MyVid: Full applied AI & Machine Learning tutorials

If you would like to understand more about what is Artificial Intelligence, Machine Learning, and how to apply this in your code. I suggest you to follow this video series from Cassie Kozyrkov, a very well known Data Decision Intelligence expert in Google.

1st Video – Introduction to Machine Learning & Artificial Intelligence :

2nd Video – Life of an Artificial Intelligence Project :

3rd Video – Taking your AI project from Prototype to Production :

4th Video – Guide to Artificial Intelligence Algorithms :

I personally really learnt a lot from her videos, especially on how to explain ML to public.
To watch the videos in byte size, based on the topic that you preferred. Here are the list:

Basic Concepts

1. Basics: MFML 000 – Welcome
2. Basics: MFML 001 – What is machine learning?
3. Basics: MFML 002 – Why use machine learning?
4. Basics: MFML 003 – How does machine learning work?
5. Basics: MFML 004 – How to test ML
6. Basics: MFML 005 – What’s inside the black box?
7. Basics: MFML 006 – Simple linear regression
8. Basics: MFML 007 – Multiple linear regression
9. Basics: MFML 008 – Feature engineering
10. Basics: MFML 009 – What is AI?
11. Basics: MFML 010 – Why did we wait so long for AI?
12. Basics: MFML 011 – Geoff, Fei-Fei, and Jeff
13. Basics: MFML 012 – Real applications
14. Basics: MFML 013 – How to find good AI use cases
15. Basics: MFML 014 – Human creativity in AI
16. Basics: MFML 015 – How Do GANs work?
17. Basics: MFML 016 – Why trust AI?
18. Basics: MFML 017 – Explainability and AI
19. Basics: MFML 018 – Intro to training, validation, and testing
20. Basics: MFML 019 – How to avoid machine learning pitfalls
21. Basics: MFML 020 – Decision Intelligence
22. Basics: MFML 021 – Why do businesses fail at machine learning?
23. Basics: MFML 022 – Skilled decision-makers
24. Basics: MFML 023 – Reliable or unreliable?
25. Basics: MFML 024 – Preventable disasters
26. Basics: MFML 025 – Wish responsibly
27. Basics: MFML 026 – AI is a team sport!
28. Basics: MFML 027 – Our AI future

The 12 Steps of AI Step 0: Reality check

1. Step 0: MFML 028 – The 12 steps of AI
2. Step 0: MFML 029 – Where to start with applied AI? 
3. Step 0: MFML 030 – Classification vs regression
4. Step 0: MFML 031 – Instances, features, and targets
5. Step 0: MFML 032 – Supervised learning
6. Step 0: MFML 033 – Unsupervised learning
7. Step 0: MFML 034 – Semi-supervised learning
8. Step 0: MFML 035 – Reinforcement learning
9. Step 0: MFML 036 – What on earth is data science?
10. Step 0: MFML 037 – Data science flowchart
11. Step 0: MFML 038 – Don’t forget data!

Step 1: Define your objectives

1. Step 1: MFML 039 – What is “good behavior” for AI?
2. Step 1: MFML 040 – False positives and true negatives
3. Step 1: MFML 041 – Confusion matrix
   Step 1: MFML 042 – Performance metrics
4. Step 1: MFML 043 – Ground truth
5. Step 1: MFML 044 – Precision vs recall
6. Step 1: MFML 045 – What is optimization?
7. Step 1: MFML 046 – Loss functions
8. Step 1: MFML 047 – Setting launch criteria

Step 2: Get access to data

1. Step 2: MFML 048 – Data engineering

Step 3: Split your data

• Step 3: MFML 049 – The danger of overfitting
• Step 3: MFML 050 – Should you care about underfitting?
• Step 3: MFML 051 – The importance of data splitting

Step 4: Explore your data

• Step 4: MFML 052 – Exploratory data analysis (EDA)

Step 5: Prepare your tools

• Step 5: MFML 053 – How to select an AI algorithm
• Step 5: MFML Part 4 – Guide to AI algorithms (not bite sized!)

Step 6: Use your tools to train some models

• Step 6: MFML 054 – Is training an AI system easy?
• Step 6: MFML 055 – A dataset’s idea shape
• Step 6: MFML 056 – How to speed up your ML/AI training phase
• Step 6: MFML 057 – Statistics versus “statistics”
• Step 6: MFML 058 – When your machine learning project takes forever
• Step 6: MFML 059 – Regularization
• Step 6: MFML 060 – Features you should never use in AI
• Step 6: MFML 061 – Can you skip the training phase in AI?

Step 7: Debug, analyze, and tune

• Step 7: MFML 062 – Debugging your machine learning model
• Step 7: MFML 063 – Hyperparameter tuning
• Step 7: MFML 064 – What is a holdout set and how do you use it?
• Step 7: MFML 065 – Understanding k-fold cross-validation
• Step 7: MFML 066 – Advanced AI debugging
• Step 7: MFML 067 – What if you skip debugging?

Step 8: Validate your models

• Step 8: MFML 068 – What to do when model validation fails
• Step 8: MFML 069 – Model validation done right
• Step 8: MFML 070 – Validation roulette

Step 9: Test your model

• Step 9: MFML 071 – What’s the difference between testing and validation
• Step 9: MFML 072 – The 12 steps of statistics
• Step 9: MFML 073 – Interpreting AI test output
• Step 9: MFML 074 – Understanding p-values
• Step 9: MFML 075 – Statistical significance
• Step 9: MFML 076 – What should you do if testing fails
• Step 9: MFML 077 – The importance of testing

Step 10: Productionize your system

• Step 10: MFML 078 – Productionization
• Step 10: MFML 079 – Repurposing data safely
• Step 10: MFML 080 – Solving AI latency problems
• Step 10: MFML 081 – How often should you retrain your AI system?
• Step 10: MFML 082 – The training-serving skew
• Step 10: MFML 083 – Be careful with chained models
• Step 10: MFML 084 – Making tiny changes to AI code
• Step 10: MFML 085 – When your AI model fails retesting
• Step 10: MFML 086 – The danger of the long tail in AI
• Step 10: MFML 087 – How to catch outliers and AI failures
• Step 10: MFML 088 – AI safety and policy layers

Step 11: Run live experiments to launch safely

• Step 11: MFML 089 – Live traffic experiments

Step 12: Monitor and maintain… forever

• Step 12: MFML 091 – AI system maintenance
• Step 12: MFML 090 – Monitoring your AI system

Enjoy!

Kind Regards,
Doddi Priyambodo