SlideShare a Scribd company logo
1 of 36
Machine Learning and
A Walk through School Exams!
Introduction to
Artificial Intelligence
SPEAKER IMAGE
Ramsha Siddiqui
Associate Data Scientist (NLP)
i2c inc. Lahore, Pakistan
โ— ๐Ÿ’ฌ Conversational AI and Dialog Systems.
โ— ๐Ÿ‘ฉ๐Ÿ’ป Google Developers Group, Lahore.
โ— ๐Ÿฅ‡ WTM and WDA Scholar, 2018-2020.
โ— ๐ŸŽ“ FAST NUCES, Lahore - Spring, 2019.
โ— โœˆ๏ธ Global UGRAD Alumnus - UIW, Texas.
โ— ๐Ÿ’ผ Co-Founder of Startup - FunKadaa.
What is Machine Learning?
Machine Learning is the application of
Artificial Intelligence that allows machines to
learn and improve from experience, without
being explicitly programmed, to solve almost
any problem in the world.
How do humans learn?
The Life of a Student
1. Gather Knowledge
The Life of a Student
1. Gather Knowledge 2. Extract Concepts
The Life of a Student
2. Extract Concepts
3. Practice Concepts
1. Gather Knowledge
The Life of a Student
3. Practice Concepts 4. Test Yourself
1. Gather Knowledge 2. Extract Concepts
Learning Chess!
3. Practice 4. Compete!
1. Learn Pieces and Moves 2. Understand & Memorize
How do machines learn?
1. Gather Training Data
The initial set of data-points required to learn
about a problem, in order to solve it.
2. Data Preprocessing
Analyzing Data and Extracting or Deriving useful
features from it, in efforts to improve results.
Why is it important?
3. Model Selection / Construction
An algorithm / mathematical derivation
containing variables that can be derived /
learned from Training Data is called a
Machine Learning Model.
The values of the variables are saved after
training to be used for predictions later.
3. Model Selection / Construction
Selecting the right โ€œkind of modelโ€ for your
Machine Learning is also important, because
feature-learning / data-understanding is an
internal process for machines, and certain
types of problems are more well-suited for
certain types of algorithms.
Letโ€™s look at the two broadest types!
Supervised
Learning
When a Modelโ€™s Expected
Outputs are defined, itโ€™s called a
Supervised Learning Problem. It
mainly has two sub-categories:
โ— Classification (categorizing
input data into classes)
โ— Regression (predicting a
continuous / real value instead
of an output class-label)
Example: Facial Recognition
Recognizing peopleโ€™s faces and its features (eyes, head-pose, etc.)
Example: Facial Recognition
Convolutional Neural Networks (CNNs) have been classically useful for
the task of identifying different components / features of images.
Example: Speech Recognition
Converting Audio Sequences
(Speech) into Text Sequences.
Example: Speech Recognition
Sequence to Sequence Networks (Seq2Seq) have so far shown
promising results for this task (with updated research and
architectures being released almost every day!)
Example: Covid Projection
Predicting the number of Covid-Cases every other day / month.
Example: Covid Projection
Time-Series Forecasting is a common problem in Machine Learning,
and all models used for that task, can be trained here for comparison.
A Note: Some of these problems such as
โ— Image Classification
โ— Text Classification, etc.
youโ€™ll find that some Model Architectures are also problem-
favorable, as theyโ€™ve shown good results before. Itโ€™s always
wise for you to do some Research beforehand to find
good Model Implementations / Datasets on the task youโ€™re
working on, before starting from scratch.
Unsupervised
Learning
When a Modelโ€™s Expected
Outputs are undefined, and
input-data only needs to be
clustered or segmented into
somewhat meaningful groups, itโ€™s
called Unsupervised Learning.
Example:
โ— K-Means Algorithm (Finds
Cluster Centroids based on
the no. of centers defined = K)
Example: Topic Modeling
Training a model to learn the topic of a document based on the correlations of
different words used inside it, without knowing prior what those topics are.
A Note: Know your Problem Domain!
4. Model Training
Feeding your Input Data to your Model for learning - is
called Model Training. Hereโ€™s some things you may wanna
do before that:
โ— Data Folds: Splitting your Training Data into two sets:
One for Training on, and one for Validating
Performance.
โ— Epochs: The number of times your model sees the
Training Data (revising it).
โ— Model Parameters: Take out a set of possible
parameter values that you want to tweak in your model.
Example: w1*x1 + w2*x2 + w3*x3 = y
where for every example, we have input-values โ€œxโ€ and model-variables
โ€œwโ€.
5. Model Testing
Alas, models canโ€™t escape examinations either. After Training a Model, we want
to see Model Predictions, and compare the values that model got with those it
got incorrect, and evaluate overall performance.
Choosing the right performance metric matters and varies per problem!
Task Performance
On average, most humans and models are able
to learn almost any task following this method.
In terms of performance comparisons
however, sometimes we:
โ— Underachieve
โ— Overachieve
Underachieving
Reasons:
โ— Unseen Test Data: If the data in the examination is totally
unrelated to the Train Data, then the model will get confused.
Evenly distribute your data between Train and Test Sets.
โ— Insufficient Training Data: Perhaps the amount of Training
Data is insufficient / too difficult to learn anything useful
from.
Add more data or try new features.
โ— Model Architecture: The Model selected for a particular
task may not be the right choice for it.
Overachieving
Reasons:
โ— Randomness: Sometimes itโ€™s just dumb luck. (Models are
initialized with Random Variable Values).
โ— Model Pretraining: If your Model was trained on a task
similar to this one before and has a good memory, it may
perform well even if your Training Data was pretty small /
useless.
A lot of research is going into pre-training these days!
Model Predictions
In order to trust that our modelโ€™s are working correctly, itโ€™s
always a good idea to provide additional explainability with the
model output like:
โ— Confidence Score(s)
โ— Input Features
Letโ€™s quickly Train a Model:
https://teachablemachine.withgoogle.com/
Thank you!
Any questions?
Find me: ramsha@gdglahore.com

More Related Content

What's hot

RecSys 2016 Talk: Feature Selection For Human Recommenders
RecSys 2016 Talk: Feature Selection For Human RecommendersRecSys 2016 Talk: Feature Selection For Human Recommenders
RecSys 2016 Talk: Feature Selection For Human RecommendersKatherine Livins
ย 
Supervised Machine Learning
Supervised Machine LearningSupervised Machine Learning
Supervised Machine LearningAnkit Rai
ย 
Machine learning overview
Machine learning overviewMachine learning overview
Machine learning overviewprih_yah
ย 
Supervised Unsupervised and Reinforcement Learning
Supervised Unsupervised and Reinforcement Learning Supervised Unsupervised and Reinforcement Learning
Supervised Unsupervised and Reinforcement Learning Aakash Chotrani
ย 
Types of Machine Learning
Types of Machine LearningTypes of Machine Learning
Types of Machine LearningSamra Shahzadi
ย 
Unsupervised Machine Learning Ml And How It Works
Unsupervised Machine Learning Ml And How It WorksUnsupervised Machine Learning Ml And How It Works
Unsupervised Machine Learning Ml And How It WorksSlideTeam
ย 
detailed Presentation on supervised learning
 detailed Presentation on supervised learning detailed Presentation on supervised learning
detailed Presentation on supervised learningZAMANCHBWN
ย 
Machine learning and types
Machine learning and typesMachine learning and types
Machine learning and typesPadma Metta
ย 
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...Simplilearn
ย 
Barcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons LearnedBarcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons LearnedXavier Amatriain
ย 
supervised learning
supervised learningsupervised learning
supervised learningAmar Tripathi
ย 
Guide to end end machine learning projects
Guide to end end machine learning projectsGuide to end end machine learning projects
Guide to end end machine learning projectsSkyl.ai
ย 
Machine learning
Machine learningMachine learning
Machine learningMohit Bishnoi
ย 
Machine Learning: Applications, Process and Techniques
Machine Learning: Applications, Process and TechniquesMachine Learning: Applications, Process and Techniques
Machine Learning: Applications, Process and TechniquesRui Pedro Paiva
ย 
Machine learning
Machine learning Machine learning
Machine learning Saurabh Agrawal
ย 
Cmpe 255 cross validation
Cmpe 255 cross validationCmpe 255 cross validation
Cmpe 255 cross validationAbraham Kong
ย 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Xavier Amatriain
ย 

What's hot (20)

RecSys 2016 Talk: Feature Selection For Human Recommenders
RecSys 2016 Talk: Feature Selection For Human RecommendersRecSys 2016 Talk: Feature Selection For Human Recommenders
RecSys 2016 Talk: Feature Selection For Human Recommenders
ย 
Supervised Machine Learning
Supervised Machine LearningSupervised Machine Learning
Supervised Machine Learning
ย 
Machine learning overview
Machine learning overviewMachine learning overview
Machine learning overview
ย 
Supervised Unsupervised and Reinforcement Learning
Supervised Unsupervised and Reinforcement Learning Supervised Unsupervised and Reinforcement Learning
Supervised Unsupervised and Reinforcement Learning
ย 
Types of Machine Learning
Types of Machine LearningTypes of Machine Learning
Types of Machine Learning
ย 
Unsupervised Machine Learning Ml And How It Works
Unsupervised Machine Learning Ml And How It WorksUnsupervised Machine Learning Ml And How It Works
Unsupervised Machine Learning Ml And How It Works
ย 
Machine learning
Machine learningMachine learning
Machine learning
ย 
detailed Presentation on supervised learning
 detailed Presentation on supervised learning detailed Presentation on supervised learning
detailed Presentation on supervised learning
ย 
Machine learning and types
Machine learning and typesMachine learning and types
Machine learning and types
ย 
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
Supervised and Unsupervised Learning In Machine Learning | Machine Learning T...
ย 
Barcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons LearnedBarcelona ML Meetup - Lessons Learned
Barcelona ML Meetup - Lessons Learned
ย 
supervised learning
supervised learningsupervised learning
supervised learning
ย 
Guide to end end machine learning projects
Guide to end end machine learning projectsGuide to end end machine learning projects
Guide to end end machine learning projects
ย 
Machine Learning
Machine Learning Machine Learning
Machine Learning
ย 
Supervised learning
  Supervised learning  Supervised learning
Supervised learning
ย 
Machine learning
Machine learningMachine learning
Machine learning
ย 
Machine Learning: Applications, Process and Techniques
Machine Learning: Applications, Process and TechniquesMachine Learning: Applications, Process and Techniques
Machine Learning: Applications, Process and Techniques
ย 
Machine learning
Machine learning Machine learning
Machine learning
ย 
Cmpe 255 cross validation
Cmpe 255 cross validationCmpe 255 cross validation
Cmpe 255 cross validation
ย 
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
Recsys 2016 tutorial: Lessons learned from building real-life recommender sys...
ย 

Similar to Machine learning: A Walk Through School Exams

Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learningShareDocView.com
ย 
Afternoons with Azure - Azure Machine Learning
Afternoons with Azure - Azure Machine Learning Afternoons with Azure - Azure Machine Learning
Afternoons with Azure - Azure Machine Learning CCG
ย 
Introduction to ML (Machine Learning)
Introduction to ML (Machine Learning)Introduction to ML (Machine Learning)
Introduction to ML (Machine Learning)SwatiTripathi44
ย 
Machine-Learning-Overview a statistical approach
Machine-Learning-Overview a statistical approachMachine-Learning-Overview a statistical approach
Machine-Learning-Overview a statistical approachAjit Ghodke
ย 
Overview of machine learning
Overview of machine learning Overview of machine learning
Overview of machine learning SolivarLabs
ย 
introduction to machine learning
introduction to machine learningintroduction to machine learning
introduction to machine learningJohnson Ubah
ย 
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MAHIRA
ย 
ML_Module_1.pdf
ML_Module_1.pdfML_Module_1.pdf
ML_Module_1.pdfJafarHussain48
ย 
Choosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your needChoosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your needGibDevs
ย 
ML crash course
ML crash courseML crash course
ML crash coursemikaelhuss
ย 
Barga Data Science lecture 2
Barga Data Science lecture 2Barga Data Science lecture 2
Barga Data Science lecture 2Roger Barga
ย 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflowCharmi Chokshi
ย 
Machine Learning
Machine LearningMachine Learning
Machine Learningpradeepskvch
ย 
2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptxgdgsurrey
ย 
Managing machine learning
Managing machine learningManaging machine learning
Managing machine learningDavid Murgatroyd
ย 
Introduction to Machine learning
Introduction to Machine learningIntroduction to Machine learning
Introduction to Machine learningKnoldus Inc.
ย 
Machine learning (domingo's paper)
Machine learning (domingo's paper)Machine learning (domingo's paper)
Machine learning (domingo's paper)Akhilesh Joshi
ย 
Machine Learning vs Decision Optimization comparison
Machine Learning vs Decision Optimization comparisonMachine Learning vs Decision Optimization comparison
Machine Learning vs Decision Optimization comparisonAlain Chabrier
ย 

Similar to Machine learning: A Walk Through School Exams (20)

Andrew NG machine learning
Andrew NG machine learningAndrew NG machine learning
Andrew NG machine learning
ย 
Afternoons with Azure - Azure Machine Learning
Afternoons with Azure - Azure Machine Learning Afternoons with Azure - Azure Machine Learning
Afternoons with Azure - Azure Machine Learning
ย 
Introduction to ML (Machine Learning)
Introduction to ML (Machine Learning)Introduction to ML (Machine Learning)
Introduction to ML (Machine Learning)
ย 
Machine-Learning-Overview a statistical approach
Machine-Learning-Overview a statistical approachMachine-Learning-Overview a statistical approach
Machine-Learning-Overview a statistical approach
ย 
Overview of machine learning
Overview of machine learning Overview of machine learning
Overview of machine learning
ย 
introduction to machine learning
introduction to machine learningintroduction to machine learning
introduction to machine learning
ย 
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
ย 
ML_Module_1.pdf
ML_Module_1.pdfML_Module_1.pdf
ML_Module_1.pdf
ย 
Choosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your needChoosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your need
ย 
ML crash course
ML crash courseML crash course
ML crash course
ย 
Barga Data Science lecture 2
Barga Data Science lecture 2Barga Data Science lecture 2
Barga Data Science lecture 2
ย 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
ย 
AI PROJECT CYCLE.pptx
AI PROJECT CYCLE.pptxAI PROJECT CYCLE.pptx
AI PROJECT CYCLE.pptx
ย 
Machine Learning
Machine LearningMachine Learning
Machine Learning
ย 
2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx
ย 
Managing machine learning
Managing machine learningManaging machine learning
Managing machine learning
ย 
Introduction to Machine learning
Introduction to Machine learningIntroduction to Machine learning
Introduction to Machine learning
ย 
Machine Learning_Unit 2_Full.ppt.pdf
Machine Learning_Unit 2_Full.ppt.pdfMachine Learning_Unit 2_Full.ppt.pdf
Machine Learning_Unit 2_Full.ppt.pdf
ย 
Machine learning (domingo's paper)
Machine learning (domingo's paper)Machine learning (domingo's paper)
Machine learning (domingo's paper)
ย 
Machine Learning vs Decision Optimization comparison
Machine Learning vs Decision Optimization comparisonMachine Learning vs Decision Optimization comparison
Machine Learning vs Decision Optimization comparison
ย 

Recently uploaded

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
ย 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
ย 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
ย 
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
ย 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesBoston Institute of Analytics
ย 
Scaling API-first โ€“ The story of a global engineering organization
Scaling API-first โ€“ The story of a global engineering organizationScaling API-first โ€“ The story of a global engineering organization
Scaling API-first โ€“ The story of a global engineering organizationRadu Cotescu
ย 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
ย 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
ย 
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
ย 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
ย 
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
ย 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
ย 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Principled Technologies
ย 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
ย 
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
ย 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
ย 
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
ย 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
ย 
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
ย 

Recently uploaded (20)

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...
ย 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
ย 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
ย 
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
ย 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
ย 
Scaling API-first โ€“ The story of a global engineering organization
Scaling API-first โ€“ The story of a global engineering organizationScaling API-first โ€“ The story of a global engineering organization
Scaling API-first โ€“ The story of a global engineering organization
ย 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
ย 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
ย 
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
ย 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
ย 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
ย 
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
ย 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
ย 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
ย 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ย 
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
ย 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
ย 
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...
ย 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
ย 
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
ย 

Machine learning: A Walk Through School Exams

  • 1. Machine Learning and A Walk through School Exams! Introduction to Artificial Intelligence
  • 2. SPEAKER IMAGE Ramsha Siddiqui Associate Data Scientist (NLP) i2c inc. Lahore, Pakistan โ— ๐Ÿ’ฌ Conversational AI and Dialog Systems. โ— ๐Ÿ‘ฉ๐Ÿ’ป Google Developers Group, Lahore. โ— ๐Ÿฅ‡ WTM and WDA Scholar, 2018-2020. โ— ๐ŸŽ“ FAST NUCES, Lahore - Spring, 2019. โ— โœˆ๏ธ Global UGRAD Alumnus - UIW, Texas. โ— ๐Ÿ’ผ Co-Founder of Startup - FunKadaa.
  • 3. What is Machine Learning? Machine Learning is the application of Artificial Intelligence that allows machines to learn and improve from experience, without being explicitly programmed, to solve almost any problem in the world.
  • 4. How do humans learn?
  • 5. The Life of a Student 1. Gather Knowledge
  • 6. The Life of a Student 1. Gather Knowledge 2. Extract Concepts
  • 7. The Life of a Student 2. Extract Concepts 3. Practice Concepts 1. Gather Knowledge
  • 8. The Life of a Student 3. Practice Concepts 4. Test Yourself 1. Gather Knowledge 2. Extract Concepts
  • 9. Learning Chess! 3. Practice 4. Compete! 1. Learn Pieces and Moves 2. Understand & Memorize
  • 10. How do machines learn?
  • 11. 1. Gather Training Data The initial set of data-points required to learn about a problem, in order to solve it.
  • 12. 2. Data Preprocessing Analyzing Data and Extracting or Deriving useful features from it, in efforts to improve results.
  • 13. Why is it important?
  • 14. 3. Model Selection / Construction An algorithm / mathematical derivation containing variables that can be derived / learned from Training Data is called a Machine Learning Model. The values of the variables are saved after training to be used for predictions later.
  • 15. 3. Model Selection / Construction Selecting the right โ€œkind of modelโ€ for your Machine Learning is also important, because feature-learning / data-understanding is an internal process for machines, and certain types of problems are more well-suited for certain types of algorithms. Letโ€™s look at the two broadest types!
  • 16. Supervised Learning When a Modelโ€™s Expected Outputs are defined, itโ€™s called a Supervised Learning Problem. It mainly has two sub-categories: โ— Classification (categorizing input data into classes) โ— Regression (predicting a continuous / real value instead of an output class-label)
  • 17. Example: Facial Recognition Recognizing peopleโ€™s faces and its features (eyes, head-pose, etc.)
  • 18. Example: Facial Recognition Convolutional Neural Networks (CNNs) have been classically useful for the task of identifying different components / features of images.
  • 19. Example: Speech Recognition Converting Audio Sequences (Speech) into Text Sequences.
  • 20. Example: Speech Recognition Sequence to Sequence Networks (Seq2Seq) have so far shown promising results for this task (with updated research and architectures being released almost every day!)
  • 21. Example: Covid Projection Predicting the number of Covid-Cases every other day / month.
  • 22. Example: Covid Projection Time-Series Forecasting is a common problem in Machine Learning, and all models used for that task, can be trained here for comparison.
  • 23. A Note: Some of these problems such as โ— Image Classification โ— Text Classification, etc. youโ€™ll find that some Model Architectures are also problem- favorable, as theyโ€™ve shown good results before. Itโ€™s always wise for you to do some Research beforehand to find good Model Implementations / Datasets on the task youโ€™re working on, before starting from scratch.
  • 24. Unsupervised Learning When a Modelโ€™s Expected Outputs are undefined, and input-data only needs to be clustered or segmented into somewhat meaningful groups, itโ€™s called Unsupervised Learning. Example: โ— K-Means Algorithm (Finds Cluster Centroids based on the no. of centers defined = K)
  • 25. Example: Topic Modeling Training a model to learn the topic of a document based on the correlations of different words used inside it, without knowing prior what those topics are.
  • 26. A Note: Know your Problem Domain!
  • 27. 4. Model Training Feeding your Input Data to your Model for learning - is called Model Training. Hereโ€™s some things you may wanna do before that: โ— Data Folds: Splitting your Training Data into two sets: One for Training on, and one for Validating Performance. โ— Epochs: The number of times your model sees the Training Data (revising it). โ— Model Parameters: Take out a set of possible parameter values that you want to tweak in your model.
  • 28. Example: w1*x1 + w2*x2 + w3*x3 = y where for every example, we have input-values โ€œxโ€ and model-variables โ€œwโ€.
  • 29. 5. Model Testing Alas, models canโ€™t escape examinations either. After Training a Model, we want to see Model Predictions, and compare the values that model got with those it got incorrect, and evaluate overall performance. Choosing the right performance metric matters and varies per problem!
  • 31. On average, most humans and models are able to learn almost any task following this method. In terms of performance comparisons however, sometimes we: โ— Underachieve โ— Overachieve
  • 32. Underachieving Reasons: โ— Unseen Test Data: If the data in the examination is totally unrelated to the Train Data, then the model will get confused. Evenly distribute your data between Train and Test Sets. โ— Insufficient Training Data: Perhaps the amount of Training Data is insufficient / too difficult to learn anything useful from. Add more data or try new features. โ— Model Architecture: The Model selected for a particular task may not be the right choice for it.
  • 33. Overachieving Reasons: โ— Randomness: Sometimes itโ€™s just dumb luck. (Models are initialized with Random Variable Values). โ— Model Pretraining: If your Model was trained on a task similar to this one before and has a good memory, it may perform well even if your Training Data was pretty small / useless. A lot of research is going into pre-training these days!
  • 34. Model Predictions In order to trust that our modelโ€™s are working correctly, itโ€™s always a good idea to provide additional explainability with the model output like: โ— Confidence Score(s) โ— Input Features
  • 35. Letโ€™s quickly Train a Model: https://teachablemachine.withgoogle.com/
  • 36. Thank you! Any questions? Find me: ramsha@gdglahore.com