Here are some points about MachineLearning :
- Machine Learning means learning from Data.
- Machine = Your machine/computer Learning = Finding patterns from data
- Machine Learning is just Data + Algorithms, but Data is more important.
- Feature extraction is key. If total prediction power is 100% then the effort of feature engineering = 80% and the effort of the learning algorithm = 20%.
- Overfitting is when your algorithm is memorizing instead of learning.
- If you have small amounts of data then you’re better off using more simple models (linear&logistic regression). If you have large amounts of data you can try out more complex models (Deep Learning, etc.)
- To avoid overfitting, always use regularization
- Training is the most important part of Machine Learning. Choose your features and hyper parameters carefully.
- Machines don’t take decisions, people do.
- Data cleaning is the most important part of Machine Learning. You know the saying: Garbage in Garbage out.
Author : Randy Lao