There are essentially two ways neural networks can recognize patterns:
...is like learning with a teacher, training dataset is like a teacher, the training dataset is used to train the machine...
Supervised learning is the machine learning task of learning a function that maps an input to an output based on example input-output pairs.
It infers a function from labeled training data consisting of a set of training examples. In supervised learning, each example is a pair consisting of an input object (typically a vector) and a desired output value (also called the supervisory signal). A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples. An optimal scenario will allow for the algorithm to correctly determine the class labels for unseen instances
examples of supervised learning
You get a bunch of photos with information about what is on them and then you train a model to recognize new photos. You have a bunch of molecules and information about which are drugs and you train a model to answer whether a new molecule is also a drug.
Unsupervised learning is a branch of machine learning that learns from test data that has not been labeled, classified or categorized. Instead of responding to feedback, unsupervised learning identifies commonalities in the data and reacts based on the presence or absence of such commonalities in each new piece of data. Alternatives include supervised learning and reinforcement learning.
examples of unsupervised learning
You have a bunch of photos of 6 people but without information about who is on which one and you want to divide this dataset into 6 piles, each with the photos of one individual. You have molecules, part of them are drugs and part are not but you do not know which are which and you want the algorithm to discover the drugs.
- This video is good to understand the difference of supervised vs unsupervised learning
- This link is very good to provide practical examples of the difference between supervised and unsupervised learning
From the IB
The concepts of supervised and unsupervised learning should be applied to the examples above (speech recognition, OCR, and natural language) and to any clearly explained example presented in the examination, as should the importance of genetic algorithms.
- Compare different ways in which neural networks can be used to recognize patterns