Types of ML

 Types of Machine Learning




1. Supervised learning:
  • Learning from Examples: Imagine you're a teacher helping a student learn to recognize different animals. You show the students pictures of animals and tell them the name of each animal in the picture. The student learns by looking at the pictures and listening to your labels.
  • Labeled Data: In machine learning, the pictures are called "data," and the names of the animals are called "labels." Together, they make "labeled data."
  • Training a Model: The student is like the machine learning model. During the "training" phase, the model looks at the data (pictures) and the labels (animal names) to understand the relationship between them.
  • Making Predictions: After learning from many examples, the model can look at a new picture (one it hasn't seen before) and guess the animal's name. This guessing is called "making predictions."
  • Improvement Over Time: Just like the student gets better at recognizing animals with more practice, the model improves as it sees more labeled data.



2. Unsupervised learning:
  • No Labels: The computer looks at data that doesn't have labels or predefined answers. It just gets a bunch of data and tries to find patterns or groupings independently.
  • Finding Patterns: The main goal is to see if the computer can discover any interesting patterns or groups within the data. It's like giving it a pile of mixed-up puzzle pieces and seeing if it can sort them into meaningful sections.


3. Reinforcement learning:

  • Exploration: The agent tries different actions in the environment to see what happens.
  • Exploitation: Based on the feedback (rewards) received, the agent learns which actions are good and tends to choose those more often.
  • Learning: Over time, the agent improves its decision-making by learning from its experiences and optimizing its actions to maximize rewards.
  • Example: In the movie PK, Aamir Khan's character attempts to purchase carrots using Indian currency featuring Mahatma Gandhi's face, believing it to be universally accepted for transactions. He gathers all the pieces of paper with Gandhi's image and presents them to the shopkeeper, expecting to receive carrots in return. However, he learns from the shopkeeper's refusal that only Indian currency notes are acceptable for transactions. This experience teaches him the importance of using the right form of currency and the limitations of his initial assumption, illustrating his learning process through trial and error.






























  • Comments

    Popular posts from this blog

    Basics of AI

    Basics of Neural networks