Intro to Machine Learning: Thunderplains 2016
0 likes595 views
This is an introduction to Machine Learning and how it fits into Data Science as well as the larger tech space in general.
Intro to Machine Learning: Thunderplains 2016
- 2. Machine Learning Frank D. Evans Thunder Plains 2016
- 9. A Data Scientist is a data analyst that lives in California
- 10. A Data Scientist is a better mathematician than any of the programmers, and a better programmer than any of the mathematicians.
- 12. OSEMN
- 13. OSEMN Obtain
- 14. OSEMN Scrub
- 15. OSEMN Explore
- 16. OSEMN Model
- 17. OSEMN Interpret
- 22. T O O L S
- 23. T O O L S
- 24. T O O L S
- 25. T O O L S
- 27. Data is huge. People are expensive. Computation is cheap.
- 28. Use applied statistics to let the computers program themselves.
- 29. Types
- 30. Types Supervised "I have a set of examples with the right answers, I want to learn a pattern and use it on examples where I don't have the answers."
- 31. Types Unsupervised "I have data with no answers, but I want to 鍖nd a pattern that might lead me to an answer."
- 32. Types Reinforcement "I want to start with what I know now, and be able to learn new things as new data comes along."
- 33. Types Supervised "I have a set of examples with the right answers, I want to learn a pattern and use it on examples where I don't have the answers." Unsupervised "I have data with no answers, but I want to 鍖nd a pattern that might lead me to an answer." Reinforcement "I want to start with what I know now, and be able to learn new things as new data comes along."
- 34. Types Supervised "I have a set of examples with the right answers, I want to learn a pattern and use it on examples where I don't have the answers." Unsupervised "I have data with no answers, but I want to 鍖nd a pattern that might lead me to an answer." Reinforcement "I want to start with what I know now, and be able to learn new things as new data comes along."
- 35. Regression vs Classi鍖cation Supervised Learning
- 36. Regression Use continuous data to make a model that predicts where new data will 鍖t.
- 37. Classi鍖cation Label data into "buckets", and make predictions on which bucket a new data point will fall into.
- 41. Deep Learning
- 42. Deep Learning generalization, not memorization
- 45. Domains Tabular
- 46. Domains Text
- 47. Domains Graph
- 48. Domains Viz
- 49. Youre not trying to learn about the data, youre trying to use the data to learn about the world.