https://github.com/kritikalcoder/ground_up_basics_trust_ml
A collection of useful educational resources to build a solid understanding of Trustworthy ML.
https://github.com/kritikalcoder/ground_up_basics_trust_ml
Last synced: 5 months ago
JSON representation
A collection of useful educational resources to build a solid understanding of Trustworthy ML.
- Host: GitHub
- URL: https://github.com/kritikalcoder/ground_up_basics_trust_ml
- Owner: Kritikalcoder
- Created: 2023-02-12T11:09:09.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-02-14T13:02:56.000Z (over 3 years ago)
- Last Synced: 2025-07-23T06:09:10.903Z (12 months ago)
- Homepage:
- Size: 8.79 KB
- Stars: 6
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## **Ground Up Basics for Trustworthy Machine Learning**
This is a curation of educational resources in various sub-fields of Computer Science and Math that are helpful to building a solid understanding of Trustworthy Machine Learning. While there are many wonderful resources out there, this collection focuses on the required basics. This list is in no way complete and I encourage others to contribute to it :)
### **Topics**
- Probability
- Statistics
- Calculus
- Linear Algebra
- Machine Learning
- Deep Learning
- Trustworthy Machine Learning
- Privacy
- Fairness
- Interpretability & Explainability
- Causality
- Adversarial Attacks & Robustness
- Other Topics
### **Probability**
- Stanford's course CS109: [Probability for Computer Scientists](https://web.stanford.edu/class/archive/cs/cs109/cs109.1214/)
### **Statistics**
### **Calculus**
### **Linear Algebra**
### **Machine Learning**
- Book on [Mathematics for Machine Learning](https://mml-book.github.io/book/mml-book.pdf)
- Coursera's [Machine Learning Specialization](https://in.coursera.org/specializations/machine-learning-introduction)
- Andrew Zisserman's course on [Machine Learning](https://www.robots.ox.ac.uk/~az/lectures/ml/index.html)
### **Deep Learning**
- Coursera's [Deep Learning Specialization](https://www.coursera.org/specializations/deep-learning)
- Ian Goodfellow's book on [Deep Learning](https://www.deeplearningbook.org/)
### **Trustworthy Machine Learning**
Note that a majority of the resources mentioned from this section onwards is re-shared from [trustworthyml.org](https://www.trustworthyml.org/resources) - a wonderful and thorough curation.
- Nicolas Papernot's talk on [What does it mean for ML to be trustworthy?](https://www.youtube.com/watch?v=UpGgIqLhaqo)
- Golnoosh Farnadi's course on [Trustworthy Machine Learning](https://gfarnadi.github.io/courses/TrustworthyMLF22/lectures.html)
- [Begginer's list for research papers in Trustworthy ML](https://trustworthy-machine-learning.github.io/) by Reza Shokri and Nicolas Papernot
### **Privacy**
- Gautam Kamath's course: [Algorithms for Private Data Analysis](http://www.gautamkamath.com/CS860-fa2020.html)
- Ted's blog series: [Why Differential Privacy is Awesome](https://desfontain.es/privacy/differential-privacy-awesomeness.html)
- Facebook AI's Udacity course: [Secure and Private AI](https://www.udacity.com/course/secure-and-private-ai--ud185)
- OpenMined's courses: [The Private AI Series](https://courses.openmined.org/courses)
### **Fairness**
### **Interpretability & Explainability**
### **Causality**
### **Adversarial Attacks & Robustness**
### **Other Topics**
- Ethics
- Security
- Accountability
- Safety
- Confidentiality
- Unlearning/Forgetting
- Decentralization/Federated Learning
### **Other Related and Larger Collections**
- [Awesome ML Fairness](https://github.com/brandeis-machine-learning/awesome-ml-fairness)
- [Awesome Trustworthy Deep Learning](https://github.com/MinghuiChen43/awesome-trustworthy-deep-learning)
### **References**
- [Trustworthyml.org](https://www.trustworthyml.org/home): This website provides a wonderful introduction and set fo resources to various sub-fields in Trustworthy ML.
### **Credits**
One step in the process of creating this collection was reaching out to fellow Trustworthy ML enthusiasts and practioners openly on twitter (https://twitter.com/kritipraks/status/1624062696319770624). I'm thankful to the following people's recommendations (found in replies to the tweet): @iPrabhavKaula @DoUseBrainCells @uhsnayvid @miguelguirao @rohithpudari @IMossavat @hrbigelow @mzahmad_92 @AbhayPuri98 @mean_numpy_user @iot_01edge @it_s_katherine @AmolSingbal :)