<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Ohazuruikeositadinma on Medium]]></title>
        <description><![CDATA[Stories by Ohazuruikeositadinma on Medium]]></description>
        <link>https://medium.com/@ohazuruikeositadinma?source=rss-01eddcd08b48------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*Aw5YereutIzV-mFc</url>
            <title>Stories by Ohazuruikeositadinma on Medium</title>
            <link>https://medium.com/@ohazuruikeositadinma?source=rss-01eddcd08b48------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 22 Nov 2026 23:43:07 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@ohazuruikeositadinma/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Summary of Chapter two of “Introduction to Machine Learning with Python” by Andreas C. Muller]]></title>
            <link>https://medium.com/@ohazuruikeositadinma/summary-of-chapter-two-of-introduction-to-machine-learning-with-python-by-andreas-c-muller-7d7cb6274794?source=rss-01eddcd08b48------2</link>
            <guid isPermaLink="false">https://medium.com/p/7d7cb6274794</guid>
            <dc:creator><![CDATA[Ohazuruikeositadinma]]></dc:creator>
            <pubDate>Sun, 19 Oct 2025 23:07:25 GMT</pubDate>
            <atom:updated>2025-10-19T23:07:25.149Z</atom:updated>
            <content:encoded><![CDATA[<p>This chapter focuses on explaining supervised learning and describing in detail the most popular algorithms associated with supervised machine learning.<br>Supervised learning is one of the most commonly used and successful types of machine learning. It is used whenever we want to predict the outcome from a given input If we have the example of input/output pairs (training set), the goal here is to make accurate prediction for new, never-before-seen data.</p><p>Supervised learning is of two types, which are<strong> Classification</strong> and <strong>regression</strong>.<br>The goal in <strong>Classification</strong> is to predict a class label which is a choice from a predefined list of possibilities. It is sometimes separated into binary classification and multi-class classification<br>Binary classification is used to distinguish between exactly two classes; that is, answering a “yes or no” question. For instance, “Is this email spam?” while the multi-class classification is used to classify more than two classes.</p><p><strong>Regression</strong> aims at predicting a continuous number, or a floating-point number in programming terms (or real numbers in mathematical terms)<br>Predicting a person’s annual income from their education, their age, and where they live is an example of a regression task; another example is predicting the yield of a corn farm by giving attributes to weather conditions, previous yield, and number of employees working on the farm. The yield could be an arbitrary number.</p><p>Distinguishing between classification and Regression tasks is to ask if there’s continuity in the output. For instance, predicting the annual income of a person is a continuity, which is regression, while the task of recognising the language of a website is a classification task, as there’s no continuity in the task, just as there’s no language between English and French.</p><p>The only measure if an algorithm will perform well on new data is the evaluation on the test set.<br>In supervised learning, the goal is to build a model on the training data and then be able to make accurate predictions on new, unseen data that has the same characteristics as the training set that we used. If a model is able to make accurate predictions on unseen data, we say it is able to generalise from the training set to the test set, i.e., a generalised model is one that finds the right balance, performing well on both the training and new data by capturing the time patterns without being overly sensitive to noise.<br>Overfitting in Machine Learning is when a model performs poorly on new data after learning the training data too well, including its noise.<br>Under-fitting is when a model is too simple and cannot capture the underlying pattern in the data, leading to poor performance on both training and new data.</p><p>In supervised Machine Learning (chapter two of the book), the most popular machine learning algorithms were discussed and explained how they learn from data and how they make predictions, how the concept of model complexity plays out for each of the models, and provided an overview of how each algorithm builds a model, examined the strengths and weaknesses of each algorithm, and what kind of data they can best be applied to.</p><p>The Supervised Machine Learning Algorithm discussed include:<br>K-Nearest Neighbor (K-NN)<br>It is the simplest Machine Learning Algorithm that predicts based on proximity to neighbours. Building the model consists only of storing the training data-set.<br>Linear Models<br>Here Linear models was discussed based on Linear models for regression and Linear models for Classification.<br>Linear models for regression are characterised as regression models for which the prediction is a line for a single feature, a plane when using two features, or a hyperplane in higher dimensions (that is, when using more features).<br>In Linear Models for Classification, data are categorised by drawing a straight line, flat plane, or hyperplane to separate different classes. The “linear” part refers to this boundary, which is a simple linear function of the input features. The model learns a set of weights for each feature, and a new data point is classified based on which side of the boundary it falls on.<br>Naive Bayes Classifiers<br>They often provide generalisation performance that is slightly worse than that of linear classifiers like LogisticRegression and LinearSVC. The reason that naive Bayes models are so efficient is that they learn parameters by looking at each feature individually and collect simple per-class statistics from each feature. There are three kinds of naive Bayes classifiers implemented in scikit-learn: GaussianNB, BernoulliNB, and MultinomialNB.<br>GaussianNB can be applied to any continuous data, while BernoulliNB assumes binary data and MultinomialNB assumes count data (that is, that each feature represents an integer count of something, like how often a word appears in a sentence). BernoulliNB and MultinomialNB are mostly used in text data classification. <br>Decision Trees <br>Decision trees are widely used models for classification and regression tasks. Essentially, they learn a hierarchy of if/else questions, leading to a decision. To build a tree, the algorithm searches over all possible tests and finds the one that is most informative about the target variable<br>Ensembles of Decision Trees <br>Ensembles are methods that combine multiple machine learning models to create more powerful models. Random forests and gradient boosted decision trees are the two type of Ensemles of Decision Trees that have proven to be effective on a wide range of data-sets for both Regression and Classification. A Random forest is essentially a collection of decision trees, where each tree is slightly different from the others, while Gradient Boosted Decision Tree(Gradient Boosting machine) gradient boosting works by building trees in a serial manner, where each tree tries to correct the mistakes of the previous one. <br>Kernelized support vector machines<br>They are an extension that allows for more complex models that are not defined simply by hyperplanes in the input space.<br>Neural Network (Deep Learning)<br>It is a model that learns to map a set of input data to a specific, desired output based on a large collection of pre-labelled examples. The network is composed of interconnected layers of “neurones” and trains itself by continually adjusting its internal parameters to minimise the error between its predictions and the correct answers.</p><p>In summary, this chapter talks about how supervised learning provides the foundation for modern artificial intelligence. It uses provided examples to learn, recognise patterns, and make accurate predictions. The power of supervised learning rests in its ability to transform data into meaningful, actionable insights, as long as complexity is managed carefully and generalisation is prioritised over perfection.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7d7cb6274794" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>