Machine Learning and Data Science from A to Z
Part 1 - Classification
- Data Pre-processing
- Naive Bayes
- Decision Trees
- Random Forest
- Rule-based models
- Instance-based models (KNN)
- Logistic Regression
- SVM (Support Vector Machines)
- Artificial Neural Networks
- Algorithms validation
- Combination and rejection of classifiers
Part 2 - Regression
- Simple Linear Regression
- Multiple Linear Regression
- Polynomial Regression
- Decision Trees
- Random Forest
- SVM (Support Vector Machines)
- Artificial Neural Networks
Part 3 - Association
- Apriori
- Eclat
Part 4 - Clustering
- K-Means
- Hierarchical Clustering
- DBSCAN
Part 5 - Complementary topics
- Learning by reinforcement
- Natural Language Processing
- Computer Vision
- Unbalanced data
- Atribute selection
- Dimensionality reduction (PCA, LDA)
- Outliers detection
- Time series
Machine Learning
We can divide the machine learning in two methods:
Predictive: The model learns from the data to make predictions.
- Classification: The model predicts a category.
- Regression: The model predicts a continuous value.
Descriptive: The model learns from the data to describe the data.
- Clustering: The model groups similar data.
- Association: The model finds rules that describe the data.
- Sumarization: The model summarizes the data.
- Sequence discovery: The model finds patterns in the data.
- Anomaly detection: The model finds outliers in the data.
Types of Machine Learning
- Supervised: The model learns from labeled data.
- Unsupervised: The model learns from unlabeled data.
- Reinforcement: The model learns from rewards and punishments.