It is science of making computers learn without being explicitly programmed.
“Field of study that gives computers the ability to learn without being explicitly programmed.”
Arthur Samuel
Machine Learning had grown to be a subfield of artificial intelligence
- how to rank web pages
- recognize people in the pictures and label them as well
- recommend sth you might like
- voice to text (Siri, Google Search) speech recognition
- detect spam mails
In general, the more opportunities you give a learning algorithm to learn, the better it will perform.
What are the major types of machine learning algorithms?
- Supervised learning: Data has right answers. It learns from being given “right answer” label Y
- You will first train your model with examples of input X and right answer output Y
- After the model has learned from these inputs and outputs, they can take a brand new input X, which has never seen before, and try to produce the appropriate corresponding output Y
- Regression and Classification
- Unsupervised learning: We are not given any labels Y. There is no label Y
- Finds some structure or some pattern in unlabeled data
- Data only comes with inputs X, but not output labels Y
- Clustering, Anomaly Detection, Dimensionality Reduction