Machine Learning (ML)
Machine Learning (ML)
Machine learning is a branch of AI, used to process and analyse the data using various algorithms that mimics the learning behaviour of humans for analysing the data. These algorithms predict the outcomes without intervention of human. It provides the systems that automatically learn and improve based on their experience.
Fig 1 depicts the process of machine learning. It consists of five steps starting with collection of data and ends at model deployment. These are 5 basic steps:
Collection of Data from various data source
Data cleaning and Feature Engineering
Model building and Selection of ML Algorithm
Model Evaluation
Model Deployment
Fig. 1 Basic Process of Machine Learning
Generally, Data collection is the key process in ML. Based on the addressed problem, we have to obtain the data from different sources. Data can be collected from social media, public opinion poll, or survey of the product success or failure. Next step in ML is data cleaning.
Before starting the analysis, we have to understand the obtained data set and pick up the cleaning activity to purify the data set, to get the optimized results. Data cleaning process gives you the better understanding of the features and the relationships between each entities/features/attributes. While cleaning the data, extraction of essential variables and avoiding non-essential variables is utmost important and is also a challenge. The third step is the model selection that should be done very carefully. In this step, training of the model is taken care of with the subset of the data and the trained model is then tested. Trained model is now evaluated for its accuracy. At the end, machine learning models are deployed into production environment.
The process of machine learning is not that easy. The reason for it being so complex is very clear, since a large amount of complex data is processed and analysed for meaningful predictive patterns and models.
Types of machine learning
Machine learning is categorized into different types and these type are demonstrated in Fig. 2
Unsupervised Learning
Supervised learning is one of the type of ML algorithms that presupposes both input and output data is initially provided. Basically, data engineers create an algorithm, then train it with a labelled dataset — the one that has actual input and output parameters. The result of a quality training process is the ability to pick a function that gives the processes the input data in the most adequate and accurate way, as it was sampled in the training dataset.
Supervised Learning
Unsupervised learning is a type of algorithm which works with the input data having no examples or suggestions of the expected output. Its primary aim is to distribute the data into categories so that the output would be more informative compared to the loaded input. The term unsupervised means that there is no supervisor who could tell the system right answers, in fact, there are no right or wrong answers in the first place.
Fig. 2 Types of Machine Learning
Reinforcement Learning
This Machine Learning type has been booming in the past few years, and researchers prefer this type of learning more. Reinforcement Learning covers more area of Artificial Intelligence which allows machines to interact with their dynamic environment in order to reach their goals. With this, machines and software agents are able to evaluate the ideal behavior in a specific context.
With the help of this reward feedback, agents are able to learn the behavior and improve it in the longer run. This simple feedback reward is known as a reinforcement signal.
Prerequisites for Machine Learning
As a beginner, you must be familiar with the following concepts to work in the area of Machine Learning:
Different Applications Areas of ML:
Machine learning is the demand of today’s technological world and has gained the popularity in various domains. Machine learning proposes an abundance of techniques to extricate knowledge from data that can be rendered into purposeful objectives.
Fig. 3 Application Areas of Machine Learning
Popular Frameworks for ML:
TensorFlow
TensorFlow is an open-source framework that comes in handy for large-scale as well as numerical ML. It includes machine learning models as well as neural network models. The most prominent feature of TensorFlow is, it runs on CPU and GPU as well.
Weka
It is also open-source software and can be accessed through a graphical user interface. This software is very user-friendly. It is widely used in research and teaching purposes.
Pytorch
Pytorch is a deep learning framework. It is very fast as well as flexible to use. This is because Pytorch has a good command over the GPU. It is one of the most popular tools of machine learning because it is used in the most vital aspects of ML which includes building deep neural networks and tensor calculations. Pytorch is completely based on Python.
Google Cloud AutoML
Google cloud AutoML is used to make artificial intelligence accessible to everyone. What Google Cloud AutoML does is, it provides the models which are pre-trained to the users in order to create various services. For example, text recognition, speech recognition, etc.
Google Cloud AutoML became very much popular among companies. As the companies want to apply artificial intelligence in every sector of the industry but they have been facing difficulties in doing so because there is a lack of skilled AI persons in the market.
Jupyter Notebook
is a very fast processing as well as an efficient platform. Moreover, it supports three languages viz. Julia, R, Python. Thus the name of Jupyter is formed by the combination of these three programming languages. Jupyter Notebook allows the user to store and share the live code in the form of notebooks. One can also access it through a GUI. For example, winpython navigator, anaconda navigator, etc.
Comments
Post a Comment