Abstract
The recent development in artificial intelligence is quite astounding in this decade. Especially, machine learning is one of the core subareas of AI. Also, ML field is an incessantly growing along with evolution and becomes a rise in its demand and importance. It transmogrified the way data is extracted, analyzed, and interpreted. Computers are trained to get in a self-training mode so that when new data is fed they can learn, grow, change, and develop themselves without explicit programming. It helps to make useful predictions that can guide better decisions in a real-life situation without human interference. Selection of ML tool is always a challenging task, since choosing an appropriate tool can end up saving time as well as making it faster and easier to provide any solution. This chapter provides a classification of various machine learning tools on the following aspects: for non-programmers, for model deployment, for Computer vision, natural language processing, and audio for reinforcement learning and data mining.
TopIntroduction
In this era of digitalization, data is generated and stored in every field. This data has the potential to be used to predict future possibilities. ML comprises of using this data to train a model for predicting results for new observations without any explicit instructions. It predicts results by analyzing the patterns in the given dataset.
Ranging from a very basic task of separating the spam emails to the revolutionary Cyborg technology ML has a wide range of applications in our life. It not only eases our tasks but has the potential to solve some of the most challenging issues of the society (Anirudhi Thanvi et al., 2019). A lot of research is going on to improve the quality and efficiency of medical care using ML. Digital diagnosis of life-threatening diseases like cancer helps to detect the problem at a very early stage, making it possible to treat it before it turns lethal. ML has great potential across several other domains like Education (Kotsiantis, 2012), Farming (Li et al., 2014; Paul et al., 2016), Environment Conservation (Rahman et al., 2014), Security (Buczak & Guven, 2016), Social Media (Alatabi & Abbas, 2020; ReddyPY.Sushmitha & M.Padma, 2016), Information Verification (Herrera et al., 2010; Sharma et al., 2019) and a lot more(Vyas & Jangir, 2019).
ML tools provide a more convenient way for developers to build, train, and deploy their models. Tools help to speed up the process by automating each step of the process which otherwise needed to be implemented manually from scratch. They help to eliminate the barrier between imagination and implementation of ideas due to a lack of skills. Developers need not be an expert in every step of implementation. They can implement their ideas easily once they are trained to work with a tool (Kumar Jangir et al., 2018, 2019).
The authors reviewed more than 50 papers and more than 100 blogs, articles, and websites that used various data analytics tools for carrying out different processes. The motivation behind carrying out this survey was the unavailability of research work that classified data analytics tools in various categories and gave a brief description of each tool.
This chapter divides data analytics tools into different categories for the simplicity and ease of choosing the right tool. It tells about the needs of tools for data analytics. The rest of the chapter is arranged as follows: Python Libraries used for carrying out various data analytics processes are explained followed by the tools for Big Data Analysis that help to organize and analyze large and complex datasets, which are difficult to be tackled by traditional database and software techniques. Then it states data mining tools that use mathematics, statistics, algorithms, and other scientific ways to provide insights from the given data set. The description is taken further by explaining tools that assist in Natural Language Processing, Voice recognition, face identification, and voice synthesizing which are classified as Tools for Computer Vision, NLP, and Audio. Then tools for Reinforcement learning that helps the agent to learn from its experiences are mentioned. After that tools that help to integrate the ML model with the existing production environment are categorized as tools for Model Deployment. At last, tools that obviate the need for programming skills are categorized under the category of tools for Non-Programmers. Various use cases of tools by different companies are given for each category. The use of some of the tools for research and development is also discussed along with the methodology, dataset description, and results used to carry out that research.
Key Terms in this Chapter
Artificial Intelligence: Domain of science that deals with the development of computer systems to perform actions like speech-recognition, decision-making, understanding human’s natural language, etc., like humans.
Machine Learning: It refers to developing the ability in computers to use available data to train themselves automatically, and to learn from its own experiences without being explicitly programmed.
Deep Learning: Sub-domain in the field of machine learning that deals with the use of algorithms inspired by human brain cells to solve complex real-world problems.
Model: In the context of machine learning, model refers to a transformation engine that helps to express a mathematical problem.e to express the dependent variables as a function of independent variables.
Contrived: Something that has not arisen naturally, rather it has been created deliberately or artificially.
Data-Mining: It refers to the process of obtaining useful insights from large datasets by using statistical methods to find patterns followed throughout the dataset.
Natural Language Processing: Sub-domain of artificial intelligence that deals with programming of computers to process large amount of natural language data.
Data-Science: Field of Science that concerns with the cleansing, preparation and final analysis of data using programming, logical reasoning, mathematics, and statistics.
Computer Vision: Domain in science that deals with the use of computers in understanding and automating the tasks that a human visual system can do.
Big Data: It refers to a massive volume of structured or unstructured data that is difficult to be processed by traditional data management tools.
Deployment: The process of putting a resource into action in real-world scenarios.