First Steps Towards Your First Machine Learning Project

Girls in ICT Brunei 2020

Transcript

1. First Steps Towards Your First Machine Learning Project Galuh Sahid (Twitter: @galuhsahid) Data Scientist at Gojek Google Developer Expert in Machine Learning
2. How to get started with machine learning?
3. Ideas for your first project Formulating your machine learning problem Tools that you can use
4. Ideas for your first project
5. It has to be… something you enjoy
6. Spotify playlists
7. Google Home (photo credit: unsplash.com)
8. I love… • Sports • Idea: build a model that predicts championship winners based on past history • Literature • Idea: text generator in the style of famous authors • Movies • Idea: classify movie review sentiments
9. It has to be… something you enjoy
10. It has to be… something you enjoy It does not have to be… something complicated or novel
11. Formulating your machine learning problem
12. Formulating an ML problem Supervised Learning
13. Formulating an ML problem Supervised Learning Leaf Width Leaf Length Species 2.7 4.9 small-leaf 3.2 5.5 big-leaf 2.9 5.1 small-leaf 3.4 6.8 big-leaf Adapted from Google’s Machine Learning Problem Framing
14. Formulating an ML problem Supervised Learning Leaf Width Leaf Length Species 2.7 4.9 small-leaf 3.2 5.5 big-leaf 2.9 5.1 small-leaf 3.4 6.8 big-leaf features label The features and their corresponding labels are fed into an algorithm in a process called training. What happens during training? The algorithm will gradually determine the relationship between features and their corresponding labels. This relationship is called the model. Adapted from Google’s Machine Learning Problem Framing
15. Formulating an ML problem Supervised Learning Adapted from Google’s Machine Learning Problem Framing
16. Formulating an ML problem Supervised Learning Adapted from Google’s Machine Learning Problem Framing
17. Formulating an ML problem Supervised Learning Leaf Width Leaf Length Species 2.7 4.9 small-leaf 3.2 5.5 big-leaf 2.9 5.1 small-leaf 3.4 6.8 big-leaf 2.1 3.4 ? small-leaf (our prediction) Adapted from Google’s Machine Learning Problem Framing
18. Supervised Learning Classification Formulating an ML problem Supervised Learning
19. Supervised Learning Classification Is this a spam/not a spam? Is the sentiment of this movie review positive or negative? Binary Is this a picture of a cat or a dog? Formulating an ML problem Supervised Learning
20. Supervised Learning Classification Is this a comedy, horror, or drama movie? Is this the voice of a dog, a bird, a cat, or a grasshopper? Binary Is this a picture of a shirt, a book, or a food? Multi-class Formulating an ML problem Supervised Learning
21. Supervised Learning Classification Binary Multi-class Regression What is the price of the house if it has 2 floors, 4 bedrooms, and 2 bathrooms? What is the temperature in Paris tomorrow? Formulating an ML problem Supervised Learning
22. Unsupervised Learning Formulating an ML problem Supervised Learning
23. Formulating an ML problem Unsupervised Learning Adapted from Google’s Machine Learning Problem Framing
24. Formulating an ML problem Unsupervised Learning Adapted from Google’s Machine Learning Problem Framing Sports Entertainment
25. Unsupervised Learning Formulating an ML problem Supervised Learning
26. Formulating an ML problem Identifying Data Sources Use ready-to-use dataset Collect & build your own dataset from scratch Extract the data from existing data sources
27. Formulating an ML problem Ready-to-use dataset Google Research (https://research.google/tools/datasets/)
28. Formulating an ML problem Ready-to-use dataset Google Dataset (datasetsearch.research.google.com)
29. Formulating an ML problem Ready-to-use dataset Google Dataset (datasetsearch.research.google.com)
30. Formulating an ML problem Ready-to-use dataset Kaggle Datasets (https://www.kaggle.com/datasets)
31. Formulating an ML problem Ready-to-use dataset • Oftentimes data cleansing, manipulation, transformations are still necessary • You need to know the labels that you expect
32. Formulating an ML problem Ready-to-use dataset Example: predicting the sentiment of movie reviews (positive or negative)
33. Formulating an ML problem Extract the data by yourself - Scraping Twitter data Example of applications: - Sentiment analysis (must be labeled) - Topic detection e.g. 50% of tweets: Chris Evans’ new TV series, 25% of the tweets: Avengers, 25% of the tweets: Golden Globes - Scraping news websites
34. Formulating an ML problem Extract the data by yourself • Might be time-consuming
35. Formulating an ML problem Build your own dataset from scratch • Might be time-consuming, especially if you need a lot of data • Need to ensure that the way your data is collected suits the real-world condition - Example: building a bird audio dataset by recording sounds of different birds
36. Formulating an ML problem Now you know: - The problem statement of your project (e.g. “Our problem is best framed as 3-class classification, which predicts whether a video will be in one of three classes—{very popular, somewhat popular, not popular}—28 days after being uploaded”) - What data you need to process (text? Images?) - Whether you need labeled data or not - Possible algorithms for your project Adapted from Google’s Machine Learning Problem Framing
37. Tools & resources
38. Tools & resources Programming languages • Python is usually the go-to programming language • However, you can now train your own machine learning models using JavaScript thanks to TensorFlow.js
39. Tools & resources Libraries • Data manipulation: numpy, pandas • NLP: NLTK, spaCy • Image processing: PIL, OpenCV • Machine learning: scikit-learn, TensorFlow, TensorFlow Lite
40. Tools & resources Teachable Machine Teachable Machine
41. Tools & resources Teachable Machine Teachable Machine
42. Tools & resources TensorFlow Hub TensorFlow Hub
43. Tools & resources TensorFlow Hub Example: mobilebert, compressed version of BERT (Bidirectional Encoder Representations from Transformers)
44. Tools & resources TensorFlow Hub
45. Tools & resources Learning Resources • Deep Learning with Python (book) by François Chollet • Machine Learning Glossary • Machine Learning Crash Course • TensorFlow Tutorials • Teachable Machine Tutorials (1, 2, 3)
46. Takeaways • Building machine learning projects can be a great way to learn machine learning • ML projects don’t have to be super fancy or complicated, they just have to be something you enjoy :) • The process of formulating your ML problem can help you figure out your next steps (e.g. collect what data, use what tools, possible algorithms) • There are lots of resources & tools out there to help you!
47. Thank you! @galuhsahid