Abstract

Data science, Artificial intelligence, Machine learning, , and deep learning are just few of the terminology that almost everyone has been familiar with as the collection and analysis of data has become one of the most important aspects of the contemporary world. However, what do each of these phrases really mean? What are the distinctions between them, and how do they relate to one another? Although all of the phrases above are linked in some way, they cannot be substituted for one another. Whether you are an expert who is interested in data-driven research, a company owner who is ready to get the most out of current technology, or simply someone who wants to become more tech-savvy, this course is for you.The interdisciplinary field of data science refers to the study of gaining insight from large amounts of data. Consider, for example, the recommendation systems that are used to provide individualised recommendations to clients based on the history of their search activity. If two different customers search for different fishing-related things, such as rods and lures, and then one of those customers searches for fishing line in addition to the other products, there is a good possibility that the first client will also be interested in buying fishing line. Data science is a vast discipline that encompasses all of the activities and technology that assist develop such systems, especially those that are going to be discussed in the following paragraphs. The study of artificial intelligence is a difficult endeavour. Let’s assume, however, for the purpose of clarity, that the term “artificial intelligence” may be used to any real-world data product. Let’s continue to use the fishing analogy as our example. You want to purchase a certain model of fishing rod, but all you have is a photo of it, and you’re not sure what brand it is. An artificial intelligence system is a piece of software that can analyse your photo and provide recommendations about a product name and stores where you may purchase the item. It is necessary to make advantage of machine learning and even deep learning sometimes while developing an AI product.The goal of machine learning is to instruct computers using historical information so that they can process new inputs based on previously learned patterns without the need for explicit programming. This means that the machines will be able to perform tasks without being given specific, hand-written instructions. It is difficult for a human to process millions of search queries, likes, and reviews to discover which customers commonly buy rods with lures and which customers purchase fishing line in addition to that. If it were not for machine learning, the recommendation engines that we have already mentioned above would be unattainable.Deep learning is the most talked about subfield in machine learning. It is characterised by the use of deep neural networks and complicated algorithms that are modelled after the way the human brain processes information. DL models are able to provide reliable findings from vast amounts of input data even when they are not provided with explicit instructions for which data features to examine. Imagine that you have the responsibility of identifying the fishing rods that lead to favourable reviews being posted on your website and those that lead to bad reviews being posted there. Deep neural networks have the ability to do sentiment analysis and extract significant attributes from reviews in this scenario. This contemporary book on “Understanding Data Science (AI, ML & DL)” focuses on the fundamentals of Data Science, illuminating how to grasp Artificial Intelligence, Machine Learning, and Deep Learning in a more holistic manner. Students in India attending colleges and universities for their M.Tech, M.Sc, or MCA degrees follow the same curriculum as outlined in the book.

Keywords:

Data Science, Artificial Intelligence, Machine Learning, Deep Learning

Bibliography

Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017, August). Understanding of a convolutional neural network. In 2017 international conference on engineering and technology (ICET) (pp. 1-6). Ieee.
Bell, J. (2022). What Is Machine Learning?. Machine Learning and the City: Applications in Architecture and Urban Design, 207-216.
Bengio, Y., Goodfellow, I., & Courville, A. (2017). Deep learning (Vol. 1). Cambridge, MA, USA: MIT press.
Bica, I., Alaa, A. M., Lambert, C., & Van Der Schaar, M. (2021). From real‐world patient data to individualized treatment effects using machine learning: current and future methods to address underlying challenges. Clinical Pharmacology & Therapeutics, 109(1), 87-100.
Bonaccorso, G. (2017). Machine learning algorithms. Packt Publishing Ltd. Flasiński, M. (2016). Introduction to artificial intelligence. Switzerland: Springer International Publishing.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
Kattenborn, T., Leitloff, J., Schiefer, F., & Hinz, S. (2021). Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 173, 24-49.
Learning, D. (2020). Deep learning. High-Dimensional Fuzzy Clustering.
Li, Y., Kumar, R., Lasecki, W. S., & Hilliges, O. (2020, April). Artificial intelligence for HCI: a modern approach. In Extended Abstracts of the 2020 CHI conference on human factors in computing systems (pp. 1-8).
Mohammed, M., Khan, M. B., & Bashier, E. B. M. (2016). Machine learning: algorithms and applications. Crc Press.
Murphy, K. P. (2022). Probabilistic machine learning: an introduction. MIT press.
Ray, S. (2019, February). A quick review of machine learning algorithms. In 2019 International conference on machine learning, big data, cloud and parallel computing (COMITCon) (pp. 35-39). IEEE.
Schütt, K. T., Sauceda, H. E., Kindermans, P. J., Tkatchenko, A., & Müller, K. R. (2018). Schnet–a deep learning architecture for molecules and materials. The Journal of Chemical Physics, 148(24), 241722.
Sewak, M., Sahay, S. K., & Rathore, H. (2020). An overview of deep learning architecture of deep neural networks and autoencoders. Journal of Computational and Theoretical Nanoscience, 17(1), 182-188.
Winston, P. H. (1992). Artificial intelligence. Addison-Wesley Longman Publishing Co., Inc..

Download Sample Pages

How to cite this Book: 

APA:
Magesh.S, Rajakumar P.S, Geetha.S, (2022). Understanding Data Science (AL, Ml &DL) (1st ed., pp. 1-154). Jupiter Publications consortium,ISBN:978-93-91303-35-8, DOI: https://doi.org/10.47715/JPC.B.84.2022.9789391303358