جبر خطی کاربردی برای یادگیری ماشین

Machine Learning is everywhere these days and a lot of fellows desire to learn it and even master it! This burning desire creates a sense of impatience. We are looking for shortcuts and willing to ONLY jump to the main concept. If you do a simple search on the web, you see thousands of people asking "How can I learn Machine Learning?", "What is the fastest approach to learn Machine Learning?", and "What are the best resources to start Machine Learning?" extit. Mastering a branch of science is NOT just a feel-good exercise. It has its own requirements. One of the most critical requirements for Machine Learning is Linear Algebra. Basically, the majority of Machine Learning is working with data and optimization. How can you want to learn those without Linear Algebra? How would you process and represent data without vectors and matrices? On the other hand, Linear Algebra is a branch of mathematics after all. A lot of people trying to avoid mathematics or have the temptation to "just learn as necessary." I agree with the second approach, though. extit: You cannot escape Linear Algebra if you want to learn Machine Learning and Deep Learning. There is NO shortcut. The good news is there are numerous resources out there. In fact, the availability of numerous resources made me ponder whether writing this book was necessary? I have been blogging about Machine Learning for a while and after searching and searching I realized there is a deficiency of an organized book which extbf teaches the most used Linear Algebra concepts in Machine Learning, extbf provides practical notions using everyday used programming languages such as Python, and extbf be concise and NOT unnecessarily lengthy. In this book, you get all of what you need to learn about Linear Algebra that you need to master Machine Learning and Deep Learning. Introduction Is Mathematics Painful? The Motivation How to Use This Book? Basic Linear Algebra Definitions Introduction Scalar and Vector Matrix Tensor Conclusion An Introduction to NumPy Introduction Data Types Basic Data Types Type Conversion Defining a NumPy Array Create an array from a list Special functions Universal functions Random array Basic Arithmetic Operations Array Manipulation Indexing Shaping Conclusion Matrix Operations Introduction Matrix Transpose Identity Matrix Adding Operation Scalar Multiplication Matrix Multiplication Matrix-Vector Multiplication Matrix Inverse Matrix Trace Matrix Determinant Special Matrices Conclusion Vector and Matrix Norms Introduction Vector Norm The Norm Function Properties Proving the Properties (Advanced) Most Used Norms L1 norm L2 norm Max norm Matrix Norm Conclusion Linear Independence Introduction The Concept Example The Relationship With Matrix Rank Linear Equations Conclusion Matrix Decomposition Introduction Matrix Eigendecomposition Eigenvector and Eigenvalue The Process Discussion on Matrix Eigendecomposition One Special Matrix Type and its Decomposition Useful Properties Using Python Singular Value Decomposition (SVD) Preliminary Definitions Matrix decomposition with SVD A Practical Implementation Applications of SVD Conclusion References Appendix A: The Notations Appendix B: Python Environment Index