Artificial Intelligence, deep learning, machine learning — whatever you’re doing if you don’t understand it — learn it. Because otherwise you’re going to be a dinosaur within 3 years.” ~ Mark Cuban.
When it comes to artificial intelligence (AI) and machine learning, there are two basic approaches: supervised learning and unsupervised learning.
Supervised Learning
Any machine learning method which is trained using labeled dataset is tagged as supervised machine learning method. The data provided to the machine to carry out the learning process is already marked with the correct label.
And therefore, based on the training dataset, the machine produces an outcome once provided with the actual data or testing data.
For example, let's consider an apple and a watermelon, we can provide our machine with information such as," If the shape of the fruit is rounded and, is red then it will be labeled an apple.", otherwise," If the shape of the fruit is rounded and, is green then it will be labeled a watermelon." Once the machine learns the above information, it is able to categorize the type of fruit when provide with raw information at the testing stage or deployment stage based on the color of the fruit.
Supervised learning is classified into two categories of algorithms:
Classification: A classification problem is when the output variable is a category, such as “Yes” or “No” or “Fast” and “Slow”.
Regression: A regression problem is when the output variable is a real value, such as “dollars” or “weight”.
Advantages
- Supervised learning allows collecting data and produces data output from previous experiences.
- Helps to optimize performance criteria with the help of experience.
- Supervised machine learning helps to solve various types of real-world computation problems.
Disadvantages
Classifying big data can be challenging.
Training for supervised learning needs a lot of computation time. So, it requires a lot of time.
Unsupervised Learning
Unsupervised learning algorithms are trained using unlabeled data and do not need human intervention. The machine is restricted to find the hidden structure in unlabeled data by itself.
For Example, the machine is given an input of images consisting of cars and bikes which it has never seen before. Now the machine will itself try to find a common pattern between the images and would categorize similar images with one another without any prior knowledge about the same.
Unsupervised learning is classified into two categories of algorithms:
Clustering: Clustering is where you want to discover the inherent groupings in the data, such as grouping customers by purchasing behavior.
Association: Association rule learning problem is where you want to discover rules that describe large portions of your data, such as people that buy X also tend to buy Y.
Advantages
- Fewer data is needed.
- Classifying big data can be easy as compared to supervised.
Disadvantages
- Computationally complex
- Less accurate