What is Machine Learning (ML)?
Machine learning algorithms build mathematical models based on sample data, known as training data. Using the training data, ML engineers build systems that automatically update themselves, and are able to make decisions or take actions without any human assistance.
Simply put, machine learning involves teaching computers to learn by themselves, without being programmed by humans for each and every task. 🤖
What are the different types of ML algorithms? (Or how can you teach machines to learn?)
There are three types of ML models:
- Supervised learning: In your algorithm, you include training data that contains inputs as well as the desired outputs (the results that you want). Regression and classification algorithms are examples of supervised learning algorithms. Real world applications of supervised learning include recommendation systems and facial recognition.
- Unsupervised learning: In your algorithm, you only include inputs, no correct outcomes. The goal is to teach the computer to identify unknown patterns in data (patterns that you don't know exist). Clustering algorithms are examples of unsupervised learning algorithms. Real world applications include detecting fraud and identifying investment opportunities.
- Reinforcement learning: For this model, you don't tell the machine what is the right outcome, but you either reward or penalize each action (remember how you learned good and bad behavior as a kid?). Q-learning is an example of reinforcement learning algorithm. Examples include operating autonomous vehicles and teaching machines to play video games.
What are the applications of ML?
Popular applications of machine learning include:
- Web search engines (think Google)
- Photo tagging applications (think Google Photos)
- Recommendation systems for streaming services (think Netflix)
- Dynamic pricing (think Uber)
- Biometric access systems (think of all the Mission Impossible movies)
Think we're missing something? 🧐 Help us update this article by sending us your suggestions here. 🙏