SlideShare une entreprise Scribd logo
DA 5330 – Advanced Machine Learning
Applications
Lecture 11 – Advanced Learning Techniques
Maninda Edirisooriya
manindaw@uom.lk
End-to-End Learning
• In earlier time intermediate features were generated and they were used again for
training another ML model
• But, when you have more data, it is much accurate to train from original data against the
result information we expect
Source: https://www.youtube.com/watch?v=bkVCAk9Nsss
Multi-Task Learning
• Different tasks (e.g.: News Summarization, News Sentiment Analysis)
need different labeled datasets which are rare
• The available datasets may be insufficient in size to train a model with
a sufficient level of accuracy level
• When the business need is updated new ML tasks emerge where
there are no labeled datasets to train
• In order to address the above problems we need to have a way to
learn more than one task at a time where a new task can be possible
to be trained with the same model without much data and with a
higher speed, which is known as Multi-Task Learning
Examples for Multi-Task Learning
Source: https://www.youtube.com/watch?v=bkVCAk9Nsss
Assumption of Multi-Task Learning
• In order to learn in the multi-task manner each task should share some
structure
• Otherwise, single-task learning is better to be used
• Fortunately, most of the task have common structures. E.g.:
• Share the same laws of physics
• Languages like English and French share common patterns due to historical reasons
• Psychology and physiology of humans are very similar
Source: https://www.youtube.com/watch?v=bkVCAk9Nsss
Notations of Multi-Task Learning
• In multi-task learning, a new variable zi known as Task Descriptor is added
to the approximation function which is generally a one-hot encoded vector
• Task descriptor encodes the task
Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
Encoding the Task Descriptor in NN
Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
Weighted Multi-Task Learning
• Instead of giving an equal weight to each of the task during the training
different weights can be given on different criteria like,
• Manually setting a priority based weight
• Dynamically adjusting during the training process
• This weight is given to the loss function during the optimization
Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
Training With Vanilla Multi-Task Learning
Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
Introduction to Transfer Learning
• Transfer Learning refers to the process of leveraging knowledge
gained from solving one problem and applying it to a different, but
related, problem
• Unlike in traditional ML, where models are trained to perform a
specific task on a specific dataset, Transfer Learning allows to transfer
knowledge from one task/domain to another. This improves the
performance of the target task, especially when labeled data for the
target task is limited or expensive to obtain
• E.g.: In order to train a cat image classifier, you can use a pre-trained
CNN using the huge ImageNet dataset with many miscellaneous
images and then train only the last few layers of the CNN, with the
available cat image dataset which is smaller in size
Motivation of Transfer Learning
• Scarcity of Labeled Data: Annotated datasets required for training
machine learning models are often scarce and expensive to acquire.
Transfer learning mitigates this issue by utilizing knowledge from
related tasks or domains
• Model Generalization: By transferring knowledge from a pre-trained
model, the model can generalize better to new tasks or domains,
even with limited data
• Efficiency: Transfer learning can significantly reduce the
computational resources and time required for training models from
scratch, making it a practical approach in various real-world scenarios
Types of Transfer Learning
1.Inductive Transfer Learning: Involves transferring knowledge from a source
domain to a target domain by learning a new task in the target domain using
the knowledge gained from solving a related task in the source domain
Example: Suppose you have a model trained to classify different types of
fruits based on images in one dataset (source domain). You can then use the
knowledge gained from this task to classify different types of vegetables
based on images in a separate dataset (target domain)
2.Transductive Transfer Learning: Focuses on adapting a model to a new
domain where the target data distribution may differ from the source domain.
Instead of learning a new task, transductive transfer learning aims to adapt
the model to perform well on the target domain.
Example: Let's say you have a model trained on data from one country
(source domain) to predict housing prices. However, when you try to apply
this model to a different country (target domain), you encounter differences
in housing market dynamics. Transductive transfer learning involves
adapting the model to the target domain's characteristics without explicitly
learning a new task
Pre-Trained Models
• Specific models can be developed by training available small labeled
data with supervised learning on top of the commonly available pre-
trained models
• Large generic datasets like ImageNet and GPT models are some of the
examples for the pre-trained models
• ImageNet is an example for a large labeled dataset
• However, there are many unsupervised pre-trained models available
as open source content such as large language models like GPT
models and BERT models
Transfer Learning via Fine Tuning
• The pre-trained model for source data is trained again for the target
domain data
• Sometimes, all the layers of the NN are trained,
• Either a small Learning Rate is used for all the layers
• Or smaller Learning Rates are used for earlier layers
• Sometimes, train only the last layers while freezing the earlier layers and
gradually the unfreezing the earlier layers
• Sometimes, only the last one or few layers are trained while other layers
keeping frozen
• When the target task is simpler than the source task no need to update earlier layers
• Best techniques/hyperparameters are selected with cross-validation
Transfer Learning via Fine Tuning
• Overfitting can be mitigated by Early Stopping technique
• New layers can be added and initialized with Random Initialization
while keeping the earlier layers as they are
Unintuitive Facts about Transfer Learning
• When the pre-training is done with unsupervised ML and fine tuned with supervised ML
(e.g. Transformer models), you don’t need that much diverse data to pre-train
• You can use the same target dataset for pre-training without much sacrifice of the
accuracy!
• This may change when both pre-training and fine tuning is done with supervised ML
Source: https://www.youtube.com/watch?v=bVjCjdq06R4
Unintuitive Facts about Transfer Learning
• Selecting the last layer of a NN may not be the best layer to be fine tuned
• For different scenarios some middle layers may perform better when selected than a full
fine tuning
Source: https://www.youtube.com/watch?v=bVjCjdq06R4
Rule of Thumb for Transfer Learning
Source: https://www.youtube.com/watch?v=bVjCjdq06R4
Meta Learning
• “Given a set of training tasks, can we optimize for the ability to learn
these tasks quickly, so that we can learn new tasks quickly too?”
• This is what is achieved by Meta Learning
• In other words optimization for transferability is known as Meta Learning
Source: https://www.youtube.com/watch?v=bVjCjdq06R4
Two Views of Meta Learning Algorithms
Source: https://www.youtube.com/watch?v=bVjCjdq06R4
Bayes View of Meta Learning
• yi,j label value probabilities are
dependent on 𝜙𝑖 parameter probabilities
of the model of a task
• All the 𝜙𝑖 parameter probabilities for all
the tasks are dependent on the meta
level parameters 𝜃
• If 𝜙𝑖 are independent for each task i,
then 𝜃 has no information and vice versa
• Learning for 𝜃 is the idea of Meta
Learning
Source: https://www.youtube.com/watch?v=bVjCjdq06R4
Mechanistic View of Meta Learning
• yi,j label value probabilities are dependent on 𝜙𝑖 parameter probabilities of the model of a task
• All the 𝜙𝑖 parameter probabilities for all the tasks are dependent on the meta level
parameters 𝜃
• If 𝜙𝑖 are independent for each task i, then 𝜃 has no information and vice versa
• Learning for 𝜃 is the idea of Meta Learning
Source: https://www.youtube.com/watch?v=bVjCjdq06R4
Questions?

Contenu connexe

Similaire à Lecture 11 - Advance Learning Techniques

Eurodidaweb2014 03-17 21 day 3-4
Eurodidaweb2014 03-17 21 day 3-4Eurodidaweb2014 03-17 21 day 3-4
Eurodidaweb2014 03-17 21 day 3-4Stefano Lariccia
 
Deltek Cobra Advanced Training
Deltek Cobra Advanced TrainingDeltek Cobra Advanced Training
Deltek Cobra Advanced TrainingTen Six Consulting
 
Introducing C7 Teaching and Learning
Introducing C7 Teaching and LearningIntroducing C7 Teaching and Learning
Introducing C7 Teaching and LearningAllan Carrington
 
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f..."Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...Edge AI and Vision Alliance
 
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
 
Using Public Datasets with TensorFlow.pptx
Using Public Datasets with TensorFlow.pptxUsing Public Datasets with TensorFlow.pptx
Using Public Datasets with TensorFlow.pptxgiddijukho
 
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...Lucidworks
 
No BS Guide to Deep Learning in the Enterprise
No BS Guide to Deep Learning in the EnterpriseNo BS Guide to Deep Learning in the Enterprise
No BS Guide to Deep Learning in the EnterpriseJesus Rodriguez
 
ODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLPODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLPindico data
 
Comparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksComparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksVincenzo Lomonaco
 
Frontier in reinforcement learning
Frontier in reinforcement learningFrontier in reinforcement learning
Frontier in reinforcement learningJie-Han Chen
 
Transfer learning with real world applications in deep learning
Transfer learning with real world applications in deep learningTransfer learning with real world applications in deep learning
Transfer learning with real world applications in deep learningRahat Yasir
 
Transfer Learning in NLP: A Survey
Transfer Learning in NLP: A SurveyTransfer Learning in NLP: A Survey
Transfer Learning in NLP: A SurveyNUPUR YADAV
 
Instructional software ab
Instructional software abInstructional software ab
Instructional software abadamb01
 
Self training improves_nlu
Self training improves_nlu Self training improves_nlu
Self training improves_nlu taeseon ryu
 
Deep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim Hunter
Deep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim HunterDeep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim Hunter
Deep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim HunterDatabricks
 
Adaptive Navigation Support and Open Social Learner Modeling for PAL
Adaptive Navigation Support and Open Social Learner Modeling for PALAdaptive Navigation Support and Open Social Learner Modeling for PAL
Adaptive Navigation Support and Open Social Learner Modeling for PALPeter Brusilovsky
 

Similaire à Lecture 11 - Advance Learning Techniques (20)

Eurodidaweb2014 03-17 21 day 3-4
Eurodidaweb2014 03-17 21 day 3-4Eurodidaweb2014 03-17 21 day 3-4
Eurodidaweb2014 03-17 21 day 3-4
 
Deltek Cobra Advanced Training
Deltek Cobra Advanced TrainingDeltek Cobra Advanced Training
Deltek Cobra Advanced Training
 
Introducing C7 Teaching and Learning
Introducing C7 Teaching and LearningIntroducing C7 Teaching and Learning
Introducing C7 Teaching and Learning
 
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f..."Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
 
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.
 
Using Public Datasets with TensorFlow.pptx
Using Public Datasets with TensorFlow.pptxUsing Public Datasets with TensorFlow.pptx
Using Public Datasets with TensorFlow.pptx
 
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
Enriching Solr with Deep Learning for a Question Answering System - Sanket Sh...
 
No BS Guide to Deep Learning in the Enterprise
No BS Guide to Deep Learning in the EnterpriseNo BS Guide to Deep Learning in the Enterprise
No BS Guide to Deep Learning in the Enterprise
 
ODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLPODSC East: Effective Transfer Learning for NLP
ODSC East: Effective Transfer Learning for NLP
 
Field study 3 ep7
Field study 3 ep7Field study 3 ep7
Field study 3 ep7
 
Comparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksComparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural Networks
 
Frontier in reinforcement learning
Frontier in reinforcement learningFrontier in reinforcement learning
Frontier in reinforcement learning
 
Transfer learning with real world applications in deep learning
Transfer learning with real world applications in deep learningTransfer learning with real world applications in deep learning
Transfer learning with real world applications in deep learning
 
Transfer Learning in NLP: A Survey
Transfer Learning in NLP: A SurveyTransfer Learning in NLP: A Survey
Transfer Learning in NLP: A Survey
 
Instructional software ab
Instructional software abInstructional software ab
Instructional software ab
 
Oop concepts
Oop conceptsOop concepts
Oop concepts
 
Remarks on MOOC's
Remarks on MOOC'sRemarks on MOOC's
Remarks on MOOC's
 
Self training improves_nlu
Self training improves_nlu Self training improves_nlu
Self training improves_nlu
 
Deep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim Hunter
Deep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim HunterDeep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim Hunter
Deep-Dive into Deep Learning Pipelines with Sue Ann Hong and Tim Hunter
 
Adaptive Navigation Support and Open Social Learner Modeling for PAL
Adaptive Navigation Support and Open Social Learner Modeling for PALAdaptive Navigation Support and Open Social Learner Modeling for PAL
Adaptive Navigation Support and Open Social Learner Modeling for PAL
 

Plus de Maninda Edirisooriya

Lecture - 10 Transformer Model, Motivation to Transformers, Principles, and ...
Lecture - 10 Transformer Model, Motivation to Transformers, Principles,  and ...Lecture - 10 Transformer Model, Motivation to Transformers, Principles,  and ...
Lecture - 10 Transformer Model, Motivation to Transformers, Principles, and ...Maninda Edirisooriya
 
Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...
Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...
Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...Maninda Edirisooriya
 
Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...
Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...
Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...Maninda Edirisooriya
 
Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...
Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...
Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...Maninda Edirisooriya
 
Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...
Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...
Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...Maninda Edirisooriya
 
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...Maninda Edirisooriya
 
Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...
Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...
Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...Maninda Edirisooriya
 
Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...
Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...
Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...Maninda Edirisooriya
 
Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...
Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...
Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...Maninda Edirisooriya
 
Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...
Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...
Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...Maninda Edirisooriya
 
Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...
Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...
Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...Maninda Edirisooriya
 
Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...
Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...
Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...Maninda Edirisooriya
 
Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...
Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...
Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...Maninda Edirisooriya
 
Analyzing the effectiveness of mobile and web channels using WSO2 BAM
Analyzing the effectiveness of mobile and web channels using WSO2 BAMAnalyzing the effectiveness of mobile and web channels using WSO2 BAM
Analyzing the effectiveness of mobile and web channels using WSO2 BAMManinda Edirisooriya
 

Plus de Maninda Edirisooriya (20)

Lecture - 10 Transformer Model, Motivation to Transformers, Principles, and ...
Lecture - 10 Transformer Model, Motivation to Transformers, Principles,  and ...Lecture - 10 Transformer Model, Motivation to Transformers, Principles,  and ...
Lecture - 10 Transformer Model, Motivation to Transformers, Principles, and ...
 
Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...
Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...
Lecture 9 - Deep Sequence Models, Learn Recurrent Neural Networks (RNN), GRU ...
 
Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...
Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...
Extra Lecture - Support Vector Machines (SVM), a lecture in subject module St...
 
Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...
Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...
Lecture 11 - KNN and Clustering, a lecture in subject module Statistical & Ma...
 
Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...
Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...
Lecture 10 - Model Testing and Evaluation, a lecture in subject module Statis...
 
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
 
Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...
Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...
Lecture 8 - Feature Engineering and Optimization, a lecture in subject module...
 
Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...
Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...
Lecture 7 - Bias, Variance and Regularization, a lecture in subject module St...
 
Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...
Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...
Lecture 6 - Logistic Regression, a lecture in subject module Statistical & Ma...
 
Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...
Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...
Lecture 5 - Gradient Descent, a lecture in subject module Statistical & Machi...
 
Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...
Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...
Lecture 4 - Linear Regression, a lecture in subject module Statistical & Mach...
 
Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...
Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...
Lecture 3 - Exploratory Data Analytics (EDA), a lecture in subject module Sta...
 
Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...
Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...
Lecture 2 - Introduction to Machine Learning, a lecture in subject module Sta...
 
Analyzing the effectiveness of mobile and web channels using WSO2 BAM
Analyzing the effectiveness of mobile and web channels using WSO2 BAMAnalyzing the effectiveness of mobile and web channels using WSO2 BAM
Analyzing the effectiveness of mobile and web channels using WSO2 BAM
 
WSO2 BAM - Your big data toolbox
WSO2 BAM - Your big data toolboxWSO2 BAM - Your big data toolbox
WSO2 BAM - Your big data toolbox
 
Training Report
Training ReportTraining Report
Training Report
 
GViz - Project Report
GViz - Project ReportGViz - Project Report
GViz - Project Report
 
Mortivation
MortivationMortivation
Mortivation
 
Hafnium impact 2008
Hafnium impact 2008Hafnium impact 2008
Hafnium impact 2008
 
ChatCrypt
ChatCryptChatCrypt
ChatCrypt
 

Dernier

Democratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek AryaDemocratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek Aryaabh.arya
 
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGBRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGKOUSTAV SARKAR
 
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdfONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdfKamal Acharya
 
Dairy management system project report..pdf
Dairy management system project report..pdfDairy management system project report..pdf
Dairy management system project report..pdfKamal Acharya
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdfKamal Acharya
 
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and VisualizationKIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and VisualizationDr. Radhey Shyam
 
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxCloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxMd. Shahidul Islam Prodhan
 
A case study of cinema management system project report..pdf
A case study of cinema management system project report..pdfA case study of cinema management system project report..pdf
A case study of cinema management system project report..pdfKamal Acharya
 
Construction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptxConstruction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptxwendy cai
 
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...Roi Lipman
 
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringKIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringDr. Radhey Shyam
 
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxCFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
 
Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...
Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...
Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...Aimil Ltd
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdfKamal Acharya
 
Online book store management system project.pdf
Online book store management system project.pdfOnline book store management system project.pdf
Online book store management system project.pdfKamal Acharya
 
Online resume builder management system project report.pdf
Online resume builder management system project report.pdfOnline resume builder management system project report.pdf
Online resume builder management system project report.pdfKamal Acharya
 
The Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfThe Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfPipe Restoration Solutions
 
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical EngineeringIntroduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical EngineeringC Sai Kiran
 
Explosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdfExplosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdf884710SadaqatAli
 
2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edgePaco Orozco
 

Dernier (20)

Democratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek AryaDemocratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek Arya
 
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGBRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
 
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdfONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
 
Dairy management system project report..pdf
Dairy management system project report..pdfDairy management system project report..pdf
Dairy management system project report..pdf
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdf
 
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and VisualizationKIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
 
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxCloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
 
A case study of cinema management system project report..pdf
A case study of cinema management system project report..pdfA case study of cinema management system project report..pdf
A case study of cinema management system project report..pdf
 
Construction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptxConstruction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptx
 
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
The battle for RAG, explore the pros and cons of using KnowledgeGraphs and Ve...
 
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringKIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
 
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxCFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
 
Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...
Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...
Soil Testing Instruments by aimil ltd.- California Bearing Ratio apparatus, c...
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
 
Online book store management system project.pdf
Online book store management system project.pdfOnline book store management system project.pdf
Online book store management system project.pdf
 
Online resume builder management system project report.pdf
Online resume builder management system project report.pdfOnline resume builder management system project report.pdf
Online resume builder management system project report.pdf
 
The Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdfThe Benefits and Techniques of Trenchless Pipe Repair.pdf
The Benefits and Techniques of Trenchless Pipe Repair.pdf
 
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical EngineeringIntroduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-5 Notes for II-II Mechanical Engineering
 
Explosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdfExplosives Industry manufacturing process.pdf
Explosives Industry manufacturing process.pdf
 
2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge
 

Lecture 11 - Advance Learning Techniques

  • 1. DA 5330 – Advanced Machine Learning Applications Lecture 11 – Advanced Learning Techniques Maninda Edirisooriya manindaw@uom.lk
  • 2. End-to-End Learning • In earlier time intermediate features were generated and they were used again for training another ML model • But, when you have more data, it is much accurate to train from original data against the result information we expect Source: https://www.youtube.com/watch?v=bkVCAk9Nsss
  • 3. Multi-Task Learning • Different tasks (e.g.: News Summarization, News Sentiment Analysis) need different labeled datasets which are rare • The available datasets may be insufficient in size to train a model with a sufficient level of accuracy level • When the business need is updated new ML tasks emerge where there are no labeled datasets to train • In order to address the above problems we need to have a way to learn more than one task at a time where a new task can be possible to be trained with the same model without much data and with a higher speed, which is known as Multi-Task Learning
  • 4. Examples for Multi-Task Learning Source: https://www.youtube.com/watch?v=bkVCAk9Nsss
  • 5. Assumption of Multi-Task Learning • In order to learn in the multi-task manner each task should share some structure • Otherwise, single-task learning is better to be used • Fortunately, most of the task have common structures. E.g.: • Share the same laws of physics • Languages like English and French share common patterns due to historical reasons • Psychology and physiology of humans are very similar Source: https://www.youtube.com/watch?v=bkVCAk9Nsss
  • 6. Notations of Multi-Task Learning • In multi-task learning, a new variable zi known as Task Descriptor is added to the approximation function which is generally a one-hot encoded vector • Task descriptor encodes the task Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
  • 7. Encoding the Task Descriptor in NN Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
  • 8. Weighted Multi-Task Learning • Instead of giving an equal weight to each of the task during the training different weights can be given on different criteria like, • Manually setting a priority based weight • Dynamically adjusting during the training process • This weight is given to the loss function during the optimization Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
  • 9. Training With Vanilla Multi-Task Learning Source: https://www.youtube.com/watch?v=vI46tzt4O7Y
  • 10. Introduction to Transfer Learning • Transfer Learning refers to the process of leveraging knowledge gained from solving one problem and applying it to a different, but related, problem • Unlike in traditional ML, where models are trained to perform a specific task on a specific dataset, Transfer Learning allows to transfer knowledge from one task/domain to another. This improves the performance of the target task, especially when labeled data for the target task is limited or expensive to obtain • E.g.: In order to train a cat image classifier, you can use a pre-trained CNN using the huge ImageNet dataset with many miscellaneous images and then train only the last few layers of the CNN, with the available cat image dataset which is smaller in size
  • 11. Motivation of Transfer Learning • Scarcity of Labeled Data: Annotated datasets required for training machine learning models are often scarce and expensive to acquire. Transfer learning mitigates this issue by utilizing knowledge from related tasks or domains • Model Generalization: By transferring knowledge from a pre-trained model, the model can generalize better to new tasks or domains, even with limited data • Efficiency: Transfer learning can significantly reduce the computational resources and time required for training models from scratch, making it a practical approach in various real-world scenarios
  • 12. Types of Transfer Learning 1.Inductive Transfer Learning: Involves transferring knowledge from a source domain to a target domain by learning a new task in the target domain using the knowledge gained from solving a related task in the source domain Example: Suppose you have a model trained to classify different types of fruits based on images in one dataset (source domain). You can then use the knowledge gained from this task to classify different types of vegetables based on images in a separate dataset (target domain) 2.Transductive Transfer Learning: Focuses on adapting a model to a new domain where the target data distribution may differ from the source domain. Instead of learning a new task, transductive transfer learning aims to adapt the model to perform well on the target domain. Example: Let's say you have a model trained on data from one country (source domain) to predict housing prices. However, when you try to apply this model to a different country (target domain), you encounter differences in housing market dynamics. Transductive transfer learning involves adapting the model to the target domain's characteristics without explicitly learning a new task
  • 13. Pre-Trained Models • Specific models can be developed by training available small labeled data with supervised learning on top of the commonly available pre- trained models • Large generic datasets like ImageNet and GPT models are some of the examples for the pre-trained models • ImageNet is an example for a large labeled dataset • However, there are many unsupervised pre-trained models available as open source content such as large language models like GPT models and BERT models
  • 14. Transfer Learning via Fine Tuning • The pre-trained model for source data is trained again for the target domain data • Sometimes, all the layers of the NN are trained, • Either a small Learning Rate is used for all the layers • Or smaller Learning Rates are used for earlier layers • Sometimes, train only the last layers while freezing the earlier layers and gradually the unfreezing the earlier layers • Sometimes, only the last one or few layers are trained while other layers keeping frozen • When the target task is simpler than the source task no need to update earlier layers • Best techniques/hyperparameters are selected with cross-validation
  • 15. Transfer Learning via Fine Tuning • Overfitting can be mitigated by Early Stopping technique • New layers can be added and initialized with Random Initialization while keeping the earlier layers as they are
  • 16. Unintuitive Facts about Transfer Learning • When the pre-training is done with unsupervised ML and fine tuned with supervised ML (e.g. Transformer models), you don’t need that much diverse data to pre-train • You can use the same target dataset for pre-training without much sacrifice of the accuracy! • This may change when both pre-training and fine tuning is done with supervised ML Source: https://www.youtube.com/watch?v=bVjCjdq06R4
  • 17. Unintuitive Facts about Transfer Learning • Selecting the last layer of a NN may not be the best layer to be fine tuned • For different scenarios some middle layers may perform better when selected than a full fine tuning Source: https://www.youtube.com/watch?v=bVjCjdq06R4
  • 18. Rule of Thumb for Transfer Learning Source: https://www.youtube.com/watch?v=bVjCjdq06R4
  • 19. Meta Learning • “Given a set of training tasks, can we optimize for the ability to learn these tasks quickly, so that we can learn new tasks quickly too?” • This is what is achieved by Meta Learning • In other words optimization for transferability is known as Meta Learning Source: https://www.youtube.com/watch?v=bVjCjdq06R4
  • 20. Two Views of Meta Learning Algorithms Source: https://www.youtube.com/watch?v=bVjCjdq06R4
  • 21. Bayes View of Meta Learning • yi,j label value probabilities are dependent on 𝜙𝑖 parameter probabilities of the model of a task • All the 𝜙𝑖 parameter probabilities for all the tasks are dependent on the meta level parameters 𝜃 • If 𝜙𝑖 are independent for each task i, then 𝜃 has no information and vice versa • Learning for 𝜃 is the idea of Meta Learning Source: https://www.youtube.com/watch?v=bVjCjdq06R4
  • 22. Mechanistic View of Meta Learning • yi,j label value probabilities are dependent on 𝜙𝑖 parameter probabilities of the model of a task • All the 𝜙𝑖 parameter probabilities for all the tasks are dependent on the meta level parameters 𝜃 • If 𝜙𝑖 are independent for each task i, then 𝜃 has no information and vice versa • Learning for 𝜃 is the idea of Meta Learning Source: https://www.youtube.com/watch?v=bVjCjdq06R4