Upgrade to Pro — share decks privately, control downloads, hide ads and more …

ML Starter Pack

ML Starter Pack

Presented at GDG Waterloo.

Basics of ML

Charmi Chokshi

April 22, 2023
Tweet

More Decks by Charmi Chokshi

Other Decks in Technology

Transcript

  1. ML Starter Pack
    A comprehensive guide to Machine Learning
    April 22, 2023
    GDG Waterloo, Canada

    View full-size slide

  2. I'm Charmi!
    ● ML Grad at Mila and UdeM
    ● GDE for ML
    ● International Speaker
    ● Worked @ AWS, Shipmnts, ISRO
    ● Tech, Art, Travel

    View full-size slide

  3. Plan of the Day!
    ● What is Machine Learning?
    ● Types of ML
    ● Supervised and Unsupervised techniques
    ● Classification and Regression
    ● Basics of Deep Learning
    ● Basics of NLP, CV, ASR
    ● The 3D ML Pipeline
    ● Fun Applications

    View full-size slide

  4. ?
    90% have failed to solve this...
    =
    =
    =
    33
    30
    36

    View full-size slide

  5. 99% have failed to solve this...

    View full-size slide

  6. Retrospection time!!
    What we just did?
    We solved logical math puzzle
    in a fraction of time

    View full-size slide

  7. Think about, How we
    solved them?
    We had inputs
    We also had outputs

    View full-size slide

  8. Think about, How we
    solved them?
    We created Rules and Patterns in our brain!!

    View full-size slide

  9. Can machines create
    rules on their own?

    View full-size slide

  10. Can machines create
    rules on their own?
    No, if it’s Classical Programming...

    View full-size slide

  11. Can machines create
    rules on their own?
    YES, if it’s Machine Learning!!!

    View full-size slide

  12. Classical Programming vs ML
    Classical
    Programming
    Machine
    Learning
    Rules
    Rules
    Data
    Data
    Answers
    Answers

    View full-size slide

  13. Artificial
    Intelligence
    Deep
    Learning
    Machine
    Learning
    Any Technique that enables
    computers to mimic human
    intelligence & behaviour
    A subset of ML exposing
    multilayered neural
    networks to vast amount of
    data
    A subset of AI that includes
    statistical techniques to
    solve the tasks using
    experience

    View full-size slide

  14. Basic Terminologies
    ● Features
    ● Labels
    ● Examples
    ○ Labelled example
    ○ Unlabelled example
    ● Data Split (Train, Valid, Test)
    ● Models (Train and Test)
    ○ Classification model
    ○ Regression model

    View full-size slide

  15. Supervised Learning
    ● Supervised Learning deals with prediction of values based on given
    combinations of data and labels given beforehand
    ● ML systems learn how to combine input to produce useful
    predictions on never-before-seen data
    ● It is like learning with a teacher

    View full-size slide

  16. Regression and Classification
    ● A regression model predicts continuous values by fitting a line
    ○ What is the value of a house in California?
    ○ What is the probability that a user will click on this ad?
    ● A classification model predicts discrete values by creating boundaries
    ○ Is a given email message spam or not spam?
    ○ Is this an image of a dog, a cat, or a hamster?

    View full-size slide

  17. Iterative Learning

    View full-size slide

  18. Overfitting vs Underfitting
    ● An overfit model gets a low loss during training but does a poor job
    predicting new data
    ● Overfitting is caused by making a model more complex than necessary
    ● The fundamental tension of machine learning is between fitting our data
    well, but also fitting the data as simply as possible

    View full-size slide

  19. Unsupervised Learning
    ● It deals with clustering values or forming groups of values
    ● One aims to infer patterns from the data rather than predicting values
    ● It is like learning on your own

    View full-size slide

  20. Evaluation Metrics
    https://en.wikipedia.org/wiki/Precision_and_recall, https://www.kdnuggets.com/2018/06/right-metric-evaluating-machine-learning-models-2.html

    View full-size slide

  21. Evaluation Metrics
    https://en.wikipedia.org/wiki/Precision_and_recall, https://www.kdnuggets.com/2018/06/right-metric-evaluating-machine-learning-models-2.html

    View full-size slide

  22. Deep Learning

    View full-size slide

  23. Neural Network
    https://gfycat.com/gifs/search/neural+network

    View full-size slide

  24. When to use or not use DL?
    ● Deep Learning outperforms other techniques if the data size is large. But
    with small data size, traditional Machine Learning algorithms are preferable
    ● Finding large amount of “Good” data is always a painful task
    ● Deep Learning techniques need to have high end infrastructure to train in
    reasonable time
    ● When there is lack of domain understanding for feature introspection,
    Deep Learning techniques outshines others as you have to worry less about
    feature engineering

    View full-size slide

  25. When to use or not use DL?
    ● Model Training time: a Deep Learning algorithm may take weeks or months
    whereas, traditional Machine Learning algorithms take few seconds or hours
    ● DL never reveals the “how and why” behind the output- it’s a Black Box
    ● Deep Learning really shines when it comes to complex problems such as
    image classification, natural language processing, and speech recognition
    ● DL excels in tasks where the basic unit (pixel, word) has very little meaning in
    itself, but the combination of such units has a useful meaning

    View full-size slide

  26. Natural Language Processing
    ● Sentiment analysis
    ● Chatbots
    ● Machine translation
    ● Speech recognition
    ● Text summarization

    View full-size slide

  27. Computer Vision
    ● Facial recognition
    ● Object detection
    ● Medical imaging
    ● Autonomous vehicles
    ● Segmentation

    View full-size slide

  28. Speech Understanding
    ● Voice-controlled personal assistants
    ● Virtual agents
    ● Dictation software
    ● Closed captioning
    ● Subtitling for movies
    ● Transcribing

    View full-size slide

  29. The 3D ML Pipeline
    Design - Develop - Deploy

    View full-size slide

  30. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  31. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  32. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  33. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  34. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  35. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  36. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  37. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  38. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  39. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  40. Data
    acquisition
    Model
    Deployment
    Data
    Cleaning
    Feature
    Engineering
    Model
    Validation
    Model
    Monitoring
    Model
    Selection
    Model
    Testing
    Model
    Training
    Hyper
    parameter
    tuning

    View full-size slide

  41. It’s time for exploring
    some FUN applications

    View full-size slide

  42. Classification on Custom Data
    https://teachablemachine.withgoogle.com/train

    View full-size slide

  43. Sketch-RNN
    https://magenta.tensorflow.org/assets/sketch_rnn_demo/index.html

    View full-size slide

  44. From where the data came
    Quick Draw: https://quickdraw.withgoogle.com/

    View full-size slide

  45. RUNN = 🏃Run + 🤖RNN
    http://vibertthio.com/runn/

    View full-size slide

  46. Experiments with Google
    https://experiments.withgoogle.com/collection/ai

    View full-size slide

  47. The project Magenta
    https://magenta.tensorflow.org/

    View full-size slide

  48. https://developers.google.com/machine-learning/

    View full-size slide

  49. Let's connect!
    @CharmiChokshi
    Charmi Chokshi
    @charmichokshi
    coda.io/@charmi-chokshi/hi

    View full-size slide

  50. Thanks!
    Questions?
    Download the deck

    View full-size slide