The following is a ML repository where I've included my notes on various Standford ML courses, some of the projects I did there, and created easy to understand tutorials for the purpose of teaching others.
Machine Learning Specialization -- Offered by Standford
Personal Notes: https://drive.google.com/file/d/1p-jURWcMEi7SYH7OzBX0OUGYy3h1WsJV/view?usp=sharing
All Projects: https://github.com/Tahir001/Artificial-Intelligence/tree/main/Standford%20ML%20Specialization
Courses: Supervised Machine Learning (Regression and Classification), Advanced Learning Algorithms, Unsupervised Learning, Reccomenders and Rienforcement Learning
Contents / Algorithms:
- Linear Regression
- Loss Functions and Gradient Descent
- Logistic Regression
- Decision Trees
- Neural Networks
- Feature Engineering
- Overfitting & Underfitting
- Regularization & Hyperparameters
- Multi-class Classifcation with NNs
- Tensorflow (Neural Networks, Autograd, Data Loaders)
- Transfer Learning & Debugging ML algorithms
- ML Metrics (Accuracy, Precision, Recall, F1-Score, etc)
- XGBoost, Random forests, Bagging vs Boosting
- K-Means Clutering, Expectation-Maximization Theorm
- Anamoly Detection, Multivariate Distributions
- Principal Component Analysis (PCA)
- Reccomendation Systems (Content-Based vs Collaborative Filtering)
- Reinforcement Learning (Markov Decision Process, Finite and Continous States)
Deep Learning Specialization -- Offered by Standford
Personal Notes:
My coded projects:
Concepts Learned:
Technical Framework & Tools:
ML-Ops Specialization - Machine Learning Engineering in Production, Offered by Standford & Google Engineers
Personal Notes:
My coded projects:
Concepts Learned:
Technical Framework & Tools:
Tensorflow Developers Certificate -- Taught by Google Engineers
Personal Notes:
My coded projects:
Concepts Learned:
Technical Framework & Tools: