What is Machine Learning? The science of getting computers to learn without being explicitly programmed. It is a subfield of AI (Artificial Intelligence), and is now widely used today.
Made an account on DeepLearning.AI
Machine Learning is likely to touch every industry in the coming years. AI Researchers are also looking even further into the future and excited at the prospect of Artificial General Intelligence (AGI).
It’ll take 50 years or 500 years or longer to get there. But mostly AI researchers believe that the best way to get closer toward that goal is by using learning algorithms. Maybe ones that take some inspiration from how the human brain works.
-Andrew Ng
Machine Learning: “The field of study that gives computers the ability to learn without being explicitly programmed.” -Arthur Samuel (1959)
Arthur Lee Samuel created a checkers playing program. He programmed the computer to play 10s of thousands of games. By watching what positions lead to wins VS losses, it learned what positions are GOOD vs BAD. With this knowledge, it learned how to get itself into those GOOD positions.
If Arthur Samuel's checkers-playing program had been allowed to play only 10 games against itself, how would this have affected its performance compared to when it was allowed to play over 10,000 games?
A: Would have made it worse
In general, the more opportunities you give a learning algorithm to learn, the better it will perform.
Types of Machine Learning Algorithms
- Supervised Learning
- Used most in real-world applications. Has also seen the most advances
- Unsupervised Learning
- Recommender Systems
- Reinforcement Learning