Idx | Notes | Course detail |
---|---|---|
1 | lesson 1 note | The Machine Learning Project Lifecycle | Welcome |
2 | lesson 2 note | The Machine Learning Project Lifecycle | Steps of an ML project |
3 | lesson 3 note | The Machine Learning Project Lifecycle | Steps of an ML project |
4 | lesson 4 note | The Machine Learning Project Lifecycle | Case study: speech recognition |
5 | lesson 5 note | Deployment | Key challenges |
6 | lesson 6 note | Deployment | Deployment patterns |
7 | lesson 7 note | Deployment | Monitoring |
8 | skip | |
9 | lesson 9 note | Select and train model | Modeling overview |
10 | lesson 10 note | Select and train model | Key challenges |
11 | lesson 11 note | Select and train model | Why low average test error isn't good enough |
12 | lesson 12 note | Select and train model | Establish a baseline |
13 | lesson 13 note | Select and train model | Tips for getting started |
14 | lesson 14 note | Error analysis and performance auditing | Error analysis example |
15 | lesson 15 note | Error analysis and performance auditing | Prioritizing what to work on |
16 | lesson 16 note | Error analysis and performance auditing | Skewed datasets |
17 | lesson 17 note | Error analysis and performance auditing | Performance auditing |
18 | lesson 18 note | Data iteration | Data-centric AI development |
19 | lesson 19 note | Data iteration | A useful picture of data augmentation |
20 | lesson 20 note | Data iteration | Data audgmentation |
21 | lesson 21 note | Data iteration | Can adding data hurt? |
22 | lesson 22 note | Data iteration | Adding features |
23 | lesson 23 note | Data iteration | Experiment tracking |
24 | lesson 24 note | Data iteration | From big data to good data |
25 | lesson 25 note | Define data and establish baseline | Why is data definition hard? |
26 | lesson 26 note | Define data and establish baseline | More label ambiguity examples |
27 | lesson 27 note | Define data and establish baseline | Major types of adata problems |
28 | lesson 28 note | Define data and establish baseline | Small data and label consistency |
29 | lesson 29 note | Define data and establish baseline | Improving label consistency |
30 | lesson 30 note | Define data and establish baseline | Human level performance (HLP) |
31 | lesson 31 note | Define data and establish baseline | Raising HLP |
32 | lesson 32 note | Label and organize data | Obtaining data |
33 | lesson 33 note | Label and organize data | Data pipeline |
34 | lesson 34 note | Label and organize data | Meta-data, data provenance and lineage |
35 | lesson 35 note | Label and organize data | Balanced train/dev/test splits |
36 | lesson 36 note | Scoping | What is scoping? |
37 | lesson 37 note | Scoping | Scoping process |
38 | lesson 38 note | Scoping | Diligence on feasibility and value |
39 | lesson 39 note | Scoping | Diligence on value |
40 | lesson 40 note | Scoping | Milestones and resourcing |
-
Notifications
You must be signed in to change notification settings - Fork 0
YuriXStuart/MLOPS_Andrew_Ng
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
앤드류 응 교수의 ML Ops 강의 정리하는 노트
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published