What is Machine Learning ?
Let’s see what is Machine Learning and how it works...
What is Machine Leaning ?
Machine Learning is the study of computer algorithms that improve automatically through experience. It is a is the process of teaching a computer system how to make accurate predictions when fed data. It is seen as a subset of Artificial Intelligence(AI).
In simple term machine learning is an application of the AI. It allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. By using machine learning algorithms we can predict so many things in the world, because machine learning algorithms use historical data as input to predict new output values.
What is the different between Artificial Intelligence and Machine Learning ?
Artificial Intelligence(AI) systems will generally demonstrate at least some of the these traits. Those are planning, learning, reasoning, problem solving, knowledge representation, perception, motion, and manipulation and, to a lesser extent, social intelligence and creativity. And the other side Machine Learning(ML), there are various other approaches used to build AI systems, including evolutionary computation, where algorithms undergo random mutations and combinations between generations in an attempt to “evolve” optimal solutions, and expert systems, where computers are programmed with rules that allow them to imitate the behavior of a human expert in a specific domain, for example an autopilot system flying a plane [1].
Types of Machine Learning
Generally Machine Learning divided into four types. It is categorized by how an algorithm learns to become more accurate in its predictions. Those types are,
- Supervised Learning
- Unsupervised Learning
- Semi-supervised Learning
- Reinforcement Learning
The type of algorithm a data scientist chooses to use depends on what type of data they want to predict.
What is Supervised Learning ?
Supervised learning is when the model is getting trained on a labelled dataset. Labelled dataset is one which have both input and output parameters. Training for supervised learning, systems are exposed to large amounts of labelled data. Data scientists supply algorithms with labeled training data and define the variables they want the algorithm to assess for correlations. Both the input and the output of the algorithm is specified.
How supervised machine learning works
Supervised machine learning requires to train the algorithm with both labeled inputs and desired outputs. Supervised learning algorithms are good for the following tasks,
- Binary classification — To divide the data into two categories.
- Multi-class classification — To choose between more than two types of answers.
- Regression modeling — To predict continuous values.
- Ensembling — To combine the predictions of multiple machine learning models to produce an accurate prediction.
What is Unsupervised Learning ?
In Unsupervised learning, algorithm used to draw inferences from datasets consisting of input data without labeled responses. Here we take algorithms with identifying patterns in data, trying to spot similarities that split that data into categories.
How unsupervised machine learning works
Unsupervised machine learning algorithms do not require data to be labeled. They sift through unlabeled data to look for patterns that can be used to group data points into subsets.
Most types of deep learning, including neural networks, are unsupervised algorithms. Unsupervised learning algorithms are good for the following tasks:
- Clustering — To split the data set into groups based on similarity of the data.
- Anomaly detection — To identify unusual data points in a data set.
- Association mining — To identify sets of items in a data set that frequently occur together.
- Dimensionality Reduction — To reduce the number of variables in a data set.
What is Semi-supervised Learning ?
In Semi-supervised Learning involves a mix of the two preceding types. The technique relies upon using a small amount of labelled data and a large amount of unlabeled data to train systems. The labelled data is used to partially train a machine-learning model, and then that partially trained model is used to label the unlabeled data, a process called pseudo-labelling. The model is then trained on the resulting mix of the labelled and pseudo-labelled data.
How semi-supervised learning works
Semi-supervised learning works by feeding a small amount of labeled training data to an algorithm. The performance of algorithms typically improves when they train on labeled data sets. Semi-supervised learning strikes a middle ground between the performance of supervised learning and the efficiency of unsupervised learning. Some areas where semi-supervised learning is used include:
- Machine translation — To teach algorithms to translate language based on less than a full dictionary of words.
- Fraud detection — To identify cases of fraud when you only have a few positive examples.
- Labeling data — To train algorithms on small data sets can learn to apply data labels to larger sets automatically.
What is Reinforcement Learning ?
This is not like unsupervised and supervised machine learning, reinforcement learning does not rely on a static dataset. It operates in a dynamic environment and learns from collected experiences. Data points, or experiences, are collected during training through trial-and-error interactions between the environment and a software agent. This aspect of reinforcement learning is important, because it alleviates the need for data collection, preprocessing, and labeling before training, otherwise necessary in supervised and unsupervised learning.
How reinforcement learning works
Reinforcement learning works by programming an algorithm with a distinct goal and a prescribed set of rules for accomplishing that goal. Reinforcement learning is often used in areas like,
- Robotics — Robots can learn to perform tasks in the physical world using this technique.
- Video gameplay — Reinforcement learning has been used to teach bots to play a number of video games.
- Resource management — Given finite resources and a defined goal.
Uses of Machine Learning
Today most of the time we are using machine learning in our daily life even without knowing it. Such as Google maps, Google assistant, Alexa, Siri etc. And it is growing very rapidly day by day.
Machine learning can help enterprises understand their customers at a deeper level. By collecting customer data and correlating it with behaviors over time, machine learning algorithms can learn associations and help teams tailor product development and marketing initiatives to customer demand. Like wise, most of the time it easier our works.
Conclusion
In this article I just give only brief introduction about the Machine Learning. We can use machine learning to predict the data and it is very useful technique for us.
Therefore, in the future, I hope to discuss more about the Machine Learning and how can we do the predictions by using machine learning with you.
Thank you for going through this article and feel free to leave a few claps if you found this helpful.
References
[1] Heath, N., 2020. What Is Machine Learning? Everything You Need To Know | Zdnet. [online] ZDNet. Available at: <https://www.zdnet.com/article/what-is-machine-learning-everything-you-need-to-know/> [Accessed 2 December 2020].
[2] SearchEnterpriseAI. 2020. What Is Machine Learning (ML)?. [online] Available at: <https://searchenterpriseai.techtarget.com/definition/machine-learning-ML> [Accessed 2 December 2020].
