title
Support Vector Machine - How Support Vector Machine Works | SVM In Machine Learning | Simplilearn

description
🔥Professional Certificate Course In AI And Machine Learning by IIT Kanpur (India Only): https://www.simplilearn.com/iitk-professional-certificate-course-ai-machine-learning?utm_campaign=23AugustTubebuddyExpPCPAIandML&utm_medium=DescriptionFF&utm_source=youtube 🔥AI Engineer Masters Program (Discount Code - YTBE15): https://www.simplilearn.com/masters-in-artificial-intelligence?utm_campaign=SCE-AIMasters&utm_medium=DescriptionFF&utm_source=youtube 🔥AI & Machine Learning Bootcamp(US Only): https://www.simplilearn.com/ai-machine-learning-bootcamp?utm_campaign=MachineLearning-TtKF996oEl8&utm_medium=Descriptionff&utm_source=youtube 🔥 Purdue Post Graduate Program In AI And Machine Learning: https://www.simplilearn.com/pgp-ai-machine-learning-certification-training-course?utm_campaign=MachineLearning-TtKF996oEl8&utm_medium=Descriptionff&utm_source=youtube This Support Vector Machine (SVM) tutorial video will help you understand the basics of the Support Vector Machine algorithm, where and when to use the SVM algorithm, and how Support Vector Machine works. You will learn about hyperplanes and support vectors, how distance margin helps in optimizing the hyperplane, kernel functions in SVM for data transformation and advantages of the SVM algorithm. Below topics are explained in this Support Vector Machine Tutorial: 00:00 - 01:03 Applications and Agenda 01:04 - 01:58 What is Machine Learning? 01:58 - 03:39 Why support vector machine? 03:39 - 07:59 What is a support vector machine? 07:59 - 09:15 Advantages of support vector machine 09:15 - 26:42 Use Case in Python ✅Subscribe to our Channel to learn more about the top Technologies: https://bit.ly/2VT4WtH ⏩ Check out the Machine Learning tutorial videos: https://bit.ly/3fFR4f4 Machine Learning Articles: https://www.simplilearn.com/what-is-artificial-intelligence-and-why-ai-certification-article?utm_campaign=Support-Vector-machine-Tutorial-TtKF996oEl8&utm_medium=Tutorials&utm_source=youtube 👉Learn more at: https://bit.ly/3fouyY0 #SupportVectorMachine #SVMMachineLearning #SupportVectorMachineInMachineLearning #SVM #SVMAlgorithmInMachineLearning #SupportVectorMachines #SVMAlgorithm #MachineLearningTutorial #MachineLearning #Simplilearn What is a Support Vector Machine? Support Vector Machines are powerful supervised learning algorithms for both classification and regression. It is a discriminative classifier that is formally defined by a separating hyperplane. So given labelled training data, the algorithm outputs an optimal hyperplane that categorizes new examples. ➡️ Advanced Certificate Program In Data Science This Advanced Certificate Program in Data Science is designed for working professionals & covers job-critical topics like R, Python, Machine Learning techniques, NLP notions,& Data Visualization with Tableau, using an active learning model that includes live sessions from global professionals, practical labs, IBM Hackathons, corporate ready projects. ✅ Key features: - Advanced Data Science certificate and Purdue alumni association membership - 3 Capstone and 25+ Projects with industry data sets from Amazon, Uber, Walmart, Comcast, and many more - Masterclasses delivered by Purdue faculty and IBM experts - Exclusive hackathons and Ask Me Anything sessions by IBM - Simplilearn's JobAssist helps you get noticed by top hiring companies - Resume preparation and LinkedIn profile building - 1:1 mock interview - Career accelerator webinars - 8X higher engagement in live online classes by seasoned academics and industry professionals ✅ Skills covered:- - Exploratory Data Analysis - Descriptive Statistics - Inferential Statistics - Model building and fine tuning - Supervised and unsupervised learning - Natural Language Processing - Ensemble Learning 👉Learn More at: https://www.simplilearn.com/pgp-data-science-certification-bootcamp-program?utm_campaign=MachineLearning-TtKF996oEl8&utm_medium=Description&utm_source=youtube 🔥 Enroll for FREE Machine Learning Course & Get your Completion Certificate: https://www.simplilearn.com/learn-machine-learning-basics-skillup?utm_campaign=MachineLearning&utm_medium=Description&utm_source=youtube 🔥🔥 Interested in Attending Live Classes? Call Us: IN - 18002127688 / US - +18445327688

detail
{'title': 'Support Vector Machine - How Support Vector Machine Works | SVM In Machine Learning | Simplilearn', 'heatmap': [{'end': 325.049, 'start': 253.063, 'weight': 0.717}, {'end': 387.446, 'start': 335.815, 'weight': 0.766}, {'end': 449.302, 'start': 429.531, 'weight': 0.756}, {'end': 833.565, 'start': 815.51, 'weight': 0.715}], 'summary': 'Covers support vector machine (svm) applications including face detection, text categorization, and bioinformatics, discusses svm basics, gender classification using height and weight data, implementing svm in python, analyzing svm results, and using svm for crocodile and alligator classification.', 'chapters': [{'end': 41.581, 'segs': [{'end': 41.581, 'src': 'embed', 'start': 4.289, 'weight': 0, 'content': [{'end': 9.31, 'text': 'Welcome to Support Vector Machine, a lot of times referred to as the SVM algorithm.', 'start': 4.289, 'duration': 5.021}, {'end': 10.811, 'text': 'My name is Richard Kirshner.', 'start': 9.59, 'duration': 1.221}, {'end': 12.091, 'text': "I'm with Simply Learn.", 'start': 10.931, 'duration': 1.16}, {'end': 18.232, 'text': "Before we dive into the SVM, let's take a look at applications of the Support Vector Machine,", 'start': 12.251, 'duration': 5.981}, {'end': 20.753, 'text': 'at least some general ones that are commonly used with it.', 'start': 18.232, 'duration': 2.521}, {'end': 27.755, 'text': 'Face detection, text and hypertext categorization, classification of images, and bioinformatics.', 'start': 21.073, 'duration': 6.682}, {'end': 31.756, 'text': 'These are only but a few of those that are used with this SVM.', 'start': 28.155, 'duration': 3.601}, {'end': 33.116, 'text': 'As we go through this lesson,', 'start': 31.876, 'duration': 1.24}, {'end': 37.979, 'text': 'See if you can figure out what other ones you could apply it to and also what you would want to use some other tools for.', 'start': 33.416, 'duration': 4.563}, {'end': 41.581, 'text': "What's in it for you? Today we're going to cover about six different sections.", 'start': 38.259, 'duration': 3.322}], 'summary': 'Svm algorithm used for face detection, text categorization, image classification, bioinformatics. covers six sections.', 'duration': 37.292, 'max_score': 4.289, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl84289.jpg'}], 'start': 4.289, 'title': 'Support vector machine applications', 'summary': 'Introduces the support vector machine algorithm and highlights its applications in face detection, text and hypertext categorization, classification of images, and bioinformatics, while encouraging exploration of additional applications.', 'chapters': [{'end': 41.581, 'start': 4.289, 'title': 'Support vector machine applications', 'summary': 'Introduces the support vector machine algorithm and highlights its applications in face detection, text and hypertext categorization, classification of images, and bioinformatics, while encouraging exploration of additional applications.', 'duration': 37.292, 'highlights': ['The Support Vector Machine algorithm is commonly used in face detection, text and hypertext categorization, image classification, and bioinformatics.', 'The chapter encourages exploration of additional applications for the SVM algorithm.', 'The chapter is structured to cover about six different sections.']}], 'duration': 37.292, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl84289.jpg', 'highlights': ['The Support Vector Machine algorithm is commonly used in face detection, text and hypertext categorization, image classification, and bioinformatics.', 'The chapter encourages exploration of additional applications for the SVM algorithm.', 'The chapter is structured to cover about six different sections.']}, {'end': 210.744, 'segs': [{'end': 210.744, 'src': 'embed', 'start': 167.283, 'weight': 0, 'content': [{'end': 170.925, 'text': "In this case we're using the support vector machine model.", 'start': 167.283, 'duration': 3.642}, {'end': 177.969, 'text': 'SVM is a supervised learning method that looks at data and sorts it into one of two categories,', 'start': 171.205, 'duration': 6.764}, {'end': 181.211, 'text': "and in this case we're sorting the strawberry into the strawberry side.", 'start': 177.969, 'duration': 3.242}, {'end': 185.516, 'text': 'At this point you should be asking the question how does the prediction work?', 'start': 181.451, 'duration': 4.065}, {'end': 190.542, 'text': "Before we dig into an example with numbers, let's apply this to our fruit scenario.", 'start': 185.756, 'duration': 4.786}, {'end': 192.284, 'text': 'We have our support vector machine.', 'start': 190.702, 'duration': 1.582}, {'end': 200.053, 'text': "We've taken it, and we've taken a labeled sample of data, strawberries and apples, and we've drawn a line down the middle between the two groups.", 'start': 192.404, 'duration': 7.649}, {'end': 207.34, 'text': 'This split now allows us to take new data in this case an apple and a strawberry and place them in the appropriate group,', 'start': 200.493, 'duration': 6.847}, {'end': 209.082, 'text': 'based on which side of the line they fall in.', 'start': 207.34, 'duration': 1.742}, {'end': 210.744, 'text': 'And that way we can predict the unknown.', 'start': 209.202, 'duration': 1.542}], 'summary': 'Using svm to classify fruits like strawberries and apples into separate categories based on a drawn line.', 'duration': 43.461, 'max_score': 167.283, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8167283.jpg'}], 'start': 41.761, 'title': 'Support vector machine', 'summary': 'Discusses the concept of support vector machines and their role in supervised learning, classification, and future predictions, using the analogy of fruit identification and data sorting.', 'chapters': [{'end': 210.744, 'start': 41.761, 'title': 'Understanding support vector machine', 'summary': 'Explains the concept of a support vector machine in supervised learning, its role in classification, and how it makes future predictions, using the analogy of fruit identification, and the process of data sorting and prediction.', 'duration': 168.983, 'highlights': ['The support vector machine is a supervised learning method that sorts data into two categories, primarily used for classification, and makes future predictions based on past input data.', 'The SVM model is trained using labeled data, enabling it to identify new data, similar to predicting an unknown fruit by already knowing the characteristics of strawberries and apples.', 'The process of prediction in SVM involves drawing a line between two groups of data and placing new data on the appropriate side of the line to make predictions.', 'The chapter also delves into the broader context of machine learning, categorizing SVM as a part of supervised learning, and emphasizes its role in classification tasks.']}], 'duration': 168.983, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl841761.jpg', 'highlights': ['The support vector machine is a supervised learning method that sorts data into two categories, primarily used for classification, and makes future predictions based on past input data.', 'The SVM model is trained using labeled data, enabling it to identify new data, similar to predicting an unknown fruit by already knowing the characteristics of strawberries and apples.', 'The process of prediction in SVM involves drawing a line between two groups of data and placing new data on the appropriate side of the line to make predictions.', 'The chapter also delves into the broader context of machine learning, categorizing SVM as a part of supervised learning, and emphasizes its role in classification tasks.']}, {'end': 588.071, 'segs': [{'end': 241.881, 'src': 'embed', 'start': 210.924, 'weight': 4, 'content': [{'end': 213.747, 'text': 'As colorful and tasty as the fruit example is.', 'start': 210.924, 'duration': 2.823}, {'end': 219.353, 'text': "let's take a look at another example with some numbers involved, and we can take a closer look at how the math works.", 'start': 213.747, 'duration': 5.606}, {'end': 222.474, 'text': "In this example, we're going to be classifying men and women.", 'start': 219.713, 'duration': 2.761}, {'end': 226.836, 'text': "And we're going to start with a set of people with a different height and a different weight.", 'start': 222.574, 'duration': 4.262}, {'end': 233.019, 'text': "And to make this work, we'll have to have a sample data set of female, where you have their height and weight, 174, 65, 174, 88, and so on.", 'start': 227.296, 'duration': 5.723}, {'end': 237.94, 'text': "And we'll need a sample data set of the male.", 'start': 236.24, 'duration': 1.7}, {'end': 241.881, 'text': 'They have a height 179, 90, 180 to 80 and so on.', 'start': 238.04, 'duration': 3.841}], 'summary': 'Analyzing gender classification based on height and weight data.', 'duration': 30.957, 'max_score': 210.924, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8210924.jpg'}, {'end': 325.049, 'src': 'heatmap', 'start': 253.063, 'weight': 0.717, 'content': [{'end': 258.004, 'text': "Now if we're going to create a classifier, let's add a new data point and figure out if it's male or female.", 'start': 253.063, 'duration': 4.941}, {'end': 261.964, 'text': 'So before we can do that, we need to split our data first.', 'start': 258.144, 'duration': 3.82}, {'end': 265.226, 'text': 'We can split our data by choosing any of these lines.', 'start': 262.325, 'duration': 2.901}, {'end': 270.289, 'text': 'In this case, we draw in two lines through the data in the middle that separates the men from the women.', 'start': 265.706, 'duration': 4.583}, {'end': 275.953, 'text': 'But to predict the gender of a new data point, we should split the data in the best possible way.', 'start': 270.429, 'duration': 5.524}, {'end': 282.558, 'text': 'And we say the best possible way because this line has a maximum space that separates the two classes.', 'start': 276.193, 'duration': 6.365}, {'end': 289.466, 'text': "Here you can see there's a clear split between the two different classes, and in this one there's not so much a clear split.", 'start': 283.018, 'duration': 6.448}, {'end': 292.45, 'text': "This doesn't have the maximum space that separates the two.", 'start': 289.686, 'duration': 2.764}, {'end': 295.093, 'text': 'That is why this line best splits the data.', 'start': 292.61, 'duration': 2.483}, {'end': 297.536, 'text': "We don't want to just do this by eyeballing it.", 'start': 295.253, 'duration': 2.283}, {'end': 301.341, 'text': 'And before we go further, we need to add some technical terms to this.', 'start': 297.816, 'duration': 3.525}, {'end': 306.943, 'text': 'We can also say that the distance between the points in the line should be as far as possible.', 'start': 301.761, 'duration': 5.182}, {'end': 313.845, 'text': 'In technical terms, we can say the distance between the support vector and the hyperplane should be as far as possible.', 'start': 307.103, 'duration': 6.742}, {'end': 317.867, 'text': 'And this is where the support vectors are the extreme points in the data set.', 'start': 314.025, 'duration': 3.842}, {'end': 319.887, 'text': 'And if you look at this data set,', 'start': 318.127, 'duration': 1.76}, {'end': 325.049, 'text': 'they have circled two points which seem to be right on the outskirts of the women and one on the outskirts of the men.', 'start': 319.887, 'duration': 5.162}], 'summary': 'Creating a classifier to predict gender by splitting data using support vectors.', 'duration': 71.986, 'max_score': 253.063, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8253063.jpg'}, {'end': 329.791, 'src': 'embed', 'start': 301.761, 'weight': 2, 'content': [{'end': 306.943, 'text': 'We can also say that the distance between the points in the line should be as far as possible.', 'start': 301.761, 'duration': 5.182}, {'end': 313.845, 'text': 'In technical terms, we can say the distance between the support vector and the hyperplane should be as far as possible.', 'start': 307.103, 'duration': 6.742}, {'end': 317.867, 'text': 'And this is where the support vectors are the extreme points in the data set.', 'start': 314.025, 'duration': 3.842}, {'end': 319.887, 'text': 'And if you look at this data set,', 'start': 318.127, 'duration': 1.76}, {'end': 325.049, 'text': 'they have circled two points which seem to be right on the outskirts of the women and one on the outskirts of the men.', 'start': 319.887, 'duration': 5.162}, {'end': 329.791, 'text': 'And hyperplane has a maximum distance to the support vectors of any class.', 'start': 325.289, 'duration': 4.502}], 'summary': 'In svm, maximize distance between hyperplane and support vectors', 'duration': 28.03, 'max_score': 301.761, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8301761.jpg'}, {'end': 387.446, 'src': 'heatmap', 'start': 335.815, 'weight': 0.766, 'content': [{'end': 338.617, 'text': "it's really not just a line, but a plane of intersections.", 'start': 335.815, 'duration': 2.802}, {'end': 342.84, 'text': 'And you can see here where the support vectors have been drawn in dashed lines.', 'start': 338.918, 'duration': 3.922}, {'end': 345.162, 'text': 'The math behind this is very simple.', 'start': 343.221, 'duration': 1.941}, {'end': 351.387, 'text': "We take D plus the shortest distance to the closest positive point, which would be on the men's side,", 'start': 345.322, 'duration': 6.065}, {'end': 356.05, 'text': "and D minus is the shortest distance to the closest negative point, which is on the women's side.", 'start': 351.387, 'duration': 4.663}, {'end': 359.653, 'text': 'The sum of D plus and D minus is called the distance margin.', 'start': 356.23, 'duration': 3.423}, {'end': 364.135, 'text': 'or the distance between the two support vectors that are shown in the dashed lines.', 'start': 359.893, 'duration': 4.242}, {'end': 369.918, 'text': 'And then by finding the largest distance margin, we can get the optimal hyperplane.', 'start': 364.515, 'duration': 5.403}, {'end': 374.86, 'text': "Once we've created an optimal hyperplane, we can easily see which side the new data fits in.", 'start': 370.118, 'duration': 4.742}, {'end': 378.842, 'text': 'And based on the hyperplane, we can say the new data point belongs to the male gender.', 'start': 375.04, 'duration': 3.802}, {'end': 381.843, 'text': "Hopefully that's clear how that works on a visual level.", 'start': 379.082, 'duration': 2.761}, {'end': 387.446, 'text': 'As a data scientist, you should also be asking what happens if the hyperplane is not optimal.', 'start': 382.044, 'duration': 5.402}], 'summary': 'Support vector machine finds optimal hyperplane to classify data points by gender.', 'duration': 51.631, 'max_score': 335.815, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8335815.jpg'}, {'end': 369.918, 'src': 'embed', 'start': 338.918, 'weight': 3, 'content': [{'end': 342.84, 'text': 'And you can see here where the support vectors have been drawn in dashed lines.', 'start': 338.918, 'duration': 3.922}, {'end': 345.162, 'text': 'The math behind this is very simple.', 'start': 343.221, 'duration': 1.941}, {'end': 351.387, 'text': "We take D plus the shortest distance to the closest positive point, which would be on the men's side,", 'start': 345.322, 'duration': 6.065}, {'end': 356.05, 'text': "and D minus is the shortest distance to the closest negative point, which is on the women's side.", 'start': 351.387, 'duration': 4.663}, {'end': 359.653, 'text': 'The sum of D plus and D minus is called the distance margin.', 'start': 356.23, 'duration': 3.423}, {'end': 364.135, 'text': 'or the distance between the two support vectors that are shown in the dashed lines.', 'start': 359.893, 'duration': 4.242}, {'end': 369.918, 'text': 'And then by finding the largest distance margin, we can get the optimal hyperplane.', 'start': 364.515, 'duration': 5.403}], 'summary': 'Using support vectors to find optimal hyperplane in svm.', 'duration': 31, 'max_score': 338.918, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8338918.jpg'}, {'end': 452.503, 'src': 'heatmap', 'start': 422.546, 'weight': 1, 'content': [{'end': 429.371, 'text': "So when you see data like this, it's necessary to move away from a 1D view of the data to a two-dimensional view of the data.", 'start': 422.546, 'duration': 6.825}, {'end': 433.034, 'text': "And for the transformation, we use what's called a kernel function.", 'start': 429.531, 'duration': 3.503}, {'end': 438.679, 'text': 'The kernel function will take the 1D input and transfer it to a two-dimensional output.', 'start': 433.214, 'duration': 5.465}, {'end': 446.801, 'text': 'As you can see in this picture here, the 1D when transferred to a two-dimensional makes it very easy to draw a line between the two data sets.', 'start': 439.139, 'duration': 7.662}, {'end': 449.302, 'text': 'What if we make it even more complicated?', 'start': 447.161, 'duration': 2.141}, {'end': 452.503, 'text': 'How do we perform an SVM for this type of data set?', 'start': 449.562, 'duration': 2.941}], 'summary': 'Using kernel function to transform 1d data to 2d for svm analysis.', 'duration': 29.957, 'max_score': 422.546, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8422546.jpg'}, {'end': 521.634, 'src': 'embed', 'start': 495.935, 'weight': 0, 'content': [{'end': 501.478, 'text': 'When you get to a thousand dimensions, a lot of problems start occurring with most algorithms that have to be adjusted for.', 'start': 495.935, 'duration': 5.543}, {'end': 504.759, 'text': 'The SVM automatically does that in high dimensional space.', 'start': 501.678, 'duration': 3.081}, {'end': 511.122, 'text': 'One of the high dimensional space, one high dimensional space that we work on is sparse document vectors.', 'start': 505.339, 'duration': 5.783}, {'end': 515.847, 'text': 'This is where we tokenize the words in documents so we can run our machine learning algorithms over them.', 'start': 511.482, 'duration': 4.365}, {'end': 519.672, 'text': "I've seen ones get as high as 2.4 million different tokens.", 'start': 515.967, 'duration': 3.705}, {'end': 521.634, 'text': "That's a lot of vectors to look at.", 'start': 519.852, 'duration': 1.782}], 'summary': 'The svm adjusts for problems in high-dimensional space, handling up to 2.4 million different tokens.', 'duration': 25.699, 'max_score': 495.935, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8495935.jpg'}], 'start': 210.924, 'title': 'Gender classification and svm basics', 'summary': 'Covers gender classification using height and weight data to create a classifier and explains support vector machine basics, including support vectors, hyperplanes, distance margin, and advantages in high dimensional space. it also includes a python use case study for differentiating crocodiles and alligators at the zoo.', 'chapters': [{'end': 301.341, 'start': 210.924, 'title': 'Gender classification using height and weight data', 'summary': 'Demonstrates gender classification using height and weight data, visualizing and splitting the data to create a classifier with the goal of predicting the gender of new data points, aiming to maximize the separation between the two classes.', 'duration': 90.417, 'highlights': ['The chapter demonstrates the process of classifying men and women based on height and weight data, visually representing the data on a graph and emphasizing the importance of maximizing the separation between the two classes.', 'The speaker explains the need to split the data in the best possible way to predict the gender of new data points and highlights the significance of choosing a line that maximizes the space separating the two classes.', 'The transcript introduces the concept of splitting the data to create a classifier and emphasizes the importance of technical terms in the process.']}, {'end': 588.071, 'start': 301.761, 'title': 'Support vector machine basics', 'summary': 'Explains the concept of support vectors, hyperplanes, distance margin, optimal hyperplane, transformation using kernel functions, advantages of support vector machine in high dimensional space, and a python use case study for differentiating crocodiles and alligators at the zoo.', 'duration': 286.31, 'highlights': ['The support vectors are the extreme points in the data set and the hyperplane has a maximum distance to the support vectors of any class.', 'The math behind finding the largest distance margin to get the optimal hyperplane is explained as taking the sum of D plus and D minus, which is called the distance margin.', 'The concept of using a kernel function to transform 1D input to a two-dimensional output for dealing with more complex data sets is discussed.', 'The advantages of support vector machine in high dimensional space, especially in dealing with sparse document vectors and avoiding overfitting and bias problems, are emphasized.', 'A Python use case study for differentiating crocodiles and alligators at the zoo is presented, demonstrating the practical application of support vector machine.']}], 'duration': 377.147, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8210924.jpg', 'highlights': ['The advantages of support vector machine in high dimensional space, especially in dealing with sparse document vectors and avoiding overfitting and bias problems, are emphasized.', 'The concept of using a kernel function to transform 1D input to a two-dimensional output for dealing with more complex data sets is discussed.', 'The support vectors are the extreme points in the data set and the hyperplane has a maximum distance to the support vectors of any class.', 'The math behind finding the largest distance margin to get the optimal hyperplane is explained as taking the sum of D plus and D minus, which is called the distance margin.', 'The chapter demonstrates the process of classifying men and women based on height and weight data, visually representing the data on a graph and emphasizing the importance of maximizing the separation between the two classes.']}, {'end': 1062.26, 'segs': [{'end': 614.651, 'src': 'embed', 'start': 588.331, 'weight': 5, 'content': [{'end': 593.935, 'text': 'And of course, in the modern day and age, the father is sitting here thinking how can I turn this into a lesson for my son?', 'start': 588.331, 'duration': 5.604}, {'end': 597.198, 'text': 'And he goes let a support vector machine segregate the two groups.', 'start': 594.075, 'duration': 3.123}, {'end': 599.94, 'text': "I don't know if my dad ever told me that, but that would be funny.", 'start': 597.498, 'duration': 2.442}, {'end': 604.403, 'text': "Now, in this example, we're not going to use actual measurements and data.", 'start': 600.1, 'duration': 4.303}, {'end': 606.084, 'text': "We're just using that for imagery.", 'start': 604.583, 'duration': 1.501}, {'end': 609.707, 'text': "And that's very common in a lot of machine learning algorithms and setting them up.", 'start': 606.264, 'duration': 3.443}, {'end': 614.651, 'text': "But let's roll up our sleeves and we'll talk about that more in just a moment as we break into our Python script.", 'start': 609.947, 'duration': 4.704}], 'summary': 'Modern approach to teaching, using support vector machine and python for machine learning.', 'duration': 26.32, 'max_score': 588.331, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8588331.jpg'}, {'end': 652.157, 'src': 'embed', 'start': 624.498, 'weight': 0, 'content': [{'end': 629.862, 'text': "First we're going to cover in the code the setup, how to actually create our SVM,", 'start': 624.498, 'duration': 5.364}, {'end': 632.785, 'text': "and you're going to find that there's only two lines of code that actually create it,", 'start': 629.862, 'duration': 2.923}, {'end': 636.928, 'text': "and the rest of it is done so quick and fast that it's all here in the first page.", 'start': 632.785, 'duration': 4.143}, {'end': 641.31, 'text': "And we'll show you what that looks like as far as our data because we're going to create some data.", 'start': 637.228, 'duration': 4.082}, {'end': 643.111, 'text': 'I talked about creating data just a minute ago.', 'start': 641.431, 'duration': 1.68}, {'end': 646.834, 'text': "And so we'll get into the creating data here and you'll see this nice correction of our two blobs.", 'start': 643.212, 'duration': 3.622}, {'end': 648.234, 'text': "And we'll go through that in just a second.", 'start': 646.874, 'duration': 1.36}, {'end': 652.157, 'text': "And then the second part is we're going to take this and we're going to bump it up a notch.", 'start': 648.475, 'duration': 3.682}], 'summary': 'The svm setup code only involves two lines, with the rest being quick. data creation and visualization are also covered.', 'duration': 27.659, 'max_score': 624.498, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8624498.jpg'}, {'end': 686.421, 'src': 'embed', 'start': 657.28, 'weight': 1, 'content': [{'end': 659.781, 'text': 'I like to use the Anaconda Jupyter Notebook.', 'start': 657.28, 'duration': 2.501}, {'end': 665.825, 'text': "because it's very easy to use, but you can use any of your favorite Python editors or setups and go in there.", 'start': 660.021, 'duration': 5.804}, {'end': 668.047, 'text': "But let's go ahead and switch over there and see what that looks like.", 'start': 665.906, 'duration': 2.141}, {'end': 674.652, 'text': 'So here we are in the Anaconda Python notebook, or Anaconda Jupyter notebook with Python.', 'start': 668.568, 'duration': 6.084}, {'end': 676.233, 'text': "We're using Python 3.", 'start': 674.672, 'duration': 1.561}, {'end': 680.837, 'text': 'I believe this is 3.5, but it should work in any of your 3x versions.', 'start': 676.233, 'duration': 4.604}, {'end': 686.421, 'text': "And you'd have to look at the sklearn and make sure if you're using a 2x version or an earlier version.", 'start': 681.217, 'duration': 5.204}], 'summary': 'Anaconda jupyter notebook makes it easy to use python 3 for data science.', 'duration': 29.141, 'max_score': 657.28, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8657280.jpg'}, {'end': 757.089, 'src': 'embed', 'start': 731.496, 'weight': 3, 'content': [{'end': 736.758, 'text': "And I'll talk about that in a minute so you can understand why we want to use a numpy array versus the standard Python array.", 'start': 731.496, 'duration': 5.262}, {'end': 740.78, 'text': "And normally it's pretty standard setup to use np for numpy.", 'start': 736.958, 'duration': 3.822}, {'end': 743.682, 'text': "The matplotlibrary is how we're going to view our data.", 'start': 741, 'duration': 2.682}, {'end': 751.325, 'text': 'So this has, you do need the np for the sklearn module, but the matplotlibrary is purely for our use for visualization.', 'start': 743.962, 'duration': 7.363}, {'end': 757.089, 'text': "And so you really don't need that for the SVM, but we're going to put it there so you have a nice visual aid and we can show you what it looks like.", 'start': 751.745, 'duration': 5.344}], 'summary': 'Using numpy for data analysis and matplotlibrary for visualization in svm implementation.', 'duration': 25.593, 'max_score': 731.496, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8731496.jpg'}, {'end': 821.176, 'src': 'embed', 'start': 790.996, 'weight': 2, 'content': [{'end': 793.138, 'text': "It's a wonderful tool if you're ready to test your.", 'start': 790.996, 'duration': 2.142}, {'end': 799.061, 'text': "set up and you're not sure about what data you're going to put in there, you can create this blob and it makes it real easy to use.", 'start': 794.079, 'duration': 4.982}, {'end': 804.642, 'text': 'And finally we have our actual SVM, the sklearn import SVM on line 3.', 'start': 799.401, 'duration': 5.241}, {'end': 806.303, 'text': 'So that covers all our imports.', 'start': 804.642, 'duration': 1.661}, {'end': 812.767, 'text': "We're going to create remember, I used the make blobs to create data And we're going to create a capital X and a lowercase.", 'start': 806.603, 'duration': 6.164}, {'end': 815.51, 'text': 'y equals make blobs in samples equals 40..', 'start': 812.767, 'duration': 2.743}, {'end': 817.592, 'text': "So we're going to make 40 lines of data.", 'start': 815.51, 'duration': 2.082}, {'end': 821.176, 'text': "It's going to have two centers with a random state equals 20.", 'start': 817.913, 'duration': 3.263}], 'summary': 'Using make_blobs to create 40 lines of data with two centers and random state=20.', 'duration': 30.18, 'max_score': 790.996, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8790996.jpg'}, {'end': 845.292, 'src': 'heatmap', 'start': 815.51, 'weight': 0.715, 'content': [{'end': 817.592, 'text': "So we're going to make 40 lines of data.", 'start': 815.51, 'duration': 2.082}, {'end': 821.176, 'text': "It's going to have two centers with a random state equals 20.", 'start': 817.913, 'duration': 3.263}, {'end': 824.8, 'text': 'So each group is going to have 20 different pieces of data in it.', 'start': 821.176, 'duration': 3.624}, {'end': 829.682, 'text': "And the way that looks is that we'll have under x an xy plane.", 'start': 825.02, 'duration': 4.662}, {'end': 833.565, 'text': "So I'll have two numbers under x, and y will be 0 or 1.", 'start': 829.883, 'duration': 3.682}, {'end': 834.925, 'text': "That's the two different centers.", 'start': 833.565, 'duration': 1.36}, {'end': 838.467, 'text': 'So we have yes or no, in this case alligator or crocodile.', 'start': 835.125, 'duration': 3.342}, {'end': 839.828, 'text': "That's what that represents.", 'start': 838.627, 'duration': 1.201}, {'end': 845.292, 'text': 'And then I told you that the actual SK Learner, the SVM, is in two lines of code.', 'start': 840.268, 'duration': 5.024}], 'summary': "Generate 40 lines of data with 2 centers, each containing 20 pieces, representing 'alligator' or 'crocodile'. svm implemented in 2 lines.", 'duration': 29.782, 'max_score': 815.51, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8815510.jpg'}], 'start': 588.331, 'title': 'Support vector machines in python', 'summary': "Introduces and demonstrates support vector machines (svm) in python, covering implementation, data visualization, and usage of anaconda jupyter notebook for svm with 'make blobs' for data creation.", 'chapters': [{'end': 657.059, 'start': 588.331, 'title': 'Introduction to support vector machines in python', 'summary': 'Introduces the concept of support vector machines (svm) and provides a demonstration of its implementation in python, covering the creation of svm, quick setup with minimal lines of code, and generation of data for visualization.', 'duration': 68.728, 'highlights': ['The chapter covers the setup of Support Vector Machines in Python, demonstrating the creation of SVM with only two lines of code and quick implementation, providing a visual representation of the generated data for better understanding.', 'The discussion includes the process of creating data for the SVM, presenting a visual illustration of two blobs, and delves into the behind-the-scenes aspects of the implementation.', 'The father-son scenario is used as an analogy to explain the concept of SVM, highlighting the modern-day relevance and potential for turning real-life situations into learning opportunities.', 'The chapter touches on the common practice of using imagery rather than actual measurements and data in machine learning algorithms, emphasizing the practical approach in the field.']}, {'end': 1062.26, 'start': 657.28, 'title': 'Anaconda jupyter notebook for svm in python', 'summary': "Discusses using anaconda jupyter notebook to implement a support vector machine (svm) in python, covering important imports, data creation using 'make blobs', svm implementation, and data visualization through scatter plot and prediction.", 'duration': 404.98, 'highlights': ['Anaconda Jupyter Notebook is used for implementing SVM in Python and is compatible with any Python 3x version.', 'Importing necessary libraries such as numpy and matplotlibrary for data manipulation and visualization in SVM.', "Explanation of using 'make blobs' from SKLearn to create sample data for SVM and its simplicity in generating test data.", "Demonstration of SVM implementation using sklearn.svm and creation of SVM classifier using 'clf.fit' method.", 'Visualization of data using a scatter plot with specific notation for numpy array and color mapping for different classes.', 'Prediction of new data using the trained SVM model and the process of assigning new data and obtaining predictions.']}], 'duration': 473.929, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl8588331.jpg', 'highlights': ['The chapter covers the setup of Support Vector Machines in Python, demonstrating the creation of SVM with only two lines of code and quick implementation, providing a visual representation of the generated data for better understanding.', 'Anaconda Jupyter Notebook is used for implementing SVM in Python and is compatible with any Python 3x version.', 'The discussion includes the process of creating data for the SVM, presenting a visual illustration of two blobs, and delves into the behind-the-scenes aspects of the implementation.', 'Importing necessary libraries such as numpy and matplotlibrary for data manipulation and visualization in SVM.', "Demonstration of SVM implementation using sklearn.svm and creation of SVM classifier using 'clf.fit' method.", 'The father-son scenario is used as an analogy to explain the concept of SVM, highlighting the modern-day relevance and potential for turning real-life situations into learning opportunities.']}, {'end': 1323.247, 'segs': [{'end': 1123.043, 'src': 'embed', 'start': 1062.38, 'weight': 0, 'content': [{'end': 1069.282, 'text': "Now that's a pretty short explanation for the setup, but really we want to dig in and see what's going on behind the scenes.", 'start': 1062.38, 'duration': 6.902}, {'end': 1070.882, 'text': "And let's see what that looks like.", 'start': 1069.542, 'duration': 1.34}, {'end': 1076.404, 'text': "So the next step is to dig in deep and find out what's going on behind the scenes.", 'start': 1071.523, 'duration': 4.881}, {'end': 1078.665, 'text': 'And also put that in a nice pretty graph.', 'start': 1076.704, 'duration': 1.961}, {'end': 1083.176, 'text': "We're going to spend more work on this than we did actually generating the original model.", 'start': 1079.252, 'duration': 3.924}, {'end': 1088.48, 'text': "And you'll see here that we go through a few steps, and I'll move this over to our editor in just a second.", 'start': 1083.376, 'duration': 5.104}, {'end': 1091.043, 'text': 'We come in, we create our original data.', 'start': 1088.881, 'duration': 2.162}, {'end': 1096.407, 'text': "it's exactly identical to the first part, and I'll explain why we redid that and show you how not to redo that.", 'start': 1091.043, 'duration': 5.364}, {'end': 1099.45, 'text': "And then we're going to go in there and add in those lines.", 'start': 1096.748, 'duration': 2.702}, {'end': 1102.613, 'text': "We're going to see what those lines look like and how to set those up.", 'start': 1099.91, 'duration': 2.703}, {'end': 1105.754, 'text': "And finally, we're going to plot all that on here and show it.", 'start': 1103.211, 'duration': 2.543}, {'end': 1111.602, 'text': "And you'll get a nice graph with what we saw earlier when we were going through the theory behind this,", 'start': 1106.015, 'duration': 5.587}, {'end': 1115.227, 'text': 'where it shows the support vectors and the hyperplane.', 'start': 1111.602, 'duration': 3.625}, {'end': 1120.614, 'text': 'And those are done where you can see the support vectors as the dashed lines and the solid line, which is the hyperplane.', 'start': 1115.607, 'duration': 5.007}, {'end': 1123.043, 'text': "Let's get that into our Jupyter notebook.", 'start': 1120.902, 'duration': 2.141}], 'summary': 'In-depth analysis and visualization of data, including model generation, with a focus on creating a graph.', 'duration': 60.663, 'max_score': 1062.38, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl81062380.jpg'}, {'end': 1228.299, 'src': 'embed', 'start': 1197.503, 'weight': 4, 'content': [{'end': 1200.624, 'text': "Now right now we're actually spending a lot of time just graphing.", 'start': 1197.503, 'duration': 3.121}, {'end': 1201.825, 'text': "That's all we're doing here.", 'start': 1200.664, 'duration': 1.161}, {'end': 1206.788, 'text': 'Okay, so this is how we display a nice graph with our results and our data.', 'start': 1202.205, 'duration': 4.583}, {'end': 1214.572, 'text': "AX is a very standard used variable when you're talking about PLT, and it's just setting it to that axis, the last axis in the PLT.", 'start': 1207.108, 'duration': 7.464}, {'end': 1221.715, 'text': "It can get very confusing if you're working with many different layers of data on the same graph, and this makes it very easy to reference the AX.", 'start': 1214.612, 'duration': 7.103}, {'end': 1228.299, 'text': 'So this reference is looking at the PLT that we created and we already mapped out our two blobs on.', 'start': 1222.096, 'duration': 6.203}], 'summary': 'Focus on graphing data with plt, using ax for easy referencing.', 'duration': 30.796, 'max_score': 1197.503, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl81197503.jpg'}, {'end': 1288.505, 'src': 'embed', 'start': 1256.351, 'weight': 3, 'content': [{'end': 1258.133, 'text': 'And this is a numpy command.', 'start': 1256.351, 'duration': 1.782}, {'end': 1260.696, 'text': "So we're back to our numbers Python.", 'start': 1258.494, 'duration': 2.202}, {'end': 1265.682, 'text': "Let's go through what these numpy commands mean with the line space and the mesh grid.", 'start': 1261.057, 'duration': 4.625}, {'end': 1275.973, 'text': "We've taken xx, small xx equals np linespace, and we have our x limit 0 and our x limit 1, and we're going to create 30 points on it.", 'start': 1265.942, 'duration': 10.031}, {'end': 1278.296, 'text': "And we're going to do the same thing for the y-axis.", 'start': 1275.993, 'duration': 2.303}, {'end': 1280.859, 'text': 'Now, this has nothing to do with our evaluation.', 'start': 1278.456, 'duration': 2.403}, {'end': 1288.505, 'text': "All we're doing is we're creating a grid of data and so we're creating a set of points between 0 and the X limit.", 'start': 1281.619, 'duration': 6.886}], 'summary': 'Using numpy to create 30 points on a grid for x and y axis.', 'duration': 32.154, 'max_score': 1256.351, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl81256351.jpg'}], 'start': 1062.38, 'title': 'Analyzing data and graphing svm results', 'summary': 'Discusses analyzing data to create graphs, emphasizing the effort required, and demonstrates graphing svm results in a jupyter notebook. it covers plotting support vectors, the hyperplane, using matplotlib for data representation, and the purpose of using ax variable for graphical referencing.', 'chapters': [{'end': 1102.613, 'start': 1062.38, 'title': 'Analyzing data and creating graphs', 'summary': 'Discusses the process of digging deep into the data to create a graph, requiring more effort than generating the original model.', 'duration': 40.233, 'highlights': ['The process involves creating original data, adding lines, and setting them up.', 'The effort put into analyzing the data and creating the graph exceeds that of generating the original model.']}, {'end': 1323.247, 'start': 1103.211, 'title': 'Graphing svm results in jupyter notebook', 'summary': 'Demonstrates how to graph svm results in a jupyter notebook, including plotting support vectors and the hyperplane, using matplotlib to create a grid for data representation, and explaining the purpose of using ax variable for graphical referencing.', 'duration': 220.036, 'highlights': ['The chapter demonstrates how to plot support vectors and the hyperplane in a graph, providing a visual representation of the SVM results using matplotlib.', 'The transcript explains the process of creating a grid for data representation using numpy commands like np.linespace and mesh grid, facilitating a clear visual understanding of the plotted data.', "It elucidates the purpose of using the 'ax' variable when working with PLT, emphasizing its importance in referencing different layers of data on the same graph for clarity and ease of use."]}], 'duration': 260.867, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl81062380.jpg', 'highlights': ['The process involves creating original data, adding lines, and setting them up.', 'The effort put into analyzing the data and creating the graph exceeds that of generating the original model.', 'The chapter demonstrates how to plot support vectors and the hyperplane in a graph, providing a visual representation of the SVM results using matplotlib.', 'The transcript explains the process of creating a grid for data representation using numpy commands like np.linespace and mesh grid, facilitating a clear visual understanding of the plotted data.', "It elucidates the purpose of using the 'ax' variable when working with PLT, emphasizing its importance in referencing different layers of data on the same graph for clarity and ease of use."]}, {'end': 1600.005, 'segs': [{'end': 1437.279, 'src': 'embed', 'start': 1408.71, 'weight': 0, 'content': [{'end': 1410.611, 'text': "So we've set all of our data up.", 'start': 1408.71, 'duration': 1.901}, {'end': 1416.553, 'text': "we've labeled it to three different areas and we reshaped it and we've just taken 30 points in each direction.", 'start': 1410.931, 'duration': 5.622}, {'end': 1420.594, 'text': "If you do the math, you have 30 times 30, so that's 900 points of data,", 'start': 1416.853, 'duration': 3.741}, {'end': 1424.215, 'text': 'and we separated between the three lines and reshaped it to fit those three lines.', 'start': 1420.594, 'duration': 3.621}, {'end': 1426.996, 'text': 'We can then go back to our map plot library.', 'start': 1424.535, 'duration': 2.461}, {'end': 1433.878, 'text': "We've created the AX and we're going to create a contour and you'll see here we have contour capital XX capital YY.", 'start': 1427.256, 'duration': 6.622}, {'end': 1435.918, 'text': 'These have been reshaped to fit those lines.', 'start': 1434.098, 'duration': 1.82}, {'end': 1437.279, 'text': 'Z is the labels.', 'start': 1436.259, 'duration': 1.02}], 'summary': 'Data reshaped and labeled into three areas, totaling 900 points, then plotted on a contour map.', 'duration': 28.569, 'max_score': 1408.71, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl81408710.jpg'}, {'end': 1579.049, 'src': 'embed', 'start': 1552.031, 'weight': 1, 'content': [{'end': 1555.534, 'text': 'Why support vector machine? So that we can classify objects.', 'start': 1552.031, 'duration': 3.503}, {'end': 1561.058, 'text': 'What is support vector machine? Where we learned about the support vectors and the hyperplane.', 'start': 1556.014, 'duration': 5.044}, {'end': 1565.882, 'text': 'We dug in deeper into understanding support vector machine for using multiple data,', 'start': 1561.239, 'duration': 4.643}, {'end': 1569.365, 'text': 'where the data is split and you had to create new levels or new planes.', 'start': 1565.882, 'duration': 3.483}, {'end': 1572.806, 'text': 'And finally, we did our case study of crocodiles and alligators,', 'start': 1569.665, 'duration': 3.141}, {'end': 1579.049, 'text': "where you got to see hands-on how to do a support vector machine and what's going on behind the scenes and how to display that.", 'start': 1572.806, 'duration': 6.243}], 'summary': 'Support vector machine used to classify objects, with a case study on crocodiles and alligators.', 'duration': 27.018, 'max_score': 1552.031, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl81552031.jpg'}], 'start': 1323.307, 'title': 'Using svm for crocodile and alligator classification', 'summary': 'Details the process of employing a support vector machine with 900 data points to create three distinct lines for classifying crocodiles and alligators.', 'chapters': [{'end': 1600.005, 'start': 1323.307, 'title': 'Support vector machine for crocodile and alligator classification', 'summary': 'Explains the process of using a support vector machine to classify crocodiles and alligators, using 900 data points to create three distinct lines that separate the two groups.', 'duration': 276.698, 'highlights': ['900 data points created to fit three distinct lines for classification', 'Support vector machine used to classify crocodiles and alligators', 'Explanation of the process behind SVM and its elements']}], 'duration': 276.698, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/TtKF996oEl8/pics/TtKF996oEl81323307.jpg', 'highlights': ['900 data points created to fit three distinct lines for classification', 'Support vector machine used to classify crocodiles and alligators', 'Explanation of the process behind SVM and its elements']}], 'highlights': ['The support vector machine is commonly used in face detection, text categorization, and bioinformatics.', 'The SVM model is trained using labeled data, enabling it to identify new data.', 'The advantages of support vector machine in high dimensional space are emphasized.', 'The chapter covers the setup of Support Vector Machines in Python.', 'The process involves creating original data, adding lines, and setting them up.', '900 data points created to fit three distinct lines for classification']}