Machine Learning and Deep Learning

Machine Learning and Deep Learning

Introduction

Machine learning and deep learning are the current technologies applied in the data science field. The two fields emerge from artificial intelligence, where machines are trained and tasked to gather data, classify and analyze it to come up with better decisions. Machine learning involves mainly getting data and making machines learn from those data and experiences to make better and more informed decisions (Dargan et al., 2020). Deep learning applies the same concept as machine learning but through the use of neural networks, which are programmed to make better decisions. These technologies apply various algorithms and methods to achieve their goals (Dargan et al., 2020).

Applications: Health Care Industry

Deep learning and machine learning are applied in fields like entertainment, banking, healthcare, and marketing. They are mainly used for solving problems of classification, regression, data visualization, robotics, clustering, recognition, and prediction (Dargan et al., 2020). Our research will discuss the various case studies which apply machine learning and deep learning algorithms in the industry of healthcare.

Case Study 1: Disease Identification and Diagnosis

Machine learning and deep learning are mainly applied in identifying diseases that are hard and complex to identify. These include diseases that have a gradual infection and are hard to detect during the infection stage for example cancer and tumor (Roy, Kiral-Kornek, & Harrer, 2018). These technologies are now being applied in reducing errors experienced when normal human beings try to diagnose a patient. This high accuracy is achieved through the use of algorithms like cognitive computing.

Case Study 2: Health Records Management.

The healthcare industry is applying machine learning and deep learning algorithms in health care management systems to ensure that data is always updated, classified, clustered, and is ready to be used at all times (Xiao,  Choi,  & Sun, 2018). This saves them resources like time and costs of dealing with unclassified data. It uses some methods like handwriting and OCR recognition algorithms.

Case Study 3: Drug Discovery and Manufacturing

To reduce the resources used for developing drugs, the healthcare industry uses machine learning and deep learning to predict the drug properties and patterns relating to how diseases react to the drugs (Dalal, 2020). Form data classification and clustering drug and disease patterns are derived.

PART 2: Machine Learning and Deep Learning Models Training By Cloud Providers

Cloud Provider: Google

Google Cloud offers a platform for training and use of machine learning and deep learning models through two mechanisms. Users can develop their machine learning and deep learning algorithms or train through the use of already developed and trained models. Google Cloud offers services like image and voice recognition, translation, and messaging (Bisong, 2019). The Google platform takes the user data and trains it through its algorithms. Google’s cloud platform trains various models, such as cloud speech search and cloud voice search, which are programmed as APIs (Bisong, 2019).

For deep learning, Google has enabled a cloud platform like the tensor processing units which mainly train models relating to neural networks. The google cloud platform offers various benefits like reducing cost and time and ensuring a wide range of services are offered in a centralized environment.

References

Bisong, E. (2019). Building machine learning and deep learning models on Google Cloud platform (pp. 59-64). Berkeley, CA, USA: Apress.

Dalal, K. R. (2020, July). Analyzing the implementation of machine learning in healthcare. In 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 133-137). IEEE.

Dargan, S., Kumar, M., Ayyagari, M. R., & Kumar, G. (2020). A survey of deep learning and its applications: a new paradigm to machine learning. Archives of Computational Methods in Engineering, 27(4), 1071-1092.

Roy, S., Kiral-Kornek, I., & Harrer, S. (2018, July). Deep learning enabled automatic abnormal EEG identification. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 2756-2759). IEEE.

Xiao, C., Choi, E., & Sun, J. (2018). Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review. Journal of the American Medical Informatics Association, 25(10), 1419-1428.

ORDER A PLAGIARISM-FREE PAPER HERE

We’ll write everything from scratch

Machine Learning and Deep Learning

Select one industry (For example, retail, hospitality, banking, etc) and do research on three case studies for the classification, clustering, and prediction problems that are solved by Machine Learning/Deep Learning (ML/DL)

Select one Cloud provider (Amazon, Microsoft, or Google) and do research on the services offered by the selected cloud provider for the training and using the Machine Learning / Deep Learning (ML/DL)

Summarize your learnings in APA format.