This course will teach you everything you need to know about machine learning and deep learning from the ground up. It will cover both the theory and the practical skills you need to build your projects. By the end, you will be able to start from scratch and create complete machine learning projects yourself.

I will check notebooks for outdated libraries and update them whenever possible.

1- The Fundamentals of Machine Learning Slides1 - Slides2

2- Dataset Loading Slides - Notebook

3- Exploratory Data Analysis Slides - Notebook

4- Feature Selection and Extraction (image, text), Standardization, Normalization

5- Regression: Linear regression, Ridge regression, Kernel Ridge regression, Polynomial Regression, SV Regression, Decision tree regression Slides - Notebook

6- Classification: SVM, Logistic Regression, Stochastic Gradient Descent, KNN, Naive Bayes Classification, Decision Trees - Notebook

7- Ensemble Methods: Random Forest Classifier, Voting Classifier, AdaBoost, Gradient Boosting, XGBoost

8- Neural Networks

9- Model selection and evaluation: Cross-Validation, Hyperparameter Tuning, Pipeline

10- Clustering: K-means, DBSCAN, Hierarchical clustering Notebook

11- Projects : Notebook1 - Notebook2

1- Deep Learning and Neural Networks (Classification and Regression) Slides1 - Slides2 - Notebook1 - Notebook2

2- Convolutional Neural Network (CNN) Slides - Notebook

3- Transfer Learning (TL) Slides - Notebook

4- CNN Architectures and Autoencoder Notebook

5- Recurrent Neural Networks and Time-series Forecasting Slides - Notebook

6- Natural Language Processing (NLP) Slides - Notebook

7- Computer Vision (CV) (YOLO, Faster RCNN, Mask RCNN, Detectron2) Slides - Notebook1 - Notebook2 - Notebook3

8- Generative Adversarial Networks (GAN) Slides - Notebook

9- Audio Classification - Notebook

10- Transformers Slides

1- Machine Learning: Python + Scikit-Learn

2- Deep Learning: Python + TensorFlow and Keras

1- This course is designed for beginners and intermediate learners.

2- Basic programming experience is required, and basic knowledge of mathematics and statistics is recommended.