Fluent Essays

I have attached the document with 2 discussions and I need to reply to each one of them in 150 words each. APA format and references hussain_ds_replies.docx Unformatted Attachment Preview 7 hours ago Manoj Aluri Classification vs Regression, Supervised vs Unsupervised Machine Learning C OLLA PSE Supervised Versus Unsupervised Learning Supervised learning consists of problems that explain it consist of a model that includes variables over input and output with a proper algorithm, which will map the input variable to the output variable. It explains that the mapping function will consist of corresponding data that consists of predicted data. Supervised machine learning determines the process be of complete learning, where it processes the output data. The learning algorithm will include performance that achieves the performance of the acceptable level (Oussous et la., 2018). Supervised learning consists of the learning of data, where it shows the algorithm data that is a supervised learning algorithm that produces over training data. The supervised learning algorithm will determine the two ways of algorithms they are classification and regression. The classification explains the problem that when an output variable will be in a categorized format. Regression determines the problem where it shows the output variable will read the real value. It explains everything over supervised learning algorithms. Unsupervised learning will explain the process of training provided over information that is classified over an algorithm where it determines the patterns of data. Unsupervised learning data will explain the process over developing the input data that is considered over the output variable. Model distribution determines the process over identifying the variables which are considered of data (Gandomi & Haider, 2015). It learns where data is an unsupervised performance model that determines the algorithms where it structures the information. It shows that devices will be connected over the structure data. Unsupervised learning will be categorized into two groups of algorithms, such as clustering & association. The clustering process will discover inherent problem groups towards the data. Association will lead the problems that discover the rules of data contains portions of the data. Input data will consist of labeled data in supervised learning, and data will include very complex over the supervised learning and unsupervised learning. References: Gandomi, A., & Haider, M. (2015). Beyond the hype: Big data concepts, methods, and analytics. International journal of information management, 35(2), 137-144. Oussous, A., Benjelloun, F., Ait Lahcen, A., & Belfkih, S. (2018). Big data technologies: A survey. Journal of King Saud University - Computer and Information Sciences, 30(4), 431-448. doi:10.1016/j.jksuci.2017.06.001 1 day ago Hanumantha Rao Kurapati Week 2 Discussion C OLLA PSE Statistical learning is nothing but applying the statistical knowledge to understand data. The process has been started during 1940’s only and in current years it is one of trending technologies. There are variety of tools exist in the market and can be divided into two types one is predictable and the other one is unpredictable. In the predictable kind of tools there will be many inputs to the model developed which are called as predictable and output which depends on these inputs are called as predictors. In another type of tools there will be no output, but input variables still exist. Instead of outputs from these models the relationship between two datasets or variables can be framed (James, Witten, Hastie, & Tibshirani, 2013). For example, if data is plotted on salary of a person comparing with different parameters like age, education and year a relationship can be framed. The graph represents that with the increase of age the salary of a person increases but the data is not true with all the cases. If the output is compared along with another variables like year and education of a human being the salary range can be predicted easily. This method can be developed by using the linear regression in which the quantitative analysis can be made. If the age of the person, year in which analysis is being made and education of the person is known then an average salary can be predicted with linear regression model (Rathi, 2018). Another kind of analysis method used to find qualitative analysis in which the answer like yes/no, up/down and present/absent are identified. From the previous data of the stock market movement the predication can be made by which one can do trading if the analysis says UP or Down. Another kind of analysis is relationship with another type of data for example if analysis is being made on gene responses and compared with another kind cancer cells in which a relationship can be made. During the 19th century only some scientist like Legendre and Gauss developed statistical method called as least squares. In the current science of statistics called as linear regression is like least squares. References James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An Introduction to Statistical Learning. New York: Springer. Rathi, A. (2018, Aug 19). Statistical Learning for Data Science. Retrieved from https://medium.com: https://medium.com/@rathi.ankit/statistical-learning-for-datascience-b61b263c1196 ... Purchase answer to see full attachment