MACHINE LEARNING BASICS
Machine learning is a method of artificial intelligence, which enables computers to learn and perform tasks without us needing to program them specifically for everything. It is the most popular and fastest growing field of artificial intelligence. We use it everyday, it drives things like spam filtering , credit card fraud detection, digit recognition on checks, zip codes, detecting faces in images, MRI image analysis, recommendation system, search engines, handwriting recognition, scene classification and much more.
There are mainly three types of machine learning-
1) Supervised Learning
2) Unsupervised Learning
3) Reinforcement Learning
Supervised learning approach is when we already know the outcome and what our model is going to predict. We feed the model with input values and the output values to learn. The model learns how to draw a pattern and returns the closest output value when tested against a new input. Eg- A model to identify spam emails is trained with supervised learning.
Unsupervised learning takes place when the model is only fed with input values, and no output values. The machine then learns how to draw relationships and structure of that data, often forming clusters. Eg- Recommendation systems of YouTube and search bars.
Reinforcement learning is different from the above two, as it learns from the consequences of it’s actions rather being trained beforehand. This can be similar to hit and trial method. Eg- Game playing bots.
