To score a job in data science, machine learning, computer graphics, and cryptography, you need to bring strong math skills to the party.ÌýMath for ProgrammersÌýteaches the math you need for these hot careers, concentrating on what you need to know as a developer.
Filled with lots of helpful graphics and more than 200 exercises and mini-projects, this book unlocks the door to interesting-and lucrative!-careers in some of today's hottest programming fields.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
Even though, I went through lot of the machine learning mathematical material. Honestly, I could not recall them in an instant and failed interviews.
So - I am back to revise the content, refresh my understanding. Also if you are preparing or attending interviews. Do not get dis-hearted with failures.
The last interview was for an excellent Post-Doc position. It focused on Research & Software Engineering.
In that position, the interviewer opened his Google docs. He even asked me from Machine Learning. He asked me few basic questions, I was surprised, that I was able to recall.
What does this book cover?
Mathematical Ideas -Multidimensional spaces -Spaces of Function -Derivates and Gradients -Optimizing a function -Predicting data with functions -Calculus and Physical Simulation -Machine Learning Applications
Vectors, Scalars, Gradient: Gives rate of change in every direction for e [e is unit vector]
Inner product: Dot-product or Scalar product, remember as scalar product. In ML papers, you would notice, < > symbol Reduces dimensions
Outer product: Also called as cross-product When we take outer-product of two column vectors; u � v, We get matrix. Increases dimensions
Mathematics has a bad reputation for many people. It's hard to learn, it's hard to teach, and it doesn't have applications in the real world. I assume they mean that they will not use it.
Author Paul Orland teaches mathematics in a fun and interactive manner with programming. Orland uses Python to do all of the book's projects. He feels that teachers impart math incorrectly. Mathematicians do not discover math the way they teach it.
Math for Programmers teaches linear algebra, calculus, and machine learning applications. It does so by helping the reader develop a game. The game looks similar to Asteroids by Atari.
Linear algebra allows us to draw the figures and do transformations on them. With calculus, we can apply gravity to our game and give our rocketship realistic physics. The machine learning segment covers optical character recognition and fitting data with linear regression.
The book expects you to have some programming experience but nothing too in-depth. It doesn't mention how much experience you need, but it does say you need a strong history of programming.
I enjoyed the book, but I should have followed along with the exercises. Thanks for reading my review, and see you next time.