SlideShare a Scribd company logo
1 of 21
Download to read offline
AI and ML study group
CS231n Lectures 1 and 2
Agenda
1. Course overview + Lecture 1 key points
2. Review basic Python concepts
3. Heads up on lecture 2 key points
4. Watch lecture 2
5. Review lecture 2 key points
6. Discussion
7. Review lecture 2 detailed notes (if time)
8. Project?
○ Get the code from lecture 2 and train a model on CIFAR-10.
The course
Home page: http://cs231n.stanford.edu/
Syllabus: http://cs231n.stanford.edu/2017/syllabus.html
Videos:
https://www.youtube.com/playlist?list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zx
k
Google group: https://groups.google.com/forum/#!forum/ml-and-ai-study-group
Course overview
● Understand how to write from scratch, debug and train CNNs
● CPU vs GPU
● Tools
○ Caffe
○ TensorFlow
○ (Py)Torch
Python Basics
https://colab.research.google.com/drive/1NpFaVi2AKWXi0utnI3HCqoZcicgfzVHV
Lecture 1
Video:
https://www.youtube.com/watch?v=vT1JzLTH4G4&list=PL3FW7Lu3i5JvHM8ljYj-z
LfQRF3EO8sYv
Lecture slides:
http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture1.pdf
Key points
● The course is mostly about convolutional neural networks (CNNs) and
computer vision.
● History of computer vision and machine learning - interesting, but not
essential.
● Deep learning really took off from 2012.
● Image.net competition
○ SuperVision (AlexNet) won in 2012
○ Every winner since is a neural network
Interesting points
● SuperVision had 7 layers
● More recent networks have 200+ layers
○ We are now limited by GPU memory!
What can we do with CNNs?
● Visual recognition - image classification
● Object detection - draw bounding boxes.
● Image captioning.
● Action classification.
Why did deep learning take off?
● It’s been around since the 90s.
● CPU / GPU power (Moore’s law)
○ Allowed researchers to explore bigger models
● We have more data than ever before
● Open source tools
Related courses
● CS131 - Undergraduate intro course.
● CS224n - intersection of Deep Learning and natural language processing.
● CS231a - Neural networks for image classification.
● CS331 / CS431 - advanced topics in computer vision.
Resources
Optional text book
http://www.deeplearningbook.org/
Image.net
14m+ images organised in 22k categories
http://www.image-net.org/
Example data sets
https://en.wikipedia.org/wiki/List_of_datasets_for_machine_learning_research
Lecture 2
Video:
https://www.youtube.com/watch?v=OoUX-nOEjG0&index=3&list=PLC1qU-LWwrF64f4QKQT
-Vg5Wr4qEE1Zxk&t=9s
Lecture slides:
http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture2.pdf
Notes:
● http://cs231n.github.io/classification/
● http://cs231n.github.io/linear-classify/
Key points
● Image classification
○ Core task in computer vision
○ Difficult to hard-code an algorithm
○ Need a data driven approach
○ Sets of labelled images
○ Model learns how to relate images to labels
● Algos:
○ K nearest neighbour
○ linear classifier
○ Stepping stones to convolutional neural networks (CNN)
ML workflow
Challenges
● View point changes
● Illumination
● Deformation (different postures)
● Occlusion
● Background clutter
● Intraclass variation
Nearest neighbour
● Nearest neighbour
○ Finds the single ‘nearest’ image and uses it to classify.
● K nearest neighbour (KNN)
○ Finds the K ‘nearest’ images, figures the most common label, and uses that to classify.
● Problems
○ Quick to train, slow to predict
○ Requires a lot of storage for the data
○ The 'image distance' metric doesn't correspond well to how we perceive the distances
between images.
○ Our data needs to be evenly distributed and cover the space densely.
● Demo
○ http://vision.stanford.edu/teaching/cs231n-demos/knn/
Linear classifier
● Can be used a layer in a neural network.
● Parametric approach.
● Uses weights to classify
○ Much less storage than KNN, training data is thrown away.
● Draws a line through the problem space
○ Image is classified based on which side of the line it is on.
● Problems
○ Easy to create example data that breaks this algo.
● Demo
○ http://vision.stanford.edu/teaching/cs231n-demos/linear-classify/
Hyper parameters
● Parameters to the algo that are chosen, not learned.
● For example
○ K in KNN
○ Choice of distance metric
● Can be tuned through validation/optimization.
● Cross validation
○ Split up data into segments.
○ Best bang for buck in validation.
○ Like ‘walk forward optimization’ in quantitative trading.
Loss function
● Measures how compatible a given set of parameters is with respect to the
ground truth labels in the training dataset.
● We also saw that the loss function was defined in such way that making good
predictions on the training data is equivalent to having a small loss.
Resources
CIFAR-10
Image data set
60k 32x32 colour images
10 classes, 6k images per class
https://www.cs.toronto.edu/~kriz/cifar.html
KNN demo
http://vision.stanford.edu/teaching/cs231n-demos/knn/
Linear classifier demo
http://vision.stanford.edu/teaching/cs231n-demos/linear-classify/

More Related Content

Similar to Ai and ml study group lecture 1 and 2

Semantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite ImagerySemantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite ImageryRAHUL BHOJWANI
 
Common Design of Deep Learning Frameworks
Common Design of Deep Learning FrameworksCommon Design of Deep Learning Frameworks
Common Design of Deep Learning FrameworksKenta Oono
 
NTU DBME5028 Week8 Transfer Learning
NTU DBME5028 Week8 Transfer LearningNTU DBME5028 Week8 Transfer Learning
NTU DBME5028 Week8 Transfer LearningSean Yu
 
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15MLconf
 
10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConf10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConfXavier Amatriain
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systemsXavier Amatriain
 
Deep learning Tutorial - Part II
Deep learning Tutorial - Part IIDeep learning Tutorial - Part II
Deep learning Tutorial - Part IIQuantUniversity
 
Hands-on Deep Learning in Python
Hands-on Deep Learning in PythonHands-on Deep Learning in Python
Hands-on Deep Learning in PythonImry Kissos
 
Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)
Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)
Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)Universitat Politècnica de Catalunya
 
Time series analysis : Refresher and Innovations
Time series analysis : Refresher and InnovationsTime series analysis : Refresher and Innovations
Time series analysis : Refresher and InnovationsQuantUniversity
 
Memory Efficient Graph Convolutional Network based Distributed Link Prediction
Memory Efficient Graph Convolutional Network based Distributed Link PredictionMemory Efficient Graph Convolutional Network based Distributed Link Prediction
Memory Efficient Graph Convolutional Network based Distributed Link Predictionmiyurud
 
Reinforcement learning in a nutshell
Reinforcement learning in a nutshellReinforcement learning in a nutshell
Reinforcement learning in a nutshellNing Zhou
 
Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;
Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;
Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;Larry Smarr
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to ChainerShunta Saito
 
Portable data analysis infrastracture for LHC at INFN -vCHEP2021
Portable data analysis infrastracture for LHC at INFN -vCHEP2021Portable data analysis infrastracture for LHC at INFN -vCHEP2021
Portable data analysis infrastracture for LHC at INFN -vCHEP2021Diego Ciangottini
 
Once-for-All: Train One Network and Specialize it for Efficient Deployment
 Once-for-All: Train One Network and Specialize it for Efficient Deployment Once-for-All: Train One Network and Specialize it for Efficient Deployment
Once-for-All: Train One Network and Specialize it for Efficient Deploymenttaeseon ryu
 

Similar to Ai and ml study group lecture 1 and 2 (20)

Semantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite ImagerySemantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite Imagery
 
Common Design of Deep Learning Frameworks
Common Design of Deep Learning FrameworksCommon Design of Deep Learning Frameworks
Common Design of Deep Learning Frameworks
 
NTU DBME5028 Week8 Transfer Learning
NTU DBME5028 Week8 Transfer LearningNTU DBME5028 Week8 Transfer Learning
NTU DBME5028 Week8 Transfer Learning
 
Build machine learning pipelines from research to production
Build machine learning pipelines from research to productionBuild machine learning pipelines from research to production
Build machine learning pipelines from research to production
 
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
Xavier Amatriain, VP of Engineering, Quora at MLconf SF - 11/13/15
 
10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConf10 more lessons learned from building Machine Learning systems - MLConf
10 more lessons learned from building Machine Learning systems - MLConf
 
10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems10 more lessons learned from building Machine Learning systems
10 more lessons learned from building Machine Learning systems
 
Deep learning Tutorial - Part II
Deep learning Tutorial - Part IIDeep learning Tutorial - Part II
Deep learning Tutorial - Part II
 
Hands-on Deep Learning in Python
Hands-on Deep Learning in PythonHands-on Deep Learning in Python
Hands-on Deep Learning in Python
 
Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)
Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)
Methodology (DLAI D6L2 2017 UPC Deep Learning for Artificial Intelligence)
 
37.%20 m.e.%20cse%20
37.%20 m.e.%20cse%2037.%20 m.e.%20cse%20
37.%20 m.e.%20cse%20
 
Time series analysis : Refresher and Innovations
Time series analysis : Refresher and InnovationsTime series analysis : Refresher and Innovations
Time series analysis : Refresher and Innovations
 
Memory Efficient Graph Convolutional Network based Distributed Link Prediction
Memory Efficient Graph Convolutional Network based Distributed Link PredictionMemory Efficient Graph Convolutional Network based Distributed Link Prediction
Memory Efficient Graph Convolutional Network based Distributed Link Prediction
 
Reinforcement learning in a nutshell
Reinforcement learning in a nutshellReinforcement learning in a nutshell
Reinforcement learning in a nutshell
 
Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;
Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;
Panel: Building the NRP Ecosystem with the Regional Networks on their Campuses;
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to Chainer
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to Chainer
 
Portable data analysis infrastracture for LHC at INFN -vCHEP2021
Portable data analysis infrastracture for LHC at INFN -vCHEP2021Portable data analysis infrastracture for LHC at INFN -vCHEP2021
Portable data analysis infrastracture for LHC at INFN -vCHEP2021
 
HW04.pdf
HW04.pdfHW04.pdf
HW04.pdf
 
Once-for-All: Train One Network and Specialize it for Efficient Deployment
 Once-for-All: Train One Network and Specialize it for Efficient Deployment Once-for-All: Train One Network and Specialize it for Efficient Deployment
Once-for-All: Train One Network and Specialize it for Efficient Deployment
 

More from Ashley Davis

Live reload across the stack
Live reload across the stackLive reload across the stack
Live reload across the stackAshley Davis
 
Microservices with Node.js - Livestreamed for Manning
Microservices with Node.js - Livestreamed for ManningMicroservices with Node.js - Livestreamed for Manning
Microservices with Node.js - Livestreamed for ManningAshley Davis
 
Rapid Fullstack Development
Rapid Fullstack DevelopmentRapid Fullstack Development
Rapid Fullstack DevelopmentAshley Davis
 
Rapid Fullstack Development
Rapid Fullstack DevelopmentRapid Fullstack Development
Rapid Fullstack DevelopmentAshley Davis
 
Building microservices with Node.js - part 3
Building microservices with Node.js - part 3Building microservices with Node.js - part 3
Building microservices with Node.js - part 3Ashley Davis
 
Microservices with Node.js for BrisJS
Microservices with Node.js for BrisJSMicroservices with Node.js for BrisJS
Microservices with Node.js for BrisJSAshley Davis
 
Building microservices with Node.js - part 2
Building microservices with Node.js - part 2Building microservices with Node.js - part 2
Building microservices with Node.js - part 2Ashley Davis
 
Building microservices with Node.js - part 1
Building microservices with Node.js - part 1Building microservices with Node.js - part 1
Building microservices with Node.js - part 1Ashley Davis
 
When to reinvent the wheel / Building a query language in TypeScript
When to reinvent the wheel / Building a query language in TypeScriptWhen to reinvent the wheel / Building a query language in TypeScript
When to reinvent the wheel / Building a query language in TypeScriptAshley Davis
 
How to be a good developer
How to be a good developerHow to be a good developer
How to be a good developerAshley Davis
 
Crafting build pipelines with Docker
Crafting build pipelines with DockerCrafting build pipelines with Docker
Crafting build pipelines with DockerAshley Davis
 
How to be a good developer
How to be a good developerHow to be a good developer
How to be a good developerAshley Davis
 
Building desktop apps in java script with Electron
Building desktop apps in java script with ElectronBuilding desktop apps in java script with Electron
Building desktop apps in java script with ElectronAshley Davis
 
Testing trading strategies in JavaScript
Testing trading strategies in JavaScriptTesting trading strategies in JavaScript
Testing trading strategies in JavaScriptAshley Davis
 
Node.js memory limitations
Node.js memory limitationsNode.js memory limitations
Node.js memory limitationsAshley Davis
 
Data analysis in JavaScript
Data analysis in JavaScriptData analysis in JavaScript
Data analysis in JavaScriptAshley Davis
 

More from Ashley Davis (17)

Live reload across the stack
Live reload across the stackLive reload across the stack
Live reload across the stack
 
Microservices with Node.js - Livestreamed for Manning
Microservices with Node.js - Livestreamed for ManningMicroservices with Node.js - Livestreamed for Manning
Microservices with Node.js - Livestreamed for Manning
 
Rapid Fullstack Development
Rapid Fullstack DevelopmentRapid Fullstack Development
Rapid Fullstack Development
 
Rapid Fullstack Development
Rapid Fullstack DevelopmentRapid Fullstack Development
Rapid Fullstack Development
 
Building microservices with Node.js - part 3
Building microservices with Node.js - part 3Building microservices with Node.js - part 3
Building microservices with Node.js - part 3
 
Microservices with Node.js for BrisJS
Microservices with Node.js for BrisJSMicroservices with Node.js for BrisJS
Microservices with Node.js for BrisJS
 
Building microservices with Node.js - part 2
Building microservices with Node.js - part 2Building microservices with Node.js - part 2
Building microservices with Node.js - part 2
 
Building microservices with Node.js - part 1
Building microservices with Node.js - part 1Building microservices with Node.js - part 1
Building microservices with Node.js - part 1
 
When to reinvent the wheel / Building a query language in TypeScript
When to reinvent the wheel / Building a query language in TypeScriptWhen to reinvent the wheel / Building a query language in TypeScript
When to reinvent the wheel / Building a query language in TypeScript
 
How to be a good developer
How to be a good developerHow to be a good developer
How to be a good developer
 
Crafting build pipelines with Docker
Crafting build pipelines with DockerCrafting build pipelines with Docker
Crafting build pipelines with Docker
 
How to be a good developer
How to be a good developerHow to be a good developer
How to be a good developer
 
Building desktop apps in java script with Electron
Building desktop apps in java script with ElectronBuilding desktop apps in java script with Electron
Building desktop apps in java script with Electron
 
Testing trading strategies in JavaScript
Testing trading strategies in JavaScriptTesting trading strategies in JavaScript
Testing trading strategies in JavaScript
 
Node.js memory limitations
Node.js memory limitationsNode.js memory limitations
Node.js memory limitations
 
Web scraping
Web scrapingWeb scraping
Web scraping
 
Data analysis in JavaScript
Data analysis in JavaScriptData analysis in JavaScript
Data analysis in JavaScript
 

Recently uploaded

hybrid Seed Production In Chilli & Capsicum.pptx
hybrid Seed Production In Chilli & Capsicum.pptxhybrid Seed Production In Chilli & Capsicum.pptx
hybrid Seed Production In Chilli & Capsicum.pptx9to5mart
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...amitlee9823
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% SecurePooja Nehwal
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...amitlee9823
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...amitlee9823
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...amitlee9823
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachBoston Institute of Analytics
 
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...amitlee9823
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangaloreamitlee9823
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...karishmasinghjnh
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...amitlee9823
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...amitlee9823
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...amitlee9823
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Delhi Call girls
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramMoniSankarHazra
 

Recently uploaded (20)

hybrid Seed Production In Chilli & Capsicum.pptx
hybrid Seed Production In Chilli & Capsicum.pptxhybrid Seed Production In Chilli & Capsicum.pptx
hybrid Seed Production In Chilli & Capsicum.pptx
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning Approach
 
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
 
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service BangaloreCall Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
Call Girls Begur Just Call 👗 7737669865 👗 Top Class Call Girl Service Bangalore
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
 
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
Call Girls in Sarai Kale Khan Delhi 💯 Call Us 🔝9205541914 🔝( Delhi) Escorts S...
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
Capstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics ProgramCapstone Project on IBM Data Analytics Program
Capstone Project on IBM Data Analytics Program
 

Ai and ml study group lecture 1 and 2

  • 1. AI and ML study group CS231n Lectures 1 and 2
  • 2. Agenda 1. Course overview + Lecture 1 key points 2. Review basic Python concepts 3. Heads up on lecture 2 key points 4. Watch lecture 2 5. Review lecture 2 key points 6. Discussion 7. Review lecture 2 detailed notes (if time) 8. Project? ○ Get the code from lecture 2 and train a model on CIFAR-10.
  • 3. The course Home page: http://cs231n.stanford.edu/ Syllabus: http://cs231n.stanford.edu/2017/syllabus.html Videos: https://www.youtube.com/playlist?list=PLC1qU-LWwrF64f4QKQT-Vg5Wr4qEE1Zx k Google group: https://groups.google.com/forum/#!forum/ml-and-ai-study-group
  • 4. Course overview ● Understand how to write from scratch, debug and train CNNs ● CPU vs GPU ● Tools ○ Caffe ○ TensorFlow ○ (Py)Torch
  • 7. Key points ● The course is mostly about convolutional neural networks (CNNs) and computer vision. ● History of computer vision and machine learning - interesting, but not essential. ● Deep learning really took off from 2012. ● Image.net competition ○ SuperVision (AlexNet) won in 2012 ○ Every winner since is a neural network
  • 8. Interesting points ● SuperVision had 7 layers ● More recent networks have 200+ layers ○ We are now limited by GPU memory!
  • 9. What can we do with CNNs? ● Visual recognition - image classification ● Object detection - draw bounding boxes. ● Image captioning. ● Action classification.
  • 10. Why did deep learning take off? ● It’s been around since the 90s. ● CPU / GPU power (Moore’s law) ○ Allowed researchers to explore bigger models ● We have more data than ever before ● Open source tools
  • 11. Related courses ● CS131 - Undergraduate intro course. ● CS224n - intersection of Deep Learning and natural language processing. ● CS231a - Neural networks for image classification. ● CS331 / CS431 - advanced topics in computer vision.
  • 12. Resources Optional text book http://www.deeplearningbook.org/ Image.net 14m+ images organised in 22k categories http://www.image-net.org/ Example data sets https://en.wikipedia.org/wiki/List_of_datasets_for_machine_learning_research
  • 14. Key points ● Image classification ○ Core task in computer vision ○ Difficult to hard-code an algorithm ○ Need a data driven approach ○ Sets of labelled images ○ Model learns how to relate images to labels ● Algos: ○ K nearest neighbour ○ linear classifier ○ Stepping stones to convolutional neural networks (CNN)
  • 16. Challenges ● View point changes ● Illumination ● Deformation (different postures) ● Occlusion ● Background clutter ● Intraclass variation
  • 17. Nearest neighbour ● Nearest neighbour ○ Finds the single ‘nearest’ image and uses it to classify. ● K nearest neighbour (KNN) ○ Finds the K ‘nearest’ images, figures the most common label, and uses that to classify. ● Problems ○ Quick to train, slow to predict ○ Requires a lot of storage for the data ○ The 'image distance' metric doesn't correspond well to how we perceive the distances between images. ○ Our data needs to be evenly distributed and cover the space densely. ● Demo ○ http://vision.stanford.edu/teaching/cs231n-demos/knn/
  • 18. Linear classifier ● Can be used a layer in a neural network. ● Parametric approach. ● Uses weights to classify ○ Much less storage than KNN, training data is thrown away. ● Draws a line through the problem space ○ Image is classified based on which side of the line it is on. ● Problems ○ Easy to create example data that breaks this algo. ● Demo ○ http://vision.stanford.edu/teaching/cs231n-demos/linear-classify/
  • 19. Hyper parameters ● Parameters to the algo that are chosen, not learned. ● For example ○ K in KNN ○ Choice of distance metric ● Can be tuned through validation/optimization. ● Cross validation ○ Split up data into segments. ○ Best bang for buck in validation. ○ Like ‘walk forward optimization’ in quantitative trading.
  • 20. Loss function ● Measures how compatible a given set of parameters is with respect to the ground truth labels in the training dataset. ● We also saw that the loss function was defined in such way that making good predictions on the training data is equivalent to having a small loss.
  • 21. Resources CIFAR-10 Image data set 60k 32x32 colour images 10 classes, 6k images per class https://www.cs.toronto.edu/~kriz/cifar.html KNN demo http://vision.stanford.edu/teaching/cs231n-demos/knn/ Linear classifier demo http://vision.stanford.edu/teaching/cs231n-demos/linear-classify/