Implementation of AI & ML Technology in Indonesia’s Industry

Tech talk DSC Gunadarma - November 29, 2020

Transcript

1. Implementation of AI & ML Technology in Indonesia’s Industry Galuh Sahid @galuhsahid | galuh.me Tech talk DSC Gunadarma - November 29, 2020
2. • Data scientist at a tech company in Indonesia • Google Developer Expert in Machine Learning • Co-host podcast Kartini Teknologi (kartiniteknologi.id) @galuhsahid Hi! I’m Galuh.
3. Outline @galuhsahid • What is machine learning? • What are the differences between AI, ML, deep learning…? • Examples of ML/AI implementation • How to implement ML/AI? • Workflow • Tools & resources • Challenges in ML/AI implementation
4. @galuhsahid Photo by Bram Van Oost from Unsplash
5. @galuhsahid Photo by Frank V. from Unsplash
6. @galuhsahid Photo by Bence Boros from Unsplash
7. @galuhsahid Photo by Nordwood from Unsplash
8. @galuhsahid Photo by Krsto Jevtic from Unsplash
9. It’s an exciting time to learn more about machine learning! @galuhsahid
10. But… what is machine learning? @galuhsahid
11. A field of study that gives computers the ability to learn without being explicitly programmed. Arthur Samuel (1959) @galuhsahid
12. How is machine learning different from traditional programming? @galuhsahid
13. Traditional Programming Rules Data Answers @galuhsahid
14. if pixel[5][7] is black and pixel [5][6] is black and pixel [5][8] is black and …: if pixel[6][7] is black and pixel[6][7] is black and …: return “panda” … … … else: return “cat” Photo by Damian Patowski from Unsplash @galuhsahid
15. if pixel[5][7] is black and pixel [5][6] is black and pixel [5][7] is black and …: if pixel[6][7] is black and pixel[6][7] is black and …: return “panda” … … … else: return “not cat” Photo by Dušan Smetana from Unsplash @galuhsahid
16. Machine Learning Answers Data Rules
17. Answers Data Panda Cat Cat Photo by Max Baskalov and Zane Lee from Unsplash Panda @galuhsahid
18. ? Cat ? Photo by Cyrus Chew from Unsplash @galuhsahid
19. Machine learning? Artificial intelligence? Neural networks? Deep learning? @galuhsahid
20. Source @galuhsahid
21. Rule engine Knowledge Graphs Source @galuhsahid
22. Regression Decision Tree Random Forest Source @galuhsahid
23. ML/AI in the industry @galuhsahid
24. Recommendation system ML/AI in the industry @galuhsahid
25. Object recognition ML/AI in the industry @galuhsahid
26. Sentiment analysis for brand monitoring ML/AI in the industry @galuhsahid https://awario.com/sentiment-analysis/
27. OCR for ID cards ML/AI in the industry @galuhsahid https://global.faceid.com/products/id-card-recognition
28. Anomaly detection ML/AI in the industry @galuhsahid https://deepai.org/machine-learning-glossary-and-terms/anomaly-detection
29. ML/AI implementation: Workflow @galuhsahid
30. Workflow Implementation @galuhsahid Train your model
31. @galuhsahid Define your machine learning problem Acquire & prepare your data Train your model Serve your model Adapted from Introduction to ML Problem Framing Explore your data Workflow Implementation
32. Step #1 Define your machine learning problem @galuhsahid
33. Step #2 Acquire & prepare your data @galuhsahid
34. Step #2 Acquire & prepare your data @galuhsahid You need to know: • What are the types of data that you can use • Where to get them • How to get to know your data • How to prepare your data
35. Tabular @galuhsahid Data Type #1
36. Text @galuhsahid Data Type #2
37. Sound @galuhsahid Data Type #3
38. Image @galuhsahid Data Type #4
39. Step #3 Explore your data @galuhsahid
40. Exploratory Data Analysis Getting to know your data - Analyze your data to summarize their main characteristics - Examples include: check for basic statistics (e.g. mean, median), missing data, outliers @galuhsahid
41. Feature engineering Preparing your data - Handling categorical data @galuhsahid
42. Feature engineering Preparing your data - Handling outliers @galuhsahid
43. Step #4 Train your model @galuhsahid
44. Step #5 Serve your model @galuhsahid
45. Serving Implementation @galuhsahid • Batch • Real-time • Don’t forget to monitor your model’s performance!
46. ML/AI implementation: Tools & Resources @galuhsahid
47. Programming languages Implementation @galuhsahid
48. Programming languages Implementation @galuhsahid SQL
49. NLP Libraries Implementation @galuhsahid Deep learning libraries Computer vision Data processing & manipulation General machine learning
50. Libraries Implementation @galuhsahid Data visualization
51. Challenges @galuhsahid
52. Misconceptions about AI/ML Challenges @galuhsahid Common myths: • The most important part in implementing ML is building models • Hyperparameter tuning is the only way to improve our model • We can get a 100% accuracy • ML is the answer for everything
53. Data availability Challenges @galuhsahid • ML needs data! • However, since the awareness of data in the industry is relatively new, sometimes companies want to jump to implementing AI/ML without thinking about whether they actually have the data or not • What about open data? Indonesian open data still needs lots of improvement https://hackernoon.com/the-ai-hierarchy-of-needs-18f111fcc007
54. Data infrastructure readiness Challenges @galuhsahid • Before implementing AI/ML, we need to have the data infrastructure ready first. Building data infrastructure needs planning and takes time. https://hackernoon.com/the-ai-hierarchy-of-needs-18f111fcc007
55. Supporting resources Challenges @galuhsahid • Sometimes the success of an ML project also depends on the resource available • Example: NLP resources for Indonesian are limited compared to English https://github.com/kmkurn/id-nlp-resource
56. References
57. More machine learning • On building ML projects: First Steps Towards Your First Machine Learning Project • On ML with JavaScript: Machine Learning on the Web • On ML with TensorFlow: A Whirlwind Tour of Machine Learning with TensorFlow @galuhsahid
58. 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) •But what is a neural network? (video) @galuhsahid
59. Thank you! @galuhsahid