
Daftar isi:
Machine learning is a branch of artificial intelligence that allows systems to adapt human abilities to learn. Without us knowing it, the use of machine learning is often present in everyday life.
According to Forbes, machine learning is a current trend that will continue to develop in at least the next ten years. So, so that you don’t miss this technology, let’s get to know machine learning more closely!
What is Machine Learning?

machine learning tutorial,tipe machine learning ,What is Machine Learning,Why is Machine Learning Important,Difference between Machine Learning and Artificial Intelligence,machine learning python,machine learning pdf,belajar machine learning
Quoted from IBM, machine learning is a branch or application of artificial intelligence.
Baca Juga :
This science focuses on creating systems or algorithms that continually learn from data and improve its accuracy over time without specific programming. In machine learning applications, algorithms or statistical process sequences are trained to find certain patterns and features in large amounts of data.
It aims to make decisions and predictions based on these data. The better the algorithm, the better the accuracy of the decisions and predictions of the system.
Like humans who get smarter if they learn a lot, machines that process more data will produce more accurate output.
Baca Juga:
As previously mentioned, machine learning is now an important part of our daily activities. An example of what machine learning is used for is a digital assistant that we can use on a smartphone to execute a command.
Besides, machine learning applications can also be felt when advertisements on the internet recommend products that match our interests. The same thing applies to Netflix, which can find out movie or series preferences according to what users have watched so far.
Apart from these examples, there are many other uses of machine learning for various other things.
Why is Machine Learning Important?
According to Towards AI, machine learning is very important nowadays.
Machine learning is useful for measurably solving world problems. The application of artificial intelligence science can also be used in various industries and continues to be used by large industry owners and researchers so that it can continue to grow.
With machine learning, we can process and analyze larger and more complex data in less time. In fact, according to The Wall Street Journal, machine learning and artificial intelligence have the potential to increase up to 16% or $ 13 trillion for the United States economy by 2030.
Of course, this too will gradually affect the world economy as well.
Difference between Machine Learning and Artificial Intelligence
You already know that machine learning is a branch of artificial intelligence or artificial intelligence.
Some of the main differences between machine learning and artificial intelligence are:
1. Success vs efficiency
The goal of artificial intelligence is to increase the chances of success, while machine learning aims to increase efficiency without being success-oriented.
2. Troubleshooting vs performance
Artificial intelligence aims to solve complex problems by simulating natural intelligence
Meanwhile, machine learning works by learning from data to improve machine or system performance.
3. Decision making
Artificial intelligence simply works to make decisions. On the other hand, machine learning focuses on learning about input data.
4. Algorithm
Artificial intelligence mimics human abilities in terms of response and behavior to systems. It is different from machine learning which can create its algorithms for the learning process.
5. Optimization
Artificial intelligence is in charge of finding optimal solutions, while machine learning does not consider this
Types of Machine Learning
1. Supervised learning
Supervised machine learning is a machine learning algorithm using labeled data, for example, input where the output is known.
For example, a device has a data point labeled F (failed) or R (runs). Supervised learning algorithms accept a set of inputs with the correct output.
After that, this algorithm learns by comparing the actual output with the correct output to find errors or errors. In supervised learning, the algorithm can modify the model to suit the desired results.
Usually, supervised learning is used in applications that predict future events based on historical data.
2. Semi-supervised learning
This machine learning method is not that different from supervised learning. However, semi-supervised learning uses labeled data and not train algorithms.
Typically, small amounts of labeled data are used and large amounts of unlabelled data are used. This machine learning method can be used with other methods such as classification, regression, and prediction.
An example of using semi-supervised learning is the process of identifying someone’s face on a webcam or smartphone camera.
3. Unsupervised learning
Unsupervised machine learning is the opposite of supervised learning. In this machine learning method, the processed data does not have a label and the system does not know the correct answer or output.
The purpose of machine learning with this method is to explore data and find structures in it. Usually, this method is used for transactional data.
For example, unsupervised learning can be used to identify segments of consumers with similar attributes and group them so that they can be handled or treated the same in a digital marketing campaign.
Not only that, but supervised learning can also find the main attributes that differentiate between consumer segments.
4. Reinforcement Learning
Reinforcement learning is typically used for robotics, game creation, and navigation.
With this learning method, the algorithm will be able to find an action or treatment that produces the best output from the results of repeated trials (trial and error).
There are three main components to reinforcement learning, namely agents (decision-makers), environment (what agents interact with), and action (what agents can do).
The primary goal of machine learning reinforcement is for agents to determine what actions maximize results within a given time.