Company: Pluralsight Author: Paolo Perrotta Full Title: How Machine Learning Works Year: 2019 Language: English Genre: Educational: Machine Learning Skill Level: Beginner Price: - - Files: MP4 (+ Exercise Files, Subtitles .SRT, Slides .PDF) Time: 02:22:43 Video: AVC, 1280 x 720 (1.778) at 30.000 fps, 200 kbps Audio: AAC at 96 Kbps, 2 channels, 48.0 KHz Machine learning is amazing… and intimidating. How can computers do magical things like understand images or text? This training for programmers will dispel the magic and help you to build your own computer vision program, starting from scratch. Machine learning is fascinating for programmers, but at the same time it can be intimidating because of all those math-heavy tutorials. In this course, How Machine Learning Works, you’ll learn the basics of machine learning from code. First, you will have a look at supervised learning, and you'll quickly move to coding your first learning program. Then, you'll discover how to improve that program line by line. Finally, you'll be writing the code all by yourself without resorting to obscure machine learning libraries. By the end of the course, you'll have a working computer vision program that recognizes handwritten characters, and you'll have practical knowledge of the foundational ideas of machine learning. Lessons: 1. Course Overview 01. Course Overview 2. Introduction 02. Getting to Know Machine Learning 03. Programming vs. Machine Learning 04. Supervised Learning 05. Approximating a Function 3. Building Your First Machine Learning Program 06. Tackling a Machine Learning Problem 07. Making Sense of Our Data 08. Understanding Linear Regression 09. Implementing Prediction 10. Understanding the Loss 11. Implementing the Training Algorithm 12. Running the Code 4. Improving the Algorithm with Gradient Descent 13. Our Algorithm Doesn't Cut It 14. Understanding Gradient Descent 15. Descending the Gradient in Three Dimensions 16. Calculating the Gradient 17. Implementing Gradient Descent 5. Expanding Regression to Multiple Variables 18. Dealing with a Complicated World 19. Tricking Away the Bias 20. Switching to Matrices 21. Shaping Data 22. Upgrading the Loss 23. Running Multiple Regression 6. Predicting Discrete Outcomes 24. Getting to Know Classification 25. From Regression to Classification 26. Introducing the Log Loss 27. Testing the Classifier 7. Recognizing Individual Digits 28. Introducing MNIST 29. Understanding the Test Set 30. Preparing the Images 31. Preparing the Labels 32. Recognizing a Digit 8. Figuring Out Image Recognition 33. Planning for Multiple Classes 34. Encoding the Labels 35. Updating the Weights 36. Updating Prediction 37. Running the Final Test 9. Seeing the Big Picture 38. From the Basics to the Perceptron 39. Understanding the Perceptron's Limitations 40. The Story So Far Our members see more. Join us! ------------- Our members see more. Join us!