Machine Learning Essentials
- Pipelines: A sequence of data processing components is called data pipeline.
- Linear Regression
- Tree Regression
- Forest Regression
- Use case: Unsupervised Learning is useful for Clustering, Anomaly dettecton and Density estimation
- Clustering: group similar instances together into clusters
- Data Analysis
- Customer Segmentation
- Recommender system
- search engines
- image classification
- semi-supervised learning
- dimensionality reduction
- Anomaly Detection: what normal data looks like then use that to detect abnormal instances.
- new trend in time serise
- find defective items
- Desnsity Estimation: Estimating the probability density function PDF of the random process
- anomaly detecttion: instances located in the very low-density regions liekly to be anamalies
- analysis and visualization
- Clustering: group similar instances together into clusters