Machine Learning
Machine Learning is all about using your algorithm to "learn". (Machine learning is a sub-branch of Artificial Intelligence)
We usually take some data, train a model on that data, and then used the trained model to make predictions on new data.
We need machine learning on cases that would be difficult to program by hand all possible variants of classification/ prediction problem
Machine Learning Comes in Two Flavors:
Supervised Learning: You give your algorithm some pairs of input/output, so in the future when new inputs are presented you have an intelligent output
Unsupervised Learning: You let your algorithm to learn from the data itself without showing what is the expected output
Example of Supervised Learning
Classification: You train your data with labels and in the future, the algorithm classifies the label or recognize the label
Regression: You train your data on historical data and then in the future, the algorithm predicts the value
Example of Unsupervised Learning
Clustering: You ask the computer to separate or cluster similar kinds of data.
High Dimension Visualisation: Use the algorithm to help us visualize high dimension data
Generative Models: After a model captures the probability distribution of your input data, it'll be able to generate more data.
The Basic Recipe
This is the super simple recipe to solve a machine learning problem
