptx
Introduction to Statistics Presentation.pptxIntroduction to Statistics Presentation.pptx
Introduction to Statistics Presentation.pptx
 
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
Top profile Call Girls In Chandrapur [ 7014168258 ] Call Me For Genuine Model...
 
👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...
👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...
👉 Bhilai Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl Ser...
 
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
Charbagh + Female Escorts Service in Lucknow | Starting ₹,5K To @25k with A/C...
 
Call Girls In GOA North Goa +91-8588052666 Direct Cash Escorts Service
Call Girls In GOA North Goa +91-8588052666 Direct Cash Escorts ServiceCall Girls In GOA North Goa +91-8588052666 Direct Cash Escorts Service
Call Girls In GOA North Goa +91-8588052666 Direct Cash Escorts Service
 
Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...
Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...
Belur $ Female Escorts Service in Kolkata (Adult Only) 8005736733 Escort Serv...
 
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...
 
Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Nandurbar [ 7014168258 ] Call Me For Genuine Models...
 
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
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
 

Semi supervised learning machine learning made simple

  • 2. Context Supervised learning is amazing. It has been used to solve a whole bunch of problems. It is also very intuitive when it comes to the idea. With lots of data and a directed learning mechanism, it makes sense that our agents should be able to learn specific things. Labeling/annotating data can get extremely expensive. For eg. medical images are typically very expensive to annotate (check out the video on SinGAN-Seg for more details). There is a lot of unlabeled data that is lying around, which can be used for cheap.
  • 3. Enter Semi-Supervised Learning (Prequel) Don’t confuse this with Self-Supervised Learning (I make that mistake a lot.) How can we use the simpler concept and higher performance of Supervised Learning with the cheap, large scale data availability of using Unsupervised Learning? That’s a good question. How would you try to use both processes to leverage the strengths of both types (pause the video and think for a second)
  • 4. An Image to help you think
  • 5. SSL: Overview We take a (relatively) small amount of labelled data. Use that to learn. Then take the unlabeled data use your model to figure out the (pseudo) labels. Use that to train our models further. (Optional) Rinse and Repeat. Do some other things like add noise if you have the resources/want to get creative
  • 6. Transduction vs Induction Often you will see learning presented as either transductive or inductive learning. Transductive learning: I give you specific examples and ask you to predict specific examples. Inductive learning: I give you examples, and you figure out a pattern. Use that pattern to predict samples. Sound similar? Think back to the video on discriminative vs generative classification.
  • 7. Assumptions used in Semi Supervised Learning Take a second to pause. Think about the kinds of assumptions you make when implementing SSL. This is a good habit when dealing with ML/Data. Understanding your implicit assumptions gives you a way to figure out how to improve. SSL algorithms have 3 assumptions. To use SSL we need to make atleast one: ● Continuity assumption ● Cluster assumption ● Manifold assumption
  • 8. Assumptions- Continuity Wikipedia: Points that are close to each other are more likely to share a label. This is also generally assumed in supervised learning and yields a preference for geometrically simple decision boundaries. In the case of semi-supervised learning, the smoothness assumption additionally yields a preference for decision boundaries in low-density regions, so few points are close to each other but in different classes.
  • 9. Assumptions: Cluster Wikipedia: The data tend to form discrete clusters, and points in the same cluster are more likely to share a label (although data that shares a label may spread across multiple clusters). Gives rise to feature learning with clustering algorithms.
  • 10. Assumptions: Manifold The data lie approximately on a manifold of much lower dimension than the input space. Learning the manifold using both the labeled and unlabeled data can avoid the curse of dimensionality. Then learning can proceed using distances and densities defined on the manifold.
  • 11. SSL-> Most human way to learn? Semi Supervised Learning is often compared to how we humans learn. Think back to your favorite skills. How did you learn to do them? The SSL formula: 1) Have the learner train through specific guided examples with lots of detail. 2) As the learner becomes more proficient, we start using mixing in samples that aren’t fully worked out. Learner must work through them on their own. 3) If we really want to check proficiency of the learner, we throw in incorrect/broken examples, and have the student correct the mistakes. Let’s see how this squares with our learning process. Let’s take 3 skills I learnt: Math, French, and Brazilian JiuJitsu.
  • 12. Reach out to me Check out my other articles on Medium. : https://machine-learning-made- simple.medium.com/ My YouTube: https://rb.gy/88iwdd Reach out to me on LinkedIn: https://www.linkedin.com/in/devansh-devansh-516004168/ My Instagram: https://rb.gy/gmvuy9 My Twitter: https://twitter.com/Machine01776819 My Substack: https://devanshacc.substack.com/ Live conversations at twitch here: https://rb.gy/zlhk9y Get a free stock on Robinhood: https://join.robinhood.com/fnud75