title
A Beginner's Guide to Machine Learning with ml5.js

description
Welcome to "A Beginner's Guide to Machine Learning in JavaScript"! In this series, I'll teach the concepts behind machine learning using the ml5.js library. . Code: https://thecodingtrain.com/tracks/ml5js-beginners-guide/ml5/0-introduction/1-introduction 🎥 Next: https://youtu.be/yNkAuWz5lnY?list=PLRqwX-V7Uu6YPSwT06y_AEYTqIwbeam3y 🎥 All: https://www.youtube.com/playlist?list=PLRqwX-V7Uu6YPSwT06y_AEYTqIwbeam3y References: 💻 ml5.js: https://ml5js.org/ 📝 ml5 on Adjacent: https://itp.nyu.edu/adjacent/issue-3/ml5-friendly-open-source-machine-learning-library-for-the-web/ 🔗 Red Burns Bio: https://itp.nyu.edu/redburnsfund/bio.php 📕 Intelligence and Learning Class: https://github.com/nature-of-code/NOC-S17-2-Intelligence-Learning/tree/master/week3-classification-regression Videos: 🚂 TensorFlow.js Color Classifier: https://www.youtube.com/playlist?list=PLRqwX-V7Uu6bmMRCIoTi72aNWHo7epX4L 🚂 TensorFlow.js playlist: https://www.youtube.com/playlist?list=PLRqwX-V7Uu6YIeVA3dNxbR9PYj4wV31oQ Timestamps: 0:00 Introduction 2:00 What is machine learning? 6:00 What is ML5? 11:45 Tensorflow 14:30 Neural networks, pretrained models, and data sets 16:50 MobilNet 18:06 ML5.org 20:34 Attributions Editing by Mathieu Blanchette Animations by Jason Heglund Music from Epidemic Sound 🚂 Website: https://thecodingtrain.com/ 👾 Share Your Creation! https://thecodingtrain.com/guides/passenger-showcase-guide 🚩 Suggest Topics: https://github.com/CodingTrain/Suggestion-Box 💡 GitHub: https://github.com/CodingTrain 💬 Discord: https://thecodingtrain.com/discord 💖 Membership: http://youtube.com/thecodingtrain/join 🛒 Store: https://standard.tv/codingtrain 🖋️ Twitter: https://twitter.com/thecodingtrain 📸 Instagram: https://www.instagram.com/the.coding.train/ 🎥 Coding Challenges: https://www.youtube.com/playlist?list=PLRqwX-V7Uu6ZiZxtDDRCi6uhfTH4FilpH 🎥 Intro to Programming: https://www.youtube.com/playlist?list=PLRqwX-V7Uu6Zy51Q-x9tMWIv9cueOFTFA 🔗 p5.js: https://p5js.org 🔗 p5.js Web Editor: https://editor.p5js.org/ 🔗 Processing: https://processing.org 📄 Code of Conduct: https://github.com/CodingTrain/Code-of-Conduct This description was auto-generated. If you see a problem, please open an issue: https://github.com/CodingTrain/thecodingtrain.com/issues/new #machinelearningml #ml5js #tensorflow #p5js #ml5js #tensorflowjs

detail
{'title': "A Beginner's Guide to Machine Learning with ml5.js", 'heatmap': [{'end': 1110.641, 'start': 1090.888, 'weight': 1}], 'summary': "Series 'a beginner's guide to machine learning with ml5.js' introduces machine learning and the ml5 javascript library, emphasizing accessibility for beginners, teaching the basics, and demonstrating the use of p5.js and tensorflow.js for creating art and performing machine learning tasks.", 'chapters': [{'end': 205.624, 'segs': [{'end': 62.589, 'src': 'embed', 'start': 0.649, 'weight': 0, 'content': [{'end': 3.77, 'text': 'Hello, and welcome to a new playlist of videos.', 'start': 0.649, 'duration': 3.121}, {'end': 4.891, 'text': 'This is a playlist.', 'start': 4.07, 'duration': 0.821}, {'end': 10.593, 'text': "I mean, hopefully there's a bunch of videos in this playlist, because I'm just starting to record them now, so they don't exist yet.", 'start': 5.251, 'duration': 5.342}, {'end': 15.454, 'text': 'But this is about machine learning, and it is for the total beginner.', 'start': 10.653, 'duration': 4.801}, {'end': 17.375, 'text': "Now there's some caveats here, I suppose, to that.", 'start': 15.534, 'duration': 1.841}, {'end': 18.675, 'text': 'But I really wanted to make something.', 'start': 17.595, 'duration': 1.08}, {'end': 22.117, 'text': "You don't have to have watched any other videos about machine learning on my channel.", 'start': 18.695, 'duration': 3.422}, {'end': 24.357, 'text': 'I have others that go more in depth and use different tools.', 'start': 22.157, 'duration': 2.2}, {'end': 27.479, 'text': "This has really meant if you're starting, it's totally new to you.", 'start': 24.658, 'duration': 2.821}, {'end': 28.259, 'text': 'You heard.', 'start': 27.679, 'duration': 0.58}, {'end': 30.54, 'text': "You've heard the words machine learning.", 'start': 28.939, 'duration': 1.601}, {'end': 32.601, 'text': 'you type them into some.', 'start': 30.54, 'duration': 2.061}, {'end': 34.364, 'text': 'what is machine learning?', 'start': 32.601, 'duration': 1.763}, {'end': 35.285, 'text': 'ah, search bar.', 'start': 34.364, 'duration': 0.921}, {'end': 40.449, 'text': 'and somehow you landed here, watching from the future, leaning back.', 'start': 35.285, 'duration': 5.164}, {'end': 49.017, 'text': "you've taken your brain out for its afternoon thawing and your gelatinous couch is comfortably supporting your.", 'start': 40.449, 'duration': 8.568}, {'end': 54.862, 'text': "Anyway, the point is, you're here, I'm here, hello.", 'start': 52.02, 'duration': 2.842}, {'end': 62.589, 'text': "So I'm going to be using for this set of tutorials a pretty new JavaScript library called ml5.", 'start': 56.043, 'duration': 6.546}], 'summary': 'New playlist for total beginners on machine learning using ml5 library.', 'duration': 61.94, 'max_score': 0.649, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0649.jpg'}, {'end': 115.112, 'src': 'embed', 'start': 83.224, 'weight': 3, 'content': [{'end': 87.727, 'text': 'I will point you to other videos that can help you fill in some missing gaps.', 'start': 83.224, 'duration': 4.503}, {'end': 90.329, 'text': "But I'm going to assume a little bit of knowledge about programming.", 'start': 87.767, 'duration': 2.562}, {'end': 97.508, 'text': "particularly in JavaScript, and I'm also going to be making fairly heavy use of another JavaScript library called p5.", 'start': 91.465, 'duration': 6.043}, {'end': 101.41, 'text': "So if p5 is new to you, I'll refer you to some other p5 tutorials.", 'start': 97.808, 'duration': 3.602}, {'end': 107.473, 'text': "I will, but that's going to be a large piece of how I build various examples throughout all these videos.", 'start': 101.41, 'duration': 6.063}, {'end': 115.112, 'text': "Okay, so before I start talking to you about what is ml5, which is really what I'm here to do.", 'start': 108.513, 'duration': 6.599}], 'summary': 'The speaker assumes basic programming knowledge, especially in javascript, and plans to heavily use the p5 library in the videos.', 'duration': 31.888, 'max_score': 83.224, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP083224.jpg'}, {'end': 187.598, 'src': 'embed', 'start': 162.313, 'weight': 5, 'content': [{'end': 169.514, 'text': 'and trying to make sense of that data and teaching a computer basically to learn patterns that we can present.', 'start': 162.313, 'duration': 7.201}, {'end': 173.195, 'text': "And we're not talking about something called supervised learning here.", 'start': 169.614, 'duration': 3.581}, {'end': 175.456, 'text': 'Oh, even more terminology, supervised learning.', 'start': 173.435, 'duration': 2.021}, {'end': 178.416, 'text': "I'm going to get into all that, and I've gotten into some of that in other videos.", 'start': 175.476, 'duration': 2.94}, {'end': 187.598, 'text': 'So I just pulled up some notes that I made for a course about artificial intelligence at NYU here.', 'start': 178.876, 'duration': 8.722}], 'summary': 'Teaching computers to learn patterns, not supervised learning, part of ai course at nyu', 'duration': 25.285, 'max_score': 162.313, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0162313.jpg'}], 'start': 0.649, 'title': 'Introduction to machine learning', 'summary': 'Introduces a new playlist of videos on machine learning for total beginners, emphasizing an accessible approach for those new to the concept, and discusses the ml5 javascript library and the basics of machine learning, highlighting the need for coding knowledge and the concept of examining data to teach a computer patterns.', 'chapters': [{'end': 35.285, 'start': 0.649, 'title': 'Introduction to machine learning for beginners', 'summary': 'Introduces a new playlist of videos on machine learning designed for total beginners, with a focus on creating content for those who are new to the concept, and offers an accessible approach for those who are just starting out in the field.', 'duration': 34.636, 'highlights': ['This is a playlist about machine learning, created for total beginners, offering an accessible approach for those who are just starting out in the field.', 'The content is meant for those who are new to the concept, without requiring them to have watched any other videos about machine learning on the channel.', 'The playlist aims to provide a starting point for individuals who have heard about machine learning but are unfamiliar with the topic.']}, {'end': 205.624, 'start': 35.285, 'title': 'Introduction to ml5 in javascript', 'summary': 'Introduces the ml5 javascript library, discusses the basics of machine learning, and emphasizes the need for some coding knowledge. it outlines the concept of machine learning as examining a lot of data to teach a computer to learn patterns.', 'duration': 170.339, 'highlights': ['The chapter emphasizes the need for some coding knowledge, particularly in JavaScript, and mentions the use of the p5 JavaScript library. The tutorial assumes a little bit of knowledge about programming, particularly in JavaScript, and mentions the heavy use of the p5 JavaScript library.', 'The chapter outlines the concept of machine learning as examining a lot of data to teach a computer to learn patterns, and mentions the idea of supervised learning. Machine learning is described as examining a lot of data to teach a computer to learn patterns, and the concept of supervised learning is briefly introduced.', 'The chapter introduces the ML5 JavaScript library and emphasizes its relevance in the tutorials. The ML5 JavaScript library is introduced and its relevance in the tutorials is emphasized.']}], 'duration': 204.975, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0649.jpg', 'highlights': ['This is a playlist about machine learning, created for total beginners, offering an accessible approach for those who are just starting out in the field.', 'The playlist aims to provide a starting point for individuals who have heard about machine learning but are unfamiliar with the topic.', 'The content is meant for those who are new to the concept, without requiring them to have watched any other videos about machine learning on the channel.', 'The chapter emphasizes the need for some coding knowledge, particularly in JavaScript, and mentions the use of the p5 JavaScript library.', 'The chapter introduces the ML5 JavaScript library and emphasizes its relevance in the tutorials.', 'The chapter outlines the concept of machine learning as examining a lot of data to teach a computer to learn patterns, and mentions the idea of supervised learning.']}, {'end': 458.127, 'segs': [{'end': 355.949, 'src': 'embed', 'start': 333.504, 'weight': 0, 'content': [{'end': 341.445, 'text': 'Teaching a computer to perform a task without explicitly programming the algorithm for that task.', 'start': 333.504, 'duration': 7.941}, {'end': 349.087, 'text': "Now, it's a little convoluted because aren't we programming the machine learning algorithm? But this is the conceptual idea.", 'start': 341.485, 'duration': 7.602}, {'end': 355.949, 'text': 'OK. so now that we, as best as I, could, made some definition, created a definition of machine learning,', 'start': 350.067, 'duration': 5.882}], 'summary': 'Teaching a computer to perform a task without explicit programming, discussing the conceptual idea of machine learning.', 'duration': 22.445, 'max_score': 333.504, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0333504.jpg'}, {'end': 435.459, 'src': 'embed', 'start': 403.591, 'weight': 1, 'content': [{'end': 408.173, 'text': 'Consider the technology as a tool which in itself could do nothing.', 'start': 403.591, 'duration': 4.582}, {'end': 414.996, 'text': 'Treat the technology as something that everyone on the team could learn, understand, and explore freely.', 'start': 408.854, 'duration': 6.142}, {'end': 418.117, 'text': 'So this is really important.', 'start': 415.616, 'duration': 2.501}, {'end': 420.799, 'text': "Don't believe the hype.", 'start': 419.498, 'duration': 1.301}, {'end': 427.101, 'text': "Is that an expression that people say? But it's easy to get caught up in the shiny technology stuff.", 'start': 420.819, 'duration': 6.282}, {'end': 435.459, 'text': "But we have to remember that without human beings here on this planet, what's the point?", 'start': 427.221, 'duration': 8.238}], 'summary': 'View technology as a learnable tool, not a hype-driven distraction, to prioritize human impact.', 'duration': 31.868, 'max_score': 403.591, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0403591.jpg'}], 'start': 205.724, 'title': 'Introduction to ml5 and machine learning', 'summary': 'Explains the concept of machine learning and the key principles behind the ml5 project, emphasizing the importance of understanding technology as a tool.', 'chapters': [{'end': 458.127, 'start': 205.724, 'title': 'Introduction to ml5 and machine learning', 'summary': 'Explains the concept of machine learning, teaching a computer to perform a task without explicitly programming the algorithm for that task, and touches on the key principles behind the ml5 project, emphasizing the importance of understanding technology as a tool and not getting caught up in the hype of shiny technology.', 'duration': 252.403, 'highlights': ['Teaching a computer to perform a task without explicitly programming the algorithm for that task Machine learning involves teaching a system to understand data without writing a specific algorithm, demonstrating the core concept of machine learning.', 'Importance of understanding technology as a tool and not getting caught up in the hype of shiny technology Red Burns emphasizes the importance of treating technology as a tool that everyone can learn and understand, cautioning against getting too caught up in the excitement of new technology without considering its practical applications.']}], 'duration': 252.403, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0205724.jpg', 'highlights': ['Machine learning involves teaching a system to understand data without writing a specific algorithm, demonstrating the core concept of machine learning.', 'Red Burns emphasizes the importance of treating technology as a tool that everyone can learn and understand, cautioning against getting too caught up in the excitement of new technology without considering its practical applications.']}, {'end': 714.558, 'segs': [{'end': 617.087, 'src': 'embed', 'start': 513.604, 'weight': 0, 'content': [{'end': 524.046, 'text': 'Another really important part of this discussion is just the library TensorFlow itself, as well as maybe this thing called Keras,', 'start': 513.604, 'duration': 10.442}, {'end': 525.206, 'text': 'which I might refer to.', 'start': 524.046, 'duration': 1.16}, {'end': 535.729, 'text': 'So first of all, what is ml5.js? ml5.js itself is just a JavaScript library.', 'start': 525.707, 'duration': 10.022}, {'end': 542.33, 'text': 'It is a library of functions that you can call from your own JavaScript code.', 'start': 537.309, 'duration': 5.021}, {'end': 546.523, 'text': "So again, I mentioned that I'm going to rely heavily on p5.", 'start': 543.22, 'duration': 3.303}, {'end': 549.566, 'text': 'p5 is also just a JavaScript library.', 'start': 547.124, 'duration': 2.442}, {'end': 553.409, 'text': 'p5 is a little bit of a special JavaScript library.', 'start': 549.826, 'duration': 3.583}, {'end': 558.454, 'text': 'Make a little heart there, a couple stars, because it is really.', 'start': 553.429, 'duration': 5.025}, {'end': 564.619, 'text': "It doesn't necessarily conform to the standard patterns you might find in other JavaScript libraries.", 'start': 559.094, 'duration': 5.525}, {'end': 570.483, 'text': 'It makes a lot of decisions to be as friendly and welcoming and well-suited for a beginner as it can be.', 'start': 564.979, 'duration': 5.504}, {'end': 575.147, 'text': 'So one of the things you can do in P5 is you can write a function called setup.', 'start': 570.723, 'duration': 4.424}, {'end': 584.014, 'text': 'And any code that you put in setup executes the moment the program starts.', 'start': 578.409, 'duration': 5.605}, {'end': 586.836, 'text': 'You can write a function called draw.', 'start': 584.894, 'duration': 1.942}, {'end': 592.639, 'text': 'And any code that you put in draw happens in a loop over and over again.', 'start': 588.658, 'duration': 3.981}, {'end': 601.342, 'text': 'This is a standard kind of design pattern for writing a program that generates an animation, like a game or a piece of interactive art.', 'start': 592.679, 'duration': 8.663}, {'end': 609.964, 'text': "So what I'm saying here is that my examples that I'm going to show you in these video tutorials are using p5.js almost as the base starting point.", 'start': 602.302, 'duration': 7.662}, {'end': 614.466, 'text': 'And then I am also going to import the ml5 library.', 'start': 610.405, 'duration': 4.061}, {'end': 617.087, 'text': 'So I need to import both of these libraries.', 'start': 614.706, 'duration': 2.381}], 'summary': 'Discussion on ml5.js and p5.js libraries for javascript, with emphasis on their functions and design patterns.', 'duration': 103.483, 'max_score': 513.604, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0513604.jpg'}], 'start': 458.147, 'title': 'Ml5.js and p5.js introduction', 'summary': 'Introduces ml5.js as a beginner-friendly javascript library along with its components p5.js, tensorflow.js, tensorflow, and keras. it also demonstrates the use of p5.js for creating animations and interactive art and the incorporation of ml5 library for machine learning tasks like image classification.', 'chapters': [{'end': 570.483, 'start': 458.147, 'title': 'Introduction to ml5.js and its components', 'summary': 'Introduces ml5.js as a javascript library and its components, including p5.js, tensorflow.js, tensorflow, and keras, emphasizing its beginner-friendly nature.', 'duration': 112.336, 'highlights': ['ML5.js is a JavaScript library consisting of functions for JavaScript code, emphasizing its beginner-friendly nature and reliance on p5.js.', 'The discussion highlights the significance of p5.js, a special JavaScript library designed to be beginner-friendly and non-conforming to standard patterns.', 'The chapter introduces tensorflow.js and TensorFlow as important components in the discussion of ML5.js, highlighting their relevance in the context of the ML5 project.', "The transcript emphasizes the importance of Keras as a component of ML5.js, providing insights into the library's comprehensive nature and its reliance on various associated components."]}, {'end': 714.558, 'start': 570.723, 'title': 'Introduction to p5.js and ml5 library', 'summary': 'Introduces the use of p5.js for creating animations and interactive art, and also demonstrates the incorporation of the ml5 library for machine learning tasks, such as image classification.', 'duration': 143.835, 'highlights': ["The use of p5.js for creating animations and interactive art is demonstrated, with 'setup' and 'draw' functions executing specific code at program start and in a loop respectively.", 'Incorporation of the ml5 library for machine learning tasks, particularly demonstrated through an example of image classification, is explained with the need for importing both p5.js and ml5 libraries.', 'The process of calling functions from JavaScript libraries is discussed, emphasizing the namespaced nature of JavaScript libraries, such as the requirement to specify the library name followed by the function name.', 'The common machine learning task of image classification is highlighted, with the example of training a machine learning model to differentiate between images of kitty cats and puppy dogs being used to illustrate the concept.']}], 'duration': 256.411, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0458147.jpg', 'highlights': ['The chapter introduces tensorflow.js and TensorFlow as important components in the discussion of ML5.js, highlighting their relevance in the context of the ML5 project.', 'The discussion highlights the significance of p5.js, a special JavaScript library designed to be beginner-friendly and non-conforming to standard patterns.', 'Incorporation of the ml5 library for machine learning tasks, particularly demonstrated through an example of image classification, is explained with the need for importing both p5.js and ml5 libraries.', "The use of p5.js for creating animations and interactive art is demonstrated, with 'setup' and 'draw' functions executing specific code at program start and in a loop respectively."]}, {'end': 1140.888, 'segs': [{'end': 862.427, 'src': 'embed', 'start': 793.471, 'weight': 0, 'content': [{'end': 795.372, 'text': "But that's not the case with TensorFlow.js.", 'start': 793.471, 'duration': 1.901}, {'end': 799.915, 'text': "TensorFlow.js is everything's happening in JavaScript.", 'start': 795.612, 'duration': 4.303}, {'end': 804.558, 'text': 'And you could go and just use TensorFlow.js directly to do your machine learning stuff.', 'start': 800.976, 'duration': 3.582}, {'end': 807.3, 'text': 'And I have some video tutorials that talk about that.', 'start': 804.999, 'duration': 2.301}, {'end': 813.886, 'text': 'ML5 is a project that actually is a layer.', 'start': 809.185, 'duration': 4.701}, {'end': 815.867, 'text': 'It includes TensorFlow.js.', 'start': 814.006, 'duration': 1.861}, {'end': 825.41, 'text': 'So ML5 is a library where additional functions were added on top of TensorFlow.js to make certain tasks easier, and in truth,', 'start': 816.067, 'duration': 9.343}, {'end': 829.231, 'text': 'This is a low-level library, meaning, if you were to use it directly,', 'start': 826.07, 'duration': 3.161}, {'end': 835.753, 'text': 'you have to really worry about things like memory management and this kind of stuff.', 'start': 829.231, 'duration': 6.522}, {'end': 838.273, 'text': "It's interesting.", 'start': 835.833, 'duration': 2.44}, {'end': 839.173, 'text': 'You can do it.', 'start': 838.673, 'duration': 0.5}, {'end': 847.236, 'text': "But if you're just getting started and want to learn the basics of machine learning and experiment and play, this is going to be in your way.", 'start': 839.554, 'duration': 7.682}, {'end': 848.676, 'text': "It's going to make things take longer.", 'start': 847.256, 'duration': 1.42}, {'end': 857.383, 'text': "And so ML5's goal is to make a lot of the things that you do in TensorFlow.js a bit easier and more accessible.", 'start': 849.076, 'duration': 8.307}, {'end': 862.427, 'text': "Okay, so here's the other thing that I really want to discuss.", 'start': 858.024, 'duration': 4.403}], 'summary': 'Tensorflow.js and ml5: javascript libraries for machine learning, with ml5 making tasks easier and more accessible.', 'duration': 68.956, 'max_score': 793.471, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0793471.jpg'}, {'end': 1002.161, 'src': 'embed', 'start': 955.336, 'weight': 3, 'content': [{'end': 962.32, 'text': "the reason why I'm hoping that this video tutorial and this ML5 library is important and useful,", 'start': 955.336, 'duration': 6.984}, {'end': 969.644, 'text': 'is that our lives are increasingly being governed by pre-trained models.', 'start': 962.32, 'duration': 7.324}, {'end': 979.361, 'text': "Corporations train models to perform a particular task, to recognize your face, to turn the words you're speaking into text.", 'start': 970.558, 'duration': 8.803}, {'end': 985.543, 'text': 'There are many questionably ethical applications of this.', 'start': 980.341, 'duration': 5.202}, {'end': 988.584, 'text': 'There are also fun, artistic, and playful applications of this.', 'start': 985.863, 'duration': 2.721}, {'end': 990.686, 'text': 'So one of the ways, I think,', 'start': 989.384, 'duration': 1.302}, {'end': 998.997, 'text': 'to get started as a beginner to machine learning is actually not to learn all the math and learn how to train all your own machine learning systems,', 'start': 990.686, 'duration': 8.311}, {'end': 1002.161, 'text': 'but to actually make use of some pre-trained models that are out there.', 'start': 998.997, 'duration': 3.164}], 'summary': 'Ml5 library enables beginners to use pre-trained models for various applications.', 'duration': 46.825, 'max_score': 955.336, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0955336.jpg'}, {'end': 1065.187, 'src': 'embed', 'start': 1041.53, 'weight': 5, 'content': [{'end': 1051.636, 'text': 'And so by friendly and accessible or approachable ways of being able to experiment with pre-trained models, this is a good place to start.', 'start': 1041.53, 'duration': 10.106}, {'end': 1053.777, 'text': 'All right, so machine learning is a thing.', 'start': 1052.156, 'duration': 1.621}, {'end': 1056.22, 'text': "It's the thing people are talking about.", 'start': 1054.598, 'duration': 1.622}, {'end': 1062.625, 'text': 'We want to get some experience playing around with it, experimenting with it, understanding what it is.', 'start': 1056.66, 'duration': 5.965}, {'end': 1065.187, 'text': "We're going to use this ML5 library.", 'start': 1063.285, 'duration': 1.902}], 'summary': 'Using ml5 library to experiment with pre-trained models for accessible machine learning.', 'duration': 23.657, 'max_score': 1041.53, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP01041530.jpg'}, {'end': 1123.41, 'src': 'heatmap', 'start': 1090.888, 'weight': 1, 'content': [{'end': 1092.369, 'text': 'I would encourage you to click on.', 'start': 1090.888, 'duration': 1.481}, {'end': 1098.173, 'text': "there's lots of stuff to read about here, but I would encourage you to click on examples and go down and just try all of these.", 'start': 1092.369, 'duration': 5.804}, {'end': 1101.195, 'text': "So you can see there's some pre-trained models that I'm going to be using.", 'start': 1098.413, 'duration': 2.782}, {'end': 1103.496, 'text': "I'm going to do a tutorial basically about each one of these.", 'start': 1101.215, 'duration': 2.281}, {'end': 1110.641, 'text': 'Notably, like I mentioned, one called PoseNet, which actually can take an image and estimate your pose, meaning where your hands,', 'start': 1104.157, 'duration': 6.484}, {'end': 1113.563, 'text': 'where your shoulders, where your eyes, where your hips.', 'start': 1110.641, 'duration': 2.922}, {'end': 1115.985, 'text': 'I might be getting that somewhat wrong there.', 'start': 1114.564, 'duration': 1.421}, {'end': 1118.326, 'text': "But that's a pre-trained model.", 'start': 1116.265, 'duration': 2.061}, {'end': 1123.41, 'text': 'Just like a pre-trained model learns how to classify the content of an image,', 'start': 1118.386, 'duration': 5.024}], 'summary': 'Encouraging to explore pre-trained models like posenet for image pose estimation.', 'duration': 32.522, 'max_score': 1090.888, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP01090888.jpg'}], 'start': 714.738, 'title': 'Tensorflow.js and machine learning basics', 'summary': 'Introduces tensorflow.js, a javascript version of tensorflow, and ml5, a library built on top of tensorflow.js, enabling beginners to experiment with machine learning. it also introduces the components of machine learning: algorithms, models, and data sets, emphasizing the significance of pre-trained models for beginners to explore.', 'chapters': [{'end': 862.427, 'start': 714.738, 'title': 'Tensorflow.js and ml5', 'summary': 'Introduces tensorflow.js, a javascript version of tensorflow, and ml5, a library built on top of tensorflow.js, to make machine learning tasks easier and more accessible, enabling beginners to experiment and play with the basics of machine learning.', 'duration': 147.689, 'highlights': ['TensorFlow.js is a JavaScript version of TensorFlow, allowing machine learning tasks to be performed directly in JavaScript. TensorFlow.js is a version of TensorFlow written in JavaScript, enabling machine learning tasks to be performed directly in JavaScript, providing an alternative to writing code in Python.', 'ML5 is a library built on top of TensorFlow.js, aiming to simplify and make machine learning tasks more accessible, particularly for beginners. ML5 is a library that includes additional functions built on top of TensorFlow.js to simplify machine learning tasks, particularly for beginners, by making tasks easier and more accessible.', 'ML5 is designed to make machine learning tasks easier and more accessible for beginners, by providing additional functions and simplifying tasks that are otherwise complex in TensorFlow.js. ML5 is designed to simplify and make machine learning tasks more accessible for beginners by providing additional functions and simplifying tasks that are complex in TensorFlow.js, enabling beginners to experiment and play with the basics of machine learning.']}, {'end': 1140.888, 'start': 864.049, 'title': 'Introduction to machine learning', 'summary': 'Introduces the three components of machine learning: algorithms, models, and data sets. it emphasizes the increasing significance of pre-trained models and encourages beginners to explore and experiment with them to understand their functioning and ethical implications.', 'duration': 276.839, 'highlights': ['The significance of pre-trained models in governing our lives and the increasing use of pre-trained models by corporations for various tasks. Pre-trained models are increasingly governing our lives and are being used by corporations for tasks such as facial recognition and speech-to-text conversion.', 'Encouraging beginners to utilize pre-trained models for experimentation and learning, rather than focusing solely on learning the mathematical and statistical aspects of machine learning. Beginners are encouraged to experiment with pre-trained models as a starting point in understanding machine learning, rather than solely focusing on learning mathematical and statistical components.', 'The recommendation to explore the ML5 library and its pre-trained models, particularly PoseNet, which estimates human poses in images. Beginners are encouraged to explore the ML5 library and its pre-trained models, such as PoseNet, which estimates human poses in images.']}], 'duration': 426.15, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP0714738.jpg', 'highlights': ['TensorFlow.js enables machine learning tasks directly in JavaScript, providing an alternative to Python.', 'ML5 simplifies machine learning tasks, particularly for beginners, by providing additional functions.', 'ML5 is designed to make machine learning tasks more accessible for beginners by simplifying complex tasks in TensorFlow.js.', 'Pre-trained models are increasingly used by corporations for tasks like facial recognition and speech-to-text conversion.', 'Beginners are encouraged to experiment with pre-trained models as a starting point in understanding machine learning.', 'Exploring the ML5 library and its pre-trained models, such as PoseNet, is recommended for beginners.']}, {'end': 1387.576, 'segs': [{'end': 1309.907, 'src': 'embed', 'start': 1140.888, 'weight': 0, 'content': [{'end': 1143.612, 'text': 'because ml5.js is not a library that I created.', 'start': 1140.888, 'duration': 2.724}, {'end': 1147.997, 'text': "It's a project certainly that I have worked on, but it came from many, many other people.", 'start': 1144.372, 'duration': 3.625}, {'end': 1154.041, 'text': 'So first thing to mention is, and I did talk about this, that ml5.js is a layer on top of TensorFlow.js.', 'start': 1148.197, 'duration': 5.844}, {'end': 1158.944, 'text': 'So all of the heavy lifting behind the scenes really comes from this library, which was a prod.', 'start': 1154.061, 'duration': 4.883}, {'end': 1162.626, 'text': 'Many people are working on and contributing to this library at Google and otherwise,', 'start': 1158.984, 'duration': 3.642}, {'end': 1167.289, 'text': 'but the project was initiated by Nikhil and Daniel researchers at Google.', 'start': 1162.626, 'duration': 4.663}, {'end': 1171.952, 'text': 'The development was funded by, with the support of the Google Pig Bikster Group,', 'start': 1167.669, 'duration': 4.283}, {'end': 1181.459, 'text': 'the Google Big Picture Group and the People Plus AI Research Initiative, which is led by Martin Wattenberg and Fernanda Villegas.', 'start': 1172.572, 'duration': 8.887}, {'end': 1187.404, 'text': "And they've done a lot of wonderful projects about visualization and machine learning.", 'start': 1182.92, 'duration': 4.484}, {'end': 1195.33, 'text': 'The style and approach of our library really comes from the processing foundation.', 'start': 1188.54, 'duration': 6.79}, {'end': 1196.492, 'text': 'I mentioned the relationship.', 'start': 1195.39, 'duration': 1.102}, {'end': 1205.959, 'text': 'I guess I meant to say like the reason why the five is here is because of the sort of symbiotic relationship with p5.', 'start': 1196.552, 'duration': 9.407}, {'end': 1214.224, 'text': "We've made sure ML5 library, you absolutely do not need to use p5 with it, but it is fully compatible with p5.", 'start': 1206.479, 'duration': 7.745}, {'end': 1226.252, 'text': 'And the spirit of p5, I think, in its welcoming and inclusive sensibility is present in the ML5 library.', 'start': 1214.585, 'duration': 11.667}, {'end': 1229.475, 'text': "And so as a thank you to p5, we've used the 5 there.", 'start': 1226.332, 'duration': 3.143}, {'end': 1241.588, 'text': 'OK, Cristobal Valenzuela, who is also the creator of RunwayML, which you should definitely check out,', 'start': 1230.715, 'duration': 10.873}, {'end': 1250.44, 'text': 'started this project at ITP by creating a few examples with the deeplearn.js library, which is what TensorFlow, which is what became TensorFlow.js.', 'start': 1241.588, 'duration': 8.852}, {'end': 1261.049, 'text': "Yining has done amazing work on porting StyleTrans4, Yining Shi, and Pix2Pix models into ML5, and this is what's really wonderful.", 'start': 1251.802, 'duration': 9.247}, {'end': 1263.431, 'text': 'Pikachu, edge-to-edge Pikachu.', 'start': 1262.01, 'duration': 1.421}, {'end': 1269.917, 'text': "Yining hopefully will either be making her own videos that I will point you to, or I'll have her in as a guest to go over some of these.", 'start': 1263.491, 'duration': 6.426}, {'end': 1281.72, 'text': 'Hannah Davis has done a lot of work around data collection and responsible data collection that I encourage you to read about and find on the ML5 website through an artist residency.', 'start': 1272.318, 'duration': 9.402}, {'end': 1288.342, 'text': 'Nikita Huggins, a resident researcher at ITP, really did a ton of work project management work,', 'start': 1282.2, 'duration': 6.142}, {'end': 1293.383, 'text': 'vital important work in shepherding the library through many different stages.', 'start': 1288.342, 'duration': 5.041}, {'end': 1298.364, 'text': 'The ML5 logo on the website is designed by Alejandro.', 'start': 1295.143, 'duration': 3.221}, {'end': 1303.406, 'text': 'Heiyun Huang also gave lots of support to that.', 'start': 1299.665, 'duration': 3.741}, {'end': 1309.907, 'text': 'Dan Oved actually ported the PoseNet model to TensorFlow.js and ML5.js.', 'start': 1304.226, 'duration': 5.681}], 'summary': 'Ml5.js is a layer on top of tensorflow.js, initiated by google researchers, with contributions from various individuals and groups, and compatible with p5.', 'duration': 169.019, 'max_score': 1140.888, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP01140888.jpg'}, {'end': 1358.196, 'src': 'embed', 'start': 1325.293, 'weight': 8, 'content': [{'end': 1331.598, 'text': 'We had a lot of guest artists who came to visit us and give us lots of inspiration and ideas throughout the process.', 'start': 1325.293, 'duration': 6.305}, {'end': 1340.944, 'text': 'And then many organizations allowed us to do some of the first experimental workshops School for Poetic Computation, iBeam, Creative Coding Fest,', 'start': 1332.078, 'duration': 8.866}, {'end': 1341.625, 'text': 'ITP Camp.', 'start': 1340.944, 'duration': 0.681}, {'end': 1358.196, 'text': 'And there have been many other contributors that you can find if you go to ml5js.org and you click on code and browse the GitHub repositories and see all the wonderful people who have contributed.', 'start': 1343.026, 'duration': 15.17}], 'summary': 'Numerous guest artists and organizations, including school for poetic computation, ibeam, creative coding fest, and itp camp, provided inspiration and support. many other contributors can be found on ml5js.org.', 'duration': 32.903, 'max_score': 1325.293, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP01325293.jpg'}], 'start': 1140.888, 'title': 'Introduction to ml5.js and ml5 library', 'summary': 'Provides an introduction to ml5.js, a library built on top of tensorflow.js, initiated by nikhil and daniel at google, funded by google, and influenced by the processing foundation, designed to have a symbiotic relationship with p5. it also introduces the ml5 library, highlighting the contributions of individuals like yining shi, hannah davis, nikita huggins, and dan oved, as well as the involvement of guest artists and organizations in the development process.', 'chapters': [{'end': 1241.588, 'start': 1140.888, 'title': 'Introduction to ml5.js', 'summary': 'Introduces ml5.js, a library built on top of tensorflow.js, initiated by nikhil and daniel at google, funded by google, and influenced by the processing foundation, designed to have a symbiotic relationship with p5.', 'duration': 100.7, 'highlights': ['ml5.js is a layer on top of TensorFlow.js, leveraging the heavy lifting from this library, which was initiated by researchers at Google. (Relevance: 5)', 'The development of ml5.js was funded by the Google Pig Bikster Group, the Google Big Picture Group, and the People Plus AI Research Initiative, led by Martin Wattenberg and Fernanda Villegas. (Relevance: 4)', 'The spirit of p5, in its welcoming and inclusive sensibility, is present in the ML5 library, designed to have a symbiotic relationship with p5. (Relevance: 3)', 'Cristobal Valenzuela, the creator of RunwayML, is also associated with ML5 library. (Relevance: 2)']}, {'end': 1387.576, 'start': 1241.588, 'title': 'Introduction to ml5 library', 'summary': 'Introduces the ml5 library, highlighting the contributions of individuals like yining shi, hannah davis, nikita huggins, and dan oved, as well as the involvement of guest artists and organizations in the development process.', 'duration': 145.988, 'highlights': ["Yining Shi and Pix2Pix models were ported into ML5, showcasing significant contributions to the library's expansion.", 'Hannah Davis focused on responsible data collection, encouraging readers to explore her work on the ML5 website.', 'Nikita Huggins played a crucial role in project management for the library, ensuring its progress through various stages.', 'Dan Oved successfully ported the PoseNet model to TensorFlow.js and ML5.js, laying the groundwork for future video tutorials.', 'The involvement of guest artists and organizations provided inspiration and support throughout the development process.']}], 'duration': 246.688, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/jmznx0Q1fP0/pics/jmznx0Q1fP01140888.jpg', 'highlights': ['ml5.js leverages TensorFlow.js, initiated by Google researchers. (Relevance: 5)', 'ML5.js was funded by Google Pig Bikster Group, Google Big Picture Group, and People Plus AI Research Initiative. (Relevance: 4)', 'ML5 library is designed to have a symbiotic relationship with p5. (Relevance: 3)', 'Cristobal Valenzuela, creator of RunwayML, is associated with ML5 library. (Relevance: 2)', 'Yining Shi and Pix2Pix models were ported into ML5, expanding the library. (Relevance: 5)', 'Hannah Davis focused on responsible data collection, encouraging exploration on ML5 website. (Relevance: 4)', 'Nikita Huggins played a crucial role in project management for the library. (Relevance: 3)', 'Dan Oved successfully ported the PoseNet model to TensorFlow.js and ML5.js. (Relevance: 2)', 'Involvement of guest artists and organizations provided inspiration and support. (Relevance: 1)']}], 'highlights': ['ML5.js leverages TensorFlow.js, initiated by Google researchers.', 'The playlist aims to provide a starting point for individuals who have heard about machine learning but are unfamiliar with the topic.', 'The content is meant for those who are new to the concept, without requiring them to have watched any other videos about machine learning on the channel.', 'Machine learning involves teaching a system to understand data without writing a specific algorithm, demonstrating the core concept of machine learning.', 'The chapter introduces tensorflow.js and TensorFlow as important components in the discussion of ML5.js, highlighting their relevance in the context of the ML5 project.', 'The discussion highlights the significance of p5.js, a special JavaScript library designed to be beginner-friendly and non-conforming to standard patterns.', 'TensorFlow.js enables machine learning tasks directly in JavaScript, providing an alternative to Python.', 'ML5 simplifies machine learning tasks, particularly for beginners, by providing additional functions.', 'Pre-trained models are increasingly used by corporations for tasks like facial recognition and speech-to-text conversion.', 'ml5.js was funded by Google Pig Bikster Group, Google Big Picture Group, and People Plus AI Research Initiative.']}